Faculty of Education and Social Sciences

UNIT: RESEARCH METHODS

Mr. James Allen Juma

jamesshungu@[Link]
0791716480

Open and Distance Learning Instructional

Material
 COURSE OVERVIEW
Research methods is an integral course that is important at the graduate and post graduate levels of
higher education. Skills gained in the course are applicable across various social science fields
such as education, economics, sociology, business administration, engineering among others.
Gaining some level of expertise in research methods can give students an edge in their academic
and professional lives as they become more articulate researchers in various professions in the
private sector, public sector and also in the non-government organizations.

Course Purpose
The purpose of this course is to introduce you to simple methods and skills in research. This course
primarily introduces you to problem identification and stating, proposal writing, simple research
methods in data collection, analysis and report writing.

Expected Learning Outcomes

By the end of the course, you should be able to:-
1. Explain the nature and types of research;

2. Explain the process of research proposal;

3. Identify a problem of research and describe the criteria for selecting it;

4. Explain the role of literature review in research;

5. Embrace the procedures in research, methodology and report writing;

COURSE OUTLINE
Week Topic/Lecture Sub Topic
1 INTRODUCTION TO RESEARCH CONCEPTS Definition of research
Methods of acquiring knowledge

Properties of scientific research methods

Characteristics of good research

Purpose of research

2 CLASSIFICATION OF RESEARCH Types of research

3 IMPORTANT TERMS IN RESEARCH Research terms
4 RESEARCH PROPOSAL Purpose of a research proposal
 Types of proposals

Structure of the research proposal

5 IDENTIFICATION OF A RESEARCH PROBLEM Criteria for selecting a research problem

Sources of research problems

Conditions of a good research problem

6 LITERATURE REVIEW Concept and purpose of literature review

Qualities of an effective literature review
Formulating the literature review
Sources and techniques of reviewing literature
Writing literature review

7 RESEARCH METHODOLOGY Concept of research design

Quantitative and qualitative research design

Characteristics of quantitative and qualitative research

designs
8 CENSUS AND SAMPLING Types of populations
Concept of sampling

Sampling designs

Errors associated with sampling

9 DATA COLLECTION INSTRUMENT Primary and secondary data sources

Data collection instruments

Types of questionnaire

Advantages and disadvantages of data collection methods

10 TESTS OF SOUND MEASUREMENT AND Concept of sound measurements Characteristics of good

MEASUREMENTS OF SCALE research instrument

Validity and Reliability

Concepts of measurements of scale

Levels of measurement

11 DATA ORGANIZATION, ANALYSIS AND Data preparation and preliminary analysis

PRESENTATION
Data analysis in quantitative and qualitative research

Hypothesis testing
12 ETHICAL AND LOGISTICAL ISSUES IN Logistical issues in research
RESEARCH Ethical issues in research
13 EMRGING TRENDS Identification of the emerging trends
Challenges of the emerging trends
Managing the challenges of the emerging trends

Teaching Methods
a) Tutorials

b) Class presentations

c) Discussions

Teaching Materials
a) Chalkboard

b) Instructional Materials

c) Research papers, projects etc.

Assessment
a) Continuous Assessment Test(s) 30%

b) End of semester examination 70%

TOPIC ONE

INTRODUCTION TO RESEARCH METHODS

Research is a systematic process of investigating/examining/understanding a problem or a
phenomenon with an aim of arriving at an effective solution to the problem.
Hence, you will realize that research is a means of acquiring knowledge. Knowledge is a body of information or
facts that is important for decision making.

Methods of Acquiring Knowledge

There are TWO main methods of acquiring knowledge (scientific Vs no-scientific)

a) Non-scientific Method:

The non-scientific method of acquiring knowledge is what we would sometimes refer to as

common place, or village talk. You acquire knowledge through unproven ways so it is likely to be
biased, subjective and with a lot of errors and personal biases. The following are example of the
ways we acquire knowledge non-scientifically: -

i. Personal experience/empirical source:

Human beings learn from the experiences they encounter in everyday life. When confronted by a
situation one tends to use a common experience encountered before. Over reliance on one’s own
experience can be very limiting.

ii. The authoritarian mode:

This is the common source of knowledge that depends on the authority and rigidity of adherence.
In many communities’ people rely on the wisdom of elders, clergy, politicians etc. who may be
recognized as having a better understanding of issues than ordinary members of society. Hence,
statements and pronouncements by such experts in various areas of knowledge are seldom
challenged.

iii. The mystical mode:

In this method, the rightfulness of knowledge is sought from or resides in the supernatural source.
The knowledge source is derived from prophets, diviners, medicine men among others.
These are the authority as they claim to receive and decipher messages from ancestral spirits.
iv. Tenacity

This mode entails people clinging to certain belief regardless of supporting evidence. People tend
to hold firmly to what they regard as the truth even when there are clearly conflicting facts - which
people have always known to be true despite contrary evidence.
v. Intuition

This knowledge is sometimes considered “common sense” or “self-evident”. It may subsequently

be proved false. It however forms a basis for scientific knowledge where convictions are
substantiated by factual evidence.

vi. Rationalistic method

Knowledge is derived through reasoning. The rationalistic method is based on human reason.
The basis of knowledge is correct reasoning which allows one to know is the truth by principle.

b) Scientific methods
Scientific process is one that involves systematic steps that define the problem, formulate the
hypothesis, gather the data, analyse and interpret results. Scientific research is a systematic,
controlled, empirical and critical investigation of natural phenomena guided by theory, hypothesis
or objectives to obtain information useful in understanding the phenomena or confirm any
presumed relations among the variables in such a phenomenon.

Properties of Scientific Research

The following are the characteristics of a scientific research:
i. Purposive
A good scientific research must have a definite aim or purpose. It should provide the research
objectives and delineate the research design that will be useful in collecting reliable data.
ii. Empirical
Research should involve reasoning from facts; it should be feasible and data based.
iii. Replicability
The findings from the hypothesis should be supported over and over again, if research is repeated
in similar circumstances since the findings are objective. The replicability gives confidence that the
research design is objective and can be relied upon.
iv. Systematic and logical
The research should involve systematic steps that should be followed with rigor.
v. Rigor
This connotes carefulness and the degree of exactitude in research. The research should be -
grounded on a good theoretical base and a sound methodology. Conclusions drawn from an
investigation that lacks a good theoretical foundation is unscientific. Basing research on a
grounded theoretical backing allows for the research to collect valid results.
vi. Objectivity
The conclusions drawn through the interpretation of the result should be objective and based on
facts resulting from the actual data and not from our own subjective or emotional values. The more
objective the interpretation of the data, the more scientific the research investigation.
vii. Generalisability
This refers to the scope of applicability of the research findings. The wider the range of
applicability of the solutions generated by research, the more useful the research is.
Generalisability will depend on how elaborate the sampling design is, the kind of instruments used
in data collection and objectivity shown in the interpretation of data.

Characteristics of a Good Research

i. Purpose clearly defined
The purpose of research should be clearly defined and sharply delineated in terms as unambiguous
as possible. The statement should be declarative clearly or explicitly revealing the variables to be
measured, the scope to be covered in terms of location and target population, and identifying
clearly the reasons for carrying out the research.

ii. Statement of problem clearly stated

The statement of the problem should be clearly stated to reveal the gaps in the literature, to clearly
express what other scholars in the field have discovered so as to determine the knowledge gap.

iii. Research process is detailed

The research procedures used should be described in detail to permit another researcher to repeat
the research. Significant sections and procedures in research should be stated and explained so as
to provide the validity and reliability needed.

iv. Research design thoroughly planned

The procedural design of the research should be carefully planned to yield results that are as
objective as possible. When a sampling of the population is involved, the report should include
evidence concerning the degree of representativeness of the sample.
 v. High ethical standards applied
A research design should not pose any physical or psychological risks to the participants. Ethical
guidelines as pertains to observing proper writing etiquettes such as avoiding plagiarism. The
research process should provide careful considerations to avoid possibilities of physical and
psychological harm, exploitation, invasion of privacy and loss of dignity.

vi. Limitations frankly revealed

Limitations in research do not refer to the challenges encountered in the research; they refer to the
flaws encountered in the procedural design. For example, if you are conducting a research on
leadership styles of an administrator and you use a self-assessment report, the procedural design of
such a study is limited in that there is a likelihood of having inflated results because the results are
based on self-assessment and perceptions.

vii. Adequate analysis of the data

This analysis of the data should be sufficiently adequate to reveal its significance and show that the
methods of analysis used are appropriate. The analysis of data should be accurate and correctly tied
to the research questions. It should be clear that the analyses obtained are responding to the
pertinent questions that probed the need to carry out the research. Depending on the purpose of
research, proper analysis should be conducted. For instance, if the research aims at describing the
phenomena, descriptive analysis should be used. However, if the research aims at finding
inferences such as relationships or differences in the study, then the inferential analysis should be
more appropriate.

viii. Findings presented clearly

The language used to report the research findings should be clear, precise, accurate and
unambiguous. The findings of the research should be presented in a prudent way with no
exaggerations, over-generalizations, or unnecessary verbiage that renders the research vague. The
presentation of the data should comprehensive, easy to understand and relevant to the decision
makers.

Purpose of Research
1. Discover new knowledge – The most important role is to discover new facts, their correct
interpretation and practical application. Research is the most efficient and reliable source of
knowledge as it seeks applicable truths and is also an accurate and reliable source of knowledge.
2. Describe a phenomenon - Accurate identification of any event involves thorough description of
size, shape, age, weight, colour, height, change over time, etc. It then provides knowledge that is
the basis for the other purposes of research.
3. Enable prediction - Prediction is the ability to estimate phenomenon. Given a set of
variables such as students’ attendance, we can predict the students’ performance.
4. Enable control - In research, control is concerned with the ability to regulate the
phenomenon under study. In this case, one phenomenon is manipulated in order to exert control
over another. For example, in a classroom set-up, a lecturer can use a teaching methodology that
involves active learning in one classroom and use passive teaching methodology in another
similar classroom to find out if there are significant differences in students’ performance.
5. Enable explanation of a phenomena - Explanation involves accurate observation and
measurement of a given phenomenon. In order to explain a phenomenon, one should be able to
describe it, predict its occurrence, and observe factors that cause its occurrence with certainty
and accuracy.
6. Enable theory development- Theory development involves formulating concepts, laws,
and generalizations about a given phenomenon. Research is conducted in an attempt to confirm
or validate existing theories.

TOPIC TWO
CLASSIFICATION OF RESEARCH
Different authors have classified research into various categories.
Qualitative research
It includes designs, techniques and measures that do not produce discrete numerical data. Qualitative data can be
collected through direct observation, participant observation or interview method. Qualitative research includes
an “array of interpretive techniques which seek to describe, decode, translate and otherwise come to terms with
the meaning, not the frequency, of certain more or less naturally occurring phenomena in the social world.
Qualitative research aims to achieve an in-depth understanding of a situation. Qualitative research is designed to
tell the researcher how (process) and why (meaning) things happen as they do. Qualitative techniques are used at
both the data collection and data analysis stages of a research project. At the data collection stage, the array of
techniques includes focus groups, individual depth interviews, case studies, ethnography, grounded theory, action
research and observation. During analysis, the qualitative researcher uses content analysis of written or recorded
materials drawn from personal expressions by participants and behavioral observations.

Quantitative research
It includes designs, techniques and measures that produce discreet numerical or quantifiable data.

Advantages of using both qualitative and quantitative methods

1. Since in many cases a researcher has several objectives, some of these objectives are better
assessed using quantitative methods.
2. Both methods supplement each other i.e. qualitative methods provide the in-depth explanations
while quantitative methods provide the data needed to test hypotheses.
3. Since both methods have a bias, using both types of research helps to avoid such bias in that each
method can be used to check the other.

Disadvantages of using both qualitative and quantitative methods

1. It is expensive
2. Researchers may not have sufficient training in both methods to be able to use them effectively.

CLASSIFICATION OF RESEACH

Classification by purpose
1. Basic / Pure / Fundamental Research
Basic researchers are interested in deriving scientific knowledge i.e. they are motivated by intellectual curiosity
and need to come up with a particular solution. It focuses on generating new knowledge in order to refine or
expand existing theories. It does not consider the practical application of the findings to actual problems or
situations.
2. Applied research
It is conducted for the purpose of applying or testing theory and evaluating its usefulness in solving problems. It
provides data to support a theory, guide theory revision or suggest the development of a new theory.
3. Action research
It is conducted with the primary intention of solving a specific, immediate and concrete problem in a local setting
e.g. investigating ways of overcoming water shortage in a given area. It is not concerned with whether the results
can be generalized to any other setting.
4. Evaluation Research
It is the process of determining whether the intended results were realized.

Types of evaluation research

i. Needs assessment
A need is a discrepancy between an existing set of conditions and a desired set of conditions. The
results of needs assessment study provide the foundation for developing new programs and for
making changes in existing ones. ii.
Formative evaluation
Helps to collect data about a program while it is still being developed e.g. an educational program, a marketing
strategy etc.
iii. Summative evaluation
It is done after the program has been fully developed. It is conducted to evaluate how worthwhile the final
program has been especially compared to similar programs.

Classification by methods of analysis

1. Descriptive research

It is the process of collecting data in order to test hypotheses or to answer questions concerning the current status
of the subjects in the study. It determines and reports the way things are. It attempts to describe such things as
possible behaviour, attitudes, values and characteristics.
Steps involved in descriptive research
 Formulating the objectives of a study
 Designing the methods of data collection
 Selecting the sample
 Data collection
 Analyzing the results
2. Causal-comparative research

It is used to explore relationships between variables. It determines reasons or causes for the current status of the
phenomenon under study. The variables of interest cannot be manipulated unlike in experimental research.
Steps in causal-comparative research
  Define the research question
 Select a group that possesses the characteristics, which the researcher wants to study.
 Select a comparison group which does not display the characteristics under study but which is
similar to the group in other respects.
 Collect data on both the experimental and control groups
 Analyze the data
Advantages of causal-comparative study
 Allows a comparison of groups without having to manipulate the
independent
variables
 It can be done solely to identify variables worthy of experimental investigation  They are
relatively cheap.
Disadvantages of causal-comparative study
 Interpretations are limited because the researcher does not know whether a particular variable is a
cause or result of a behaviour being studied.
 There may be a third variable which could be affecting the established relationship but which may
not be established in the study.

3. Correlation Methods

It describes in quantitative terms the degree to which variables are related. It explores relationships between
variables and also tries to predict a subject's score on one variable given his or her score on another variable.
Steps in correlational research
 Problem statement
 Selection of subjects
 Data collection
 Data analysis

Advantages of the correlational method

 Permits one to analyze inter-relationships among a large number of variables in a single study.
Allows one to analyze how several variables either singly or in combination mig
Classification by type of research

[Link] Research
A survey is an attempt to collect data from members of a population in order to determine the current status of
that population with respect to one or more variables. Survey study is therefore a self-report study, which requires
the collection of quantifiable information from the sample. It is a descriptive research.

Steps involved in Survey research

Problem statement
Defining Objectives
 Selecting a Sample
 Preparing the instruments
 Data analysis
Purpose of survey research
i. It seeks to obtain information that describes existing phenomena by asking individuals about
their perceptions, attitudes, behaviour or values.
ii. Can be used for explaining or exploring the existing status of two or more variables, at a given
point in time.
iii. It is the most appropriate to measure characteristics of large populations.
Limitations of Survey research
i. They are dependent on the cooperation of respondents. ii. Information unknown to the respondents cannot
be tapped in a survey e.g. amount saved per year
iii. Requesting information which is considered secret and personal, encourages incorrect answers.
iv. Surveys cannot be aimed at obtaining forecasts of things to come.

2. Historical research

Involves the study of a problem that requires collecting information from the past

Purpose of Historical Research

 Aims at arriving at conclusions concerning causes, effects or trends of past occurrences that
may help explain present events and anticipate future events.
 Attempts to interpret ideas or events that had previously seemed unrelated.
 Synthesizes old data or merges old data with new historical facts that the researcher or other
researchers have discovered.
 To reinterpret past events that have been studied.
Steps involved in historical research
 Identifying and delineating the problem.
 Developing hypothesis or hypotheses that one is interested in testing.
 Collecting and classifying resource materials, determining facts by internal and external
criticism.
 Organizing facts into results
 Interpreting data in terms of stated hypothesis or theory.
 Synthesizing and presenting the research in an organized form.
3. Observational Research

The current status of a phenomenon is determined not by asking but by observing.

This helps to collect objective information.
Steps
 Selection and definition of the problem.
 Sample selection.
Definition of the observational information. Recording observational
information Data analysis and interpretation.

Types of observational research

1. Non-participant observation
The observer is not directly involved in the situation to be observed.
2. Naturalistic Observation
Behavior is studied and recorded as it normally occurs.
3. Simulation observation.
The researcher creates the situation to be observed and tells subjects to be observed what activities they are to
engage in. Disadvantage – the setting is not natural and the behavior exhibited by the subjects may not be the
behavior that would occur in a natural setting.
4. Participant observation
The observer becomes part of or a participant in the situation. May not be ethical
5. Case studies
A case study is an in-depth investigation of an individual, group, institution or phenomenon. It aims to
determine factors and relationships among the factors that have resulted in the behavior under study.
6. Content analysis
It involves observation and detailed description of objects, items or things that comprise the sample. The
purpose is to study existing documents such as books, magazines in order to determine factors that explain a
specific phenomenon.
Steps
 Decide on the unit of analysis
 Sample the content to be analyzed
 Coding
 Data analysis
 Compiling results and interpretations.

Page 15 of 78
Prepared by Mr. James
Advantages
 Researchers are able to economize in terms of time and money.
 Errors that arise during the study are easier to detect and correct.
 The method has no effect on what is being studied.
Disadvantages
 It is limited to recorded communication.
 It is difficult to ascertain the validity of the data.

Page 16 of 78
Prepared by Mr. James
 TOPIC THREE

DEFINITION OF IMPORTANT TERMS IN RESEARCH

Research Language
It is important for you as a researcher to acquire a sound understanding of the basic terms used
in research. This acquisition of language is important for the better understanding of the
research process as will be outlined in the subsequent chapters.
1. Population - This is the entire group of individuals, events, that have a common
observable characteristic and it is connoted as “N”. Although the general term
“population” refers to the universal or entire group in the universe. Ideally,
researchers would like to generalize results to the absolute population and this
population is referred to as the “Target population”. However, because of the
members of a given population may be large or scattered over a wide geographical
area, researchers draw their samples from “accessible” population which is more
narrowly defined and manageable. An example of accessible population would be:
“All standard eight pupils in Meru District”.
2. Sample - This is a carefully selected sub-group of the accessible population that is a
representative of the whole population with the relevant characteristics and is
connoted as n.
3. Sampling - This is the process of selecting a number of individuals for the study. It
can be random, stratified, cluster, systematic, snow ball, convenience, etc.
4. Sampling Frame - This is a list, directory, or index of cases from which a sample is
selected e.g., national census lists, list of professionals, list of income tax payers, list
of enrolled students etc.
5. Probability sampling - This is the sampling technique that is applied when the
population is known; that is when the list of all the members in the population either
target or accessibility is known and everyone has an equal chance of being selected
in the sample. It uses random, stratified, and systematic sampling methods.
6. Non-probability sampling- This is the sampling technique that is applied when the
list of the members in the population is not known or where a sampling frame does
not exist. For instance, it would be difficult to have a list of all the mentally
challenged in the society because probably not even our hospitals have the
comprehensive list. Thus in this technique, the members of the population do not
have an equal chance of being selected and it uses purposive, convenience and
snowballing sampling methods.
Page 17 of 78
Prepared by Mr. James
7. Parameter - This is a measurable characteristic that can assume different values in
the population. The difference between parameter and variable is that while the
variable is related to the characteristic of a sample drawn from a population,
parameter refers to the population characteristic.
8. Statistics - This is the science of organizing, describing, and analysing quantitative
data. The term statistics refer to the indices which are derived from data through
statistical procedures. An index which is descriptive of a sample is called a statistic;
whereas an index which is descriptive of a population is a parameter.

9. Variable - This is a measurable characteristic that assumes different values among

the subject in a sample e.g., gender (male/female), age (years), height (inches),
occupation etc.
10. Independent variable - This is the variable that is manipulated by the researcher. It
is also referred to as experimental or treatment variable. It influences the outcome of
the study. For example, we can say, a student’s success in school is influenced by
their study habits, time management, class attendance and involvement, etc.
11. Dependent variable - This is the outcome variable; in our example above, the
dependent variable would be student’s success in school.
16. Theory - This is an explanation of how one or more variables are related to other
variables. A theory provides the basis of establishing a hypothesis and is derived
from existing literature or knowledge e.g., theories on HIV transmission.
17. Hypothesis - This is the researcher’s anticipated explanation or opinion regarding
the result of the study. There are three types of hypothesis: Null hypothesis, alternate
(no directional) hypothesis and alternate (directional).
18. Null hypothesis - This is the default state of nature. It assumes that there is no
relationship or difference between variables and that any occurrence of a relationship
happens by chance e.g., we assume someone is healthy until proven sick.
19. Alternate hypothesis - This is the research hypothesis which represents the
researcher’s anticipated explanation.
23. Sampling errors: this is a discrepancy between the characteristics of a population
and the characteristics of a sample. This error is inherent in every sample because it
is almost impossible to have a sample that is a replica of the population in which it is
derived from. It is denoted with Greek letter alpha. This kind of error is non-
systematic, because it could be a case of an outlier being included in the sample.

Page 18 of 78
Prepared by Mr. James
 24. Sampling bias - This is the discrepancy that results because of the decision or
choices of a researcher or because of the research process. The researcher may have
included or excluded some important cases in the study, or respondent non-response
could cause a sampling bias. For example, the polls done before an election, may not
be a true representative of the population because of non-respondents.
25. Data - This refers to all the information a researcher gathers for his/her study. There
are two types of data: primary data and secondary data. Primary data refers to the
information a researcher obtains from the field e.g. using questionnaires whereas,
secondary data refers to the information a researcher obtains from the research
articles, books, etc. Data may also be classified as quantitative (numerical) or
qualitative (words/ phrases).

Self-Assessment Questions
1. Define at least ten research terms using your own words?

Page 19 of 78
Prepared by Mr. James
 TOPIC FOUR
RESEARCH PROPOSAL
The Research Proposal
A research proposal is a blue-print or a guide to the systematic study of a topic. It is a written
summary of what a researcher intends to do. A proposal is also known as a work plan,
prospectus, outline, statement of intent or a draft plan that tells us what, why, how, where, and
to whom it will be done.

Purpose/ importance of a research proposal

a. It makes known one’s intention of getting involved with research work and this is
done by the researcher spelling out the objectives of his/her study.

b. The process of writing a proposal allows the researcher to plan and review the steps

will be undertaken in the project. It gives the researcher an opportunity to spot flaws in the
logic, errors in the assumptions, and even problems that are not adequately addressed by the
objectives and design of the study.
c. It provides justification for funding, as it justifies the use of the resources.

d. After the proposal is done and approved, the document serves as a guide for the
researcher throughout the investigations as progress is monitored.

e. The proposal provides a basis for evaluation of the document. It gives the
researcher’s advisor a basis for assisting the researcher.

f. A well-designed research proposal helps the researcher to avoid the tiring and time
consuming alterations once the research project takes off.

g. The proposal ensures that time management and budget estimates are adhered to.
These estimates allow researchers to plan the project in such a way that the work
progresses steadily towards the deadline.
h. A proposal provides an opportunity for the researcher to discuss the research
efforts of others who have worked on the related areas.

i. A proposal is also able to suggest the data necessary for solving the problem and
how the data will be gathered, treated and interpreted.

Types of proposals
i. Research proposal - This is the most commonly written proposal in academic write-
ups. Its aim is to define a problem, show the need to study the problem, what other
Page 20 of 78
Prepared by Mr. James
 researchers’ in the field have studied to identify the gaps in the literature and to
provide the benefits that various stakeholders will acquire from the research findings.
ii. Evaluation proposal - This proposes to evaluate solutions. This kind of proposal
evaluates the cost and benefit associated with various solutions to the problems. It
determines and measures certain criterions such as cost, safety measures and value for
money etc.
iii. Implementation proposal - It proposes to implement solutions. This can also be
referred to as applied research. The researcher identifies a problem and implements a
solution to find out if it has solved the problem e.g., when a researcher develops a
project to solve a societal problem.

Structure of the Academic Research Proposal

Research proposal writing format
(a) Title page
This page is centred vertically and horizontally and should be numbered. It is not listed on the
table of contents. It contains the title of the proposal, full names of the candidate and
registration number, statement of fulfilment, name of the institution and the submission of year
of the proposal. The title should be clear. It should show clearly what the variables of the study
are, what the study is about and comprehensive in that it should state the target group to be
studied.
For example, a study of the factors that enhance organizational commitment of employees: A
case study of Nakumatt Supermarkets.

(b) Other Preliminary pages

These pages should start from number two (ii). All should be numbered using lower case
roman numerals.
(i) Declaration and Dedication page
• Declaration;

The candidate makes a declaration using the following words:

“I declare that this research proposal is my original work and has not been presented in any
other university”.
Signed………….…….. Date……………………
• On the same page a recommendation is made using the following words:

Page 21 of 78
Prepared by Mr. James
“This research proposal has been submitted for examination with our approval as university
supervisors”.
Signed………………………………. Date……………………
Name……………………..…………
Signed………………………..……. Date……………………
Name…………………………..……

(ii) Abstract

This should be approximately three quarters of a page. It should be comprehensive including

all the major elements in the research, with no paragraphs and should not contain any sub-
headings.

(iii) Table of Contents

The table of contents is supposed to help the reader to quickly identify the contents of the
proposal. It should therefore, only contain the First Level (Chapter Number and Chapter Title)
and Second Level (Sub-headings) for each First Level heading. The Table of Contents should
contain the following: Chapter numbers and titles. There are three (3) chapters:
CHAPTER ONE: INTRODUCTION
CHAPTER TWO: LITERATURE REVIEW
CHAPTER THREE: METHODOLOGY/METHODS AND MATERIAL

(iv) List of Tables

Starts on a new page and should contain the number of the tables, the title, and the page
number where the table is located in the proposal. The numbering of the tables should be from
1 to the last. The title of each table should be precise and descriptive of the table of contents,
and placed on top of the table. Other details are as per APA manual.

(v) List of Figures

Starts on a new page, and should contain the number of the figure, the title and the page
number where the figure is located in the proposal. The numbering of the figures should be
from 1 to the last. The title of each figure should be precise and descriptive of the figure
contents and placed at the bottom of the figure. Other details are as per the APA manual.

Page 22 of 78
Prepared by Mr. James
 (vi) Abbreviations and Acronyms

Starts on a new page and should contain only the abbreviations and acronyms used in the
proposal; all listed in alphabetical order.

CHAPTER ONE - INTRODUCTION

The numbering of the whole proposal starts from here with No:1 (Arabic) as the first page
continuing up to the last page of the proposal. The chapter should have the following sections:

(i) Background of the Study

It gives a background of what is to be studied, and should not be more than three pages. The
section sets the stage for the study and puts the topic in perspective and ends with general
statements about the need for the study. In this section, it is expected that the research will be
addressed from various perspectives such as the world/global perceptive, narrowing down to
continental, regional and local perspectives as literature permits. The issues to be addressed are
the variables in the study in relation to the participants your study is about. Hence if you study
is on factors influencing retention of students in free public schools, your background
information should target retention policies across the world in relation to the Kenyan situation.
So although information on Free Primary Education in Kenya may be relevant it should not
take the centre stage of your research. In addition, it is important that the background of the
study systematically leads the reader to the statement of the problem. The research process
should assume the shape of an inverted triangle in which we move from broad to specific.

(ii) Statement of the Problem

This is the focal point of the study. It precisely indicates the situation (need or gaps) between
the actual and the ideal state. Since the stage has already been set in the background of the
study, the statement of the problem should be precise, specific and clear enough to be easily
identified. In addition, gaps as illustrated by other researchers should be addressed. As you
summarise this section, a statement of the problem is required and should be about three
sentences to avoid ambiguity. For example, after delineating the gaps, the summary of the
statement of the problem should be stated clearly for instance, the problem of this research is
that, no study has been conducted on retention of students in free public institutions in Kenya.

(iii) Purpose of the Study

This section states precisely the ultimate goal or aim of the study which should be stated in one
sentence. The purpose should be precise, specific and clear.
Page 23 of 78
Prepared by Mr. James
 (iv) Objectives
They are derived from the statement of the problem. We derive the objectives of the study
from the purpose of research or statement of the problem by operationalizing the main
variables. For instance, if you intended to continue with the research on factors influencing
retention of students; you can delineate the factors by coming up with specific factors that you
would want to assess their effect on retention. Hence, a research objective should be a clear
concise statement(s) that informs on what the researcher seeks to do/achieve by the end of the
study. Objectives indicate the anticipated products/results that are expected to be met by the
researcher so as to accomplish the purpose. They should indicate what needs to be described.
Active verbs, such as: “to develop, to determine, to describe, to assess, to incorporate, to
explore, etc.” should be used.

These should be stated clearly so that they can act as a good guide on what is to be done.

(v) Research Questions/Hypotheses

• Research questions are central to both qualitative and quantitative research. They
indicate clearly what you want to know and they focus on the study. They clarify
relationships among variables and support competing hypotheses or theoretical
views. Research questions can be used to delineate the variables in the research
objectives to make them clearer and measurable. They always correspond to the
research objectives. Example: “Is there any relationship between employee training
and voluntary turnover of business development officers in XYZ Company?” or
“What are the factors that influence successful implementation of projects in XYZ
Company?”. It should be noted that the research questions are the same as
objectives but the latter are converted into questions.
• Hypotheses are testable statements derived from an intelligent guess about a

relationship. It is the researcher’s anticipated explanation or opinion regarding the results of the
study. It may be directional or non-directional, and is based on findings of previous research
gained from a thorough literature review. Variables must be clearly operationalized. If you
state hypotheses in your study, you must plan to test them and show clearly in the methodology
sections how the testing will be done.
• Depending on the type of study, you can choose either research questions or
hypotheses. Example of a hypothesis include: “There is no significant relationship
between employee training and voluntary turnover of business development

Page 24 of 78
Prepared by Mr. James
 officers in XYZ Company.” Depending on the statement of objectives or research
questions, one can have both research questions and hypotheses. This will be the
case if some objectives cannot be converted into hypothesis; as such no testing is
required.

(vi) Justification of the Study (1 to 2 paragraphs)

This is also known as rationale of the study and it provides a rationale to justify the reason for
the study. It answers the questions: “why is the study important?” “To whom is it important?
and “What benefit will occur if the study is done?”

(vii) Limitations of the Study (1 to 2 paragraphs)

These are the characteristics of the design or methodology that set parameters on the
application and interpretation of the results of the study. They are factors that constrain on the
generalization of the findings.

(viii) Delimitation of the Study (1 to 2 paragraphs)

These are the characteristics selected by the researcher to define the boundaries of the study.
The researcher makes inclusionary or exclusionary decisions regarding the sample and the
variables studied.

(ix) Assumptions of the Study

In the process of the study, there are some areas that the researcher will assume that they will
have no effect on the data interpretation (i.e. internal and external validity). Such assumptions
may relate to validity and reliability of measuring instruments, representativeness of the sample
taken and honesty in the subjects in making the appropriate responses. The assumptions make
it possible for the researcher to continue to undertake the study with a reasonable degree of
confidence.

(x) Operational Definition of Terms

All terms that may assume a unique meaning in the study should be defined under this section.
This may include terms that the researcher may think are new to the audience.

CHAPTER TWO – LITERATURE REVIEW

This chapter reviews what previous book writers or researchers have written or found out,
respectively, in the area. The length will depend on how much work has been done previously

Page 25 of 78
Prepared by Mr. James
in the area. If one is planning to explore a relatively new area, the literature for review may be
limited, but there is always related literature. The review will help the researcher know
whether the area being explored is new and if not the existing gaps. In case the intended area of
study has exhaustively been studied, then one has to look for another area unless there is a need
for replication. The literature review should adequately cover the objectives of the research.

Conceptual framework: This is a brief explanation of the relationships between the variables
identified for study in the statement of the problem, objectives and research questions. It is
always depicted diagrammatically showing the relationships between the independent and
dependent variables as well as any anticipated intervening variables (if any). If there is
reviewed literature that has indicated the theoretical model or framework similar to what is
under study, then it should be included as theoretical framework. Theoretical framework
should come before the conceptual framework.

CHAPTER THREE – RESEARCH METHODOLOGY

a) Introduction – should state what is contained in this chapter, namely, research design,
target and population, sampling, preparation of data collection instruments/instrumentation,
data collection procedures and methods of data analysis.
b) Research design – should discuss the design used in the study and the reason why that
design was selected. The designs may be survey correlation, experimental, ex-post facto
research design.
c) Target population - Provide a description of the population to be studied. Indicate the
population characteristics, including size and why it has been chosen.
d) Sampling procedure – This discusses how the sample is to be selected, and sample
size. Use a sampling matrix to show the population and selected sample.
e) Instrumentation - This refers to the tools that will be used to collect the data such as
questionnaires, interviews etc.
f) Methods of data collection- should discuss issues related to data collection and
procedures for administering the data instruments in the field. It should also address how
reliability and validity will be assessed in the research.
g) Methods of data analysis – should discuss issues related to qualitative and quantitative
methods of data analysis and relate them to research questions. For each research question,
one should show how he/she will analyse the variable and their relationships or differences.
Describe the type of statistical methods that will be used and justification as to why the
statistics have been prepared.

Page 26 of 78
Prepared by Mr. James
Reference List
• It should start on a new page and contain the list of all the books and journals cited in
the proposal.
• It should not have any materials not cited in the proposal nor should the proposal
have any materials not cited in the list of references. However, if the researcher
referred to any books or journals that are not directly referred to in the proposal, then
these should be listed under BIBLIOGRAPHY.
• The listing of the books or journals should be as per the Publication Manual of the
American Psychological Association (APA). (APA guidelines will be attached
alongside this document).
NB Refer to the APA manual on the appendix pages of this document and read on how we use
APA in referencing and in-text citations. Review you literature review and make sure you are
citing as per the APA guidelines.

Page 27 of 78
Prepared by Mr. James
 TOPIC FIVE
IDENTIFICATION OF A RESEARCH PROBLEM
How is a research problem identified?
The method of identifying, selecting and formulating a research problem begins with the
general and ends with a specific. It should be understood that a research problem in general,
refers to some difficulty, vague situation or puzzles which a researcher experiences in the
context of either a theoretical or practical encounter, or wants to obtain an explanation,
clarification or solution for the same.

Problem identification consists of a review of previous studies to reveal existing knowledge

and truth about the research or topic of study. The studies describe the current situation of the
problem. It also states whether the research idea is a gap in knowledge, a repeat of previous
research, an exploration of new ideas, search for unknown areas, or a social concern among
others.

There are procedures for identifying a research problem:

o Identify the broad area that one is interested in. It should be related to the profession

interest and goals of the researcher

o Identify a specific problem within it that will form the basis of the study.

The following questions should be noted (According to Ngechu, 2002)

 Is the research idea a specific problem?

 Can it be stated as a question?
 Is the idea researchable?
 Can it be defined in operational terms?
 Is it worth investigating?
 Is it a question needing answers or solutions worth recording for sharing?
 The area in which the problem is situated
 The point at which one starts searching for literature
 Characteristics of the problem.

Page 28 of 78
Prepared by Mr. James
Sources of a Research Problem
Research problems can be identified from the following sources
i. Your observations - These can be a problem in your area or some specific
observations you would like to test or hypothesis.
ii. Personal experiences – First hand observations and reflection of an intriguing
experience could be sources of the research problem.
iii. Existing relevant literature – A systematic reading program in the general area of
interest is perhaps the best way of locating specific research problems. Some research
reports also make suggestions about what further studies need to be done. Text books
and articles on the specific area give the researcher some background information.
iv. Existing theories - A theory contains generalizations that must be investigated
because it

literally is a theory and not a body of facts/

v. Discussions with experts/Research oriented people - Discussions on general topics
either in class or seminars are sources of current problems.
vi. Media - Issues which are frequently reported in the media can also form the basis
since

they are important to the majority of people.

Factors to consider when identifying a research problem

• lead to findings that have widespread implications in a particular area

• challenge some commonly held truism

• review the inadequacies of existing laws, views or policies

• cover a reasonable scope e.g. not too narrow or too general.

Conditions for a good research problem

• There must be an individual (or group, organization, or community) to whom the
problem could be attributed since individuals occupy an environment e.g., schools in
urban areas or Arid and Semi-Arid Areas (ASALs)
• There must be at least two lines of action to be pursued in the solution to the problem
which is defined by one or more variables of the controlled or identified variables e.g.,
low access to education among pupils in pastoral or urban areas is attributed to poverty

Page 29 of 78
Prepared by Mr. James
 and retrogressive practices. Thus poverty and retrogressive practices become the lines of
action to be pursued.
• There must be at least two possible outcomes of the lines of action of which one must be
preferable to the other i.e. there must be at least one outcome that the researcher wants.
• The course of action available (altering poverty and cultural retrogressive practices)
must provide some chance of attaining the objectives, but they cannot provide the same
chance. In other words we can say that the choice (of causative) must have unequal
efficiencies for that desired outcome.

Stating the problem

A research study starts with a brief introductory section. The researcher introduces briefly the general area of
study, and then narrows down to the specific problem to be studied.

Characteristics of a good problem statement

 It should be written clearly and in such a way that the readers interest is captured immediately.
 The specific problem identified in the problem statement should be objectively researchable
 The scope of the specific research problem should be indicated
 The importance of the study in adding new knowledge should be stated clearly
 The problem statement must give the purpose of the research.

Activity
Identify at least three research problems

Stating the purpose

The purpose of a study crystallizes the researchers inquiry into a particular area of knowledge in a given field.
If the purpose is accurately expressed, the research process will be carried out with ease.
The purpose of the study should meet the following criteria:
 It must be indicated clearly, unambiguously and in a declarative manner.
 The purpose should indicate the concepts or variables in the study.
 Where possible, the relationships among the variables should be stated.
 The purpose should state the target population.
 The variables and target population given in the purpose should be consistent with the
variables and target population.
In stating the purpose of the study, the researcher should choose the right words to convey the focus of the
study effectively. Use of subjective or biased words or sentences should be avoided.

Page 30 of 78
Prepared by Mr. James
Examples
Biased Neutral
To show To determine
To prove To compare
To confirm To investigate
To verify To differentiate
To check To explore
To To find out
demonstrate To examine
To indicate To inquire
To validate
To explain To establish To
To test
illustrate

Stating the Objectives

Research objectives are those specific issues within the scope of the stated purpose that the researcher wants
to focus upon and examine in the study.
Objectives guide the researcher in formulating testable hypotheses.
In stating the objectives of the study, the researcher should choose the right words to convey the focus of the
study effectively. Use of subjective or biased words or sentences should be avoided.

Characteristics of a good objective

Specific:
 Measurable
 Achievable
 Reliable
 Time bound

Introduction to Hypothesis
Hypothesis is an educated guess. Research hypothesis is a statement describing an unknown
but tentatively reasonable outcome for existing phenomena. It is a tentative answer regarding
what the researcher considers as ought to be the possible outcome of an existing problem. It is
a likely answer or solution to a problem being studied, which is stated in advance before the
actual research is undertaken. It expresses an expectation regarding how variables are related
or different and what the researcher suspects would be the outcome. For instance, a lecturer
may want to state the following hypothesis.
“There is a significant difference between students undertaking distance learning and those in
full time mode in their ability to understand research methods course.” This is a hypothesis
and it is now up to the lecturer to collect the relevant data to test the hypothesis.

Page 31 of 78
Prepared by Mr. James
Activity
From the stated research problems in your previous exercise, can you come up with at least two
hypotheses for each of the research problems?

Types of hypothesis
There are two main types of research hypothesis:
• Null hypothesis

• Alternate hypothesis

a) Null hypothesis (Ho)

The null hypothesis is the one you test and hope to prove wrong, reject or nullify. The main
objective is to show the null is false and hereby accept the alternative hypothesis. This is also
referred to as the default state of events. Knowing no other information, you would not expect
any two variables to be related or any two groups to be different, until a study is done that
either proves or disapproves the null hypothesis.

Example of null hypothesis showing differences in groups:

Ho: there is no significant difference between students from distance learning mode and those
of full time in their performance on a research method course. If we wish to show that a
difference exists among the two groups of students, we must prove it.

Example of null hypothesis showing relationships in variables:

Ho: There is no significant relationship between attendance and performance in research
methods class

b) Alternative hypothesis (H1) this is also known as the researchers’ hypothesis

The alternative hypothesis asserts that the value of relationship specified in the null is not true.
You test the null hypothesis. An alternative hypothesis simply negates the null and is also
called non-directional alternative. This usually refers to what you as the researcher expects
after carrying out the study.
H1: There is a significant difference between students from the distance learning mode and
those of full time in their performance on research methods course. (In this case, this is a non-
directional hypothesis, because we have not stated who in the two groups will perform better or
worse than the other).
H1: There is a significant relationship between attendance and performance in research methods
class. Depending on the direction of the hypothesis we can have directional and non-
Page 32 of 78
Prepared by Mr. James
directional hypothesis. Directional hypothesis, the researcher makes an assumption of the
direction of the relationship between variables, however in the non-directional he does not.
Hence, in the example above, a directional alternate hypothesis would be stated as follows: H 1:
There is a significant positive relationship between attendance and performance in research
methods course.

Characteristics of a good hypothesis

1. Hypothesis should state the relationship between two or more variables. It should
show differences between two or more groups.
2. The hypothesis should be reasonable and consistent with the existing body of
knowledge.

3. Hypothesis should be testable and verifiable.

4. It should be clear and as brief as possible.

5. Hypothesis gives the research the purpose by providing the direction of the study and
nature/kind of data to be collected.
6. Must be as simple and as concise as the complexity of the concepts involved allows.

Assumptions and Limitations

 An assumption is any fact that a researcher takes to be true without actually verifying it. It puts some
boundary around the study and provides the reader with vital information, which influences the way
results of the study are interpreted.
 A limitation is an aspect of a research that may influence the results negatively but over which the
researcher has no control. A common limitation in social science studies is the scope of the study, which
sometimes may not allow generalizations.
Sample size may also be another limitation.

TOPIC SIX
LITERATURE REVIEW

Page 33 of 78
Prepared by Mr. James
What is Literature Review?
Literature review refers to the identification, location reading and evaluation of various relevant documents
related to the problem or issue under investigation. The term is also used to refer to the works the researcher
has consulted in order to understand and investigate the research problem. In other words, literature review
consists of an account of what has been published on a topic by accredited scholars and researchers. It is
however, important to note that review of related literature should be a critical analysis of the works
consulted.

Importance of literature review

• It gives the researcher an insight to what has been done in the field as well as pinpointing its
strengths and weaknesses. This guides the researcher in formulating the theory that identifies the
gaps in the knowledge.
• It helps in developing a significant problem which provides further knowledge in the
field of study.
• It helps delimits the research problem thus giving it a focus.
• It helps in formulating and justifying the hypotheses, research questions and objectives thus
clearly exposing the variables.
• Wide review of literature exposes the researcher to a variety of approaches of dealing
with the research issue. This contributes to a well-designed methodology.
• It helps in developing an analytical framework or basis for analyzing and interpreting data.

Qualities of an effective literature review

• It should be critical, organized and analytical in orientation.

• It should justify the need for the study by identifying the gaps and controversies.

• It highlights the relationship between the past and the current study.

• It helps define the research problem by putting the research into perspective

Guidelines in formulating literature review

• Identification of key issues to be addressed by the literature review

• Formulating preliminary statement of the problem to help in material selection.

• Identification of sources of information i.e., books, articles journals and other relevant
publications.

Page 34 of 78
Prepared by Mr. James
 • Analyzing critically the identified articles.

• Classifying and coding the article as well as making notes or paraphrasing any relevant literature.

• Creating an outline for the review by noting the main points and categorizing into
logical subheadings.
• Synthesizing the information gathered with respect to variables.

• Writing the review of related literature by:

- Selecting studies that relate most directly to the problem at hand

- Tying together results of the studies to make their relevance clear

- Indicating the research gap for the reviewed areas

- Organizing the reviewed literature along relevant major points

- Giving the reader some indication of the relative importance of the reviewed
studies.

Sources of Literature
Primary source
This is a document authored or composed by the person who generated the ideas. It can also be
used to refer to the record of information that a particular researcher was responsible from a
sample collection of the population. Primary information also refers to ideas contained in a
book or document published by an author. It includes documents such as:
- Official reports

- Speeches

- Authentic letters

- Eyewitness accounts

- Original research reports

- Books

- Essays

- Stories authored by novelists and scholars

- Artistic materials such as paintings, photographs, newsreels, music coins, artifacts,

etc.
Page 35 of 78
Prepared by Mr. James
Secondary source
This is a document that is constructed from primary sources by a person who was not a direct
observer or researcher in any of the events. A scholarly source rich in primary literature seeks
to engage in terms of arguments and evidence. When composing secondary documents from
primary documents, acknowledgement must be given to avoid plagiarism.

Types of literature sources

Scholarly journals and periodicals: These are crucial research documents which include
scholarly magazines published on a regular basis. They are found in libraries in hard-copy form
or could be available online.
Theses and dissertation: They are usually found in universities in hard copies or available
online on the websites of a particular university.
Government documents: These include policy papers, legislations and research reports
sponsored by the government or funded by other agencies. For example, master plans,
economic surveys demographic and health surveys, commission, session papers, reports etc.
Conferences: These could be national, regional or international where professionals present
their research findings and other papers. Such papers are credible sources of literature.
Books: these are on various subjects and are available in libraries and bookshops. Researchers
usually include purchase of relevant books in their study budgets. References given at the back
of books provide a lead to other studies, books or documents that could be critical to the study.
Translated documents: Some documents especially in areas that have been widely studied
could be written in a variety of languages. Such would require competent translation.
Internet: This means ‘an interconnected set of distinct networks’ which has become an
indispensable tool in many areas especially in the discovery, documentation, storage, retrieval
and sharing of knowledge.
Libraries: These are collection of information resources and services organized for use and
maintained by an institution or government. It serves the people who need the material. Many
libraries are repositories and access points for other materials and documents stored in various
formats such as microfilm, microfiche, audio tapes, CDs, gramophone records, cassettes, video
tapes or digital video decoders (DVD).
Archives: This refers to a collection of records which have been selected for permanent or long
term preservation and which may be in danger of being lost permanently.
Museums: This is a public institution that acquires, conserves, researches, communicates and
publicly exhibits a variety of items, documents and materials that are considered to be of great

Page 36 of 78
Prepared by Mr. James
value to the society. They safe guard and make accessible artifacts and specimens which they
hold in trust for the society.
Classified and declassified documents: Governments generate some information which is held
in top secrecy and kept out of reach of the public including writers, scholars and researchers.
Such information is considered likely to compromise national security (however information
should not be merely classified to cover up illegal activities). Classified information is
restricted in dissemination but could be shared upon clearance. On the other hand declassified
information refers to information that is no longer considered a top secret and whose sharing
does not compromise national security. Many documents are automatically declassified after
approximately 30 years depending on the law of the country. Such documents provide rich
sources of rare information to researchers.

Writing Literature Review

In order to make the writing of literature review easy the following should be observed.
• Selecting only the most important points in each source to highlight in the
review.

• Paraphrasing while presenting author’s information or opinions accurately.

• Direct quotations to maintain author’s accuracy to add strength to one’s work.

• Maintaining the researcher’s voice despite presenting other people’s ideas.

• Citing all literature sources as a mandatory academic etiquette using the styles
required by your university.

Challenges in formulating literature review

The following are among the challenges researchers encounter while writing literature review;
i. Failing to relate the reviewed studies with the current study

ii. Poor presentation making the work disjointed especially in paragraphing

iii. Large quantities of studies to be reviewed

iv. Lack of documentation which results in forgetting or omitting important points

v. Lack of referencing thus spending a lot of time trying to track down references

vi. Lack of critique when interpreting others findings

vii. Reviewing studies that are old instead of current ones.

Page 37 of 78
Prepared by Mr. James
Self-Assessment Questions

1. Plagiarism is an academic crime that can cost your academic credentials.

Explicate ways which researchers can use to ensure they do mot plagiarize

2. Identify at least three journal articles and two books that are relevant to your
area of research

3. Review of related literature plays a critical role in any research work. Justify this statement.

Page 38 of 78
Prepared by Mr. James
 TOPIC SEVEN
RESEARCH METHODOLOGY
Research Designs
Research design is the plan, structure and strategy of investigation conceived so as to obtain answers to
research questions and control variance. A research design is a set up frame work for one’s study and the blue
print of the researcher. From what we have read in the previous lectures; there are two main types of research
designs. The other designs fall in either of the categories: quantitative and qualitative research design.
Quantitative and qualitative research designs
Quantitative research involves a scientific description of a social phenomenon in a
mathematical or a computational technique-using numbers. It is the numerical method of
describing observations of materials or characteristics. The researcher has to carefully plan the
study including the tests or data collection instruments

Characteristics of quantitative research:

i. It can be used to test research hypothesis
ii. Closed-ended questions are used to collect the data
iii. Different levels of measurements can be used: Nominal, ordinal, interval, and
ratio.

Qualitative research involves an in-depth discovery of the motives of human behaviour and is
collected using observation and interview methods among others. Qualitative research offers
opportunities for conducting exploratory and descriptive research that uses the context and
setting to search for a deeper understanding of the person(s) being studied. It is therefore more
inclusive and the key feature of this approach is that the research plays a central role in
elucidation and interpretation of the behaviors observed.
Qualitative methods consist of three kinds of data collection:
i. In-depth open ended interviews

ii. Direct observations

iii. Written documents

Page 39 of 78
Prepared by Mr. James
Other types of research designs
Experimental/quasi experimental design - These designs are used to study cause and effect
relationships. The true experimental design is considered the most useful design to demonstrate
program impact if there is random selection of participating units and random assignment of
treatment and control conditions. Research units can be individuals (students, teachers, parents
etc), groups of individuals (institutions, regions). In social sciences, since it is difficult to do
pure experiments with all the variables controlled, researchers opt for quasi experimental
research designs. The program is implemented and a post-test administered to the group which
received the treatment. Sometimes a pre-test is administered before the treatment. Finally,
differences between the group that received the treatment and the one that did not are compared
to determine the impact of the program.

Survey design - Surveys are used to gather systematically factual information necessary for
decision making. They are an efficient method of collecting descriptive data regarding:
• The characteristics of the population

• Current practices, conditions or needs

• Preliminary information for generating research questions.

When using a survey design, you should:

• Identify the population of interest

• Clarify the objective of the study

• Develop a questionnaire and field test

• Select a relevant sample

• Administer the questionnaire to members of the sample by mail or in person

• Tabulate the results in a descriptive fashion (i.e. reporting means, frequencies

percentages).

Naturalistic design - The naturalistic design grew out of the need to study phenomena as they
naturally occur in the field. The goal of a naturalistic study is to understand the phenomena
being observed. A major feature of this design has been the use of human instrument (the
observer) to collect, filter and organize incoming data. The design differs from others because
it evolves during the course of the study. The following guidelines might help researchers when
conducting a naturalistic study:

Page 40 of 78
Prepared by Mr. James
 • Establish the focus of the study

• Determine the site(s) of data collection

• Plan successive phases of the study

• Establish the trustworthiness of the data.

Correlation design - Orodho (2003) notes that correlation designs enable us to assess the
degree of relationship that exists between two or more variables. For example, a researcher
might be interested in finding out the correlation between students’ scores in KCPE
mathematics or physics. If a positive correlation is established, one could suggest that KCPE
mathematics grades are better indicators of the students’ future performance in physics at
secondary school level.

Cross-cultural design - It is used in research for comparing the behaviour patterns of different
cultures. For instance, a researcher may attempt to compare the performance of rural and urban
coastal primary pupils in Kiswahili proficiency.

Case study design - A case study seeks to describe a unit in detail, in context and holistically.
A case study becomes particularly useful when one can identify a case rich in information. For
instance, a case could be VETI. We find that VETI can allow for an in-depth investigation of
the problem at hand e.g., absence of good reading habits among the undergraduate students. In
this case, a case study of the institution will bring about deeper insights and better
understanding of the factors that influence the promotion of reading habits among students at
the college level.

Page 41 of 78
Prepared by Mr. James
 TOPIC EIGHT.
CENSUS AND SAMPLING

Population
Population refers to an entire group of individuals, events or objects having a common
observable characteristic. The universal population is everyone in the universe common
observable characteristics. It is also an aggregate of all that conforms to a given specification
e.g. all standard eight pupils in the country. A researcher first defines the population for which
he/she wants to generalize the results. The population that is targeted by the researcher to
generalize the results is referred to as the target population. Since it may be impossible to
select a representative group from a target population that may be large and scattered over a
wide geographical area, researchers draw their sample from accessible population which is
more narrowly defined and manageable. The challenge that always comes with drawer
samples out of population is that the sample may not be a true replica or a true representative of
the population hence the likelihood of sampling error. In other words, it becomes difficult to
establish population validity. If a researcher decides to collect data from the population, he
conducts a census study.

Sampling
This is a process of selecting a number of individuals or objects (sample) from a population to
be a participant in the research study. A sample in this sense is a small group of individuals or
objects selected from a population in such a manner that it represents population
characteristics. For instance, if the population is made up of men and women, married and
unmarried, the sample should represent these characteristics. In this topic we are going to
discuss various sampling designs that are used to collect data.

Advantages of sampling
i. Gathering data on a sample is less time consuming because studying the entire
population is time consuming.
ii. It is less costly to gather data on a sample.

iii. Sampling may be the only practical method of data collection. This may be the
practical way when the testing involves destruction of objects e.g., bulbs, soda, etc.

Page 42 of 78
Prepared by Mr. James
 iv. Sampling is practical when the population is infinite or extremely large.

Disadvantages of sampling
Ensuring that the sample is representative of the entire population is hardly achieved due to two
types of errors:
i. Chance factor and bias factor

ii. Non-response error

Chance factor: This happens when in a particular sample, one element, and not another has
been included. Chance factor is also referred to as sampling error. It is an error that is not in
the control of the researcher; it happens because there is no sample that is a true replica of the
population. When you select representative samples, chances are that you will not be able to
control all the characteristics within the population. Hence those discrepancies between the
sample and the population that occurs due to chance and not because of the decisions of the
researcher are referred to as “sampling error”. The only way that this kind of error can be
minimized is by increasing the number of people in the sample. The greater the sample; the less
the sampling error.

Bias in selection: This arises when some strata are over or under represented in the sample.
The bias in this case is caused by the decisions of the researcher. When the researcher
conveniently uses his/her friends as a sample, or over represents some groups of people over
others due to his/her own biases, it results to sampling bias. This shortcoming cannot be
solved statistically, because it is not a random error.

Non-sampling error: Even when a representative sample has been selected, a “non-response
error” can happen. This type of error comes about when an element of the sample does not
respond to a measurement instrument for whatever reason. It may be partially or totally and
may be caused by:
i. The respondent becoming ill or had language difficulty

[Link] interviewee changing resident or name

iii. The interviewee total attrition through death

iv. Interviewee absenting himself from the interview

Page 43 of 78
Prepared by Mr. James
 v. Interviewee refusing to give information as a result of the researcher approach
or nature

Sampling Designs: Probability and Non-Probability

A sample design is a definite plan for obtaining a sample from a given population. It refers to
the technique or the procedure the researcher adopts in selecting items for the sample. A
sample design is determined before the data is collected. Researchers must prepare a sample
design which should be reliable and appropriate for his/her research study. Sampling designs
are divided in two broad classes: probability and non- probability:

Probability sampling is where the cases in the population have a known probability of being
included in the sample because the number of people in the population is known. This is made
possible through random selection. In non-probability sampling, the chances of selecting any
case are not known because cases are non-randomly selected.

Types of Probability Sampling

i. Simple random sampling

ii. Interval or systematic sampling

iii. Stratified sampling
iv. Cluster or multi-stage sampling

1. Simple Random Sampling: It is a procedure in which all the individuals in the defined
population have an equal and independent chance of being selected as a member of the
sample. By independent it means that the selection of one individual does not affect in
any way the selection of any other individual. A more precise definition of a simple
random sampling is that it is a process of selection from a population that provides every
sample of a given size an equal probability of being selected. The process of selecting
cases ensures that selection of each individual changes slightly the probability for the next
case being selected. For example, suppose there are 100 grade eight pupils in our accessible
population, and we want to select a simple random sample of 20; when we select our first
case, each pupil has a chance in 100 of being selected. Once this pupil is selected, thereafter,
there are only 99 cases remaining so that the remaining pupil has only one chance in 99 of
being selected as the second case.

Page 44 of 78
Prepared by Mr. James
 2. Systematic Sampling or Interval Sampling: This technique is based on the selection
of elements at equal intervals, starting with a randomly selected element on the population
list. The selection of the first sample member determines the entire sample. The population
members’ names or some type of identification are put in order. For example the names of
students in a class may be placed in alphabetical order in a register. The sample size chosen
and the sampling constant ‘K’ are determined. For example, if you want to select 20
students from a list of 100 students, the sampling constant K would be:
Sampling constant, K = population/sample size
100/20=5
The researcher then selects at random, a number smaller than 5 for instance 4, then starts with
that number e.g., selects every fourth name from the list of the population. Systematic
sampling is a slightly easier procedure to use than simple random sampling. It differs from
simple random sampling in that each member of the population is not chosen
independently. Once the first member has been selected, all the other members of the sample
are automatically determined. Systematic sampling can be used instead of simple random
sampling if one is certain that the population list is in random order or possibility of periodicity
in the list. That is, if every Kth person on the list shares a characteristic of the entire population.
3. Stratified Sampling: In this case, the sample selected should assure that certain sub-
groups in the population will be represented in the sample in proportion to their numbers in
the population itself. Such sub-samples are referred to as stratified samples. In stratified
random sampling, the population is first subdivided into two or more mutually exclusive
segments called strata, based on categories of one or more combination of relevant
variables. Simple random samples are drawn from each stratum, and then joined to form the
complete stratified samples. Assume that a researcher wanted to sample 500 students from a
student population of 5000 from a given university, it is expected that the student sample
will vary by gender and according to years of study. Allocation of sample size among strata,
the decision must be made as to the numbers that will be selected from each stratum for the
sample. There are three methods of allocation (i) equal, (ii) proportional (iii) optimum
allocation.
Stratified samples are particularly appropriate in studies where the research problem requires
comparisons between various sub-groups. It assures the researcher that the sample will be
representative of the population in terms of certain critical factors that have been used as a
basis for stratification, and also assures adequate cases for subgroup analysis.

Page 45 of 78
Prepared by Mr. James
 4. Cluster Sampling: In cluster sampling, the unit of sampling is not the individual but
rather a naturally occurring group of individuals. Cluster sampling is used when it is
convenient to select groups of individuals than to select individuals from a defined
population. The situation occurs when it is either impractical or impossible to obtain a list of
all members of accessible population. For example, one defined population consists of all
residents over the age 18 in a particular city. Simple random sampling or systematic
sampling could be used if an up to date, complete census of all the city’s individuals and
their ages were available. If not, then cluster sampling is advisable. The city may be divided
into areas containing a number of blocks. Each area would be listed and numbered, and the
areas to be sampled would be drawn at random. All individuals who meet the age
requirement in each sample area would be studied, except those who cannot be reached or
are uncooperative.

7.7 Types of Non-Probability Sampling

i. Sequential sampling
ii. Purposive sampling

iii. Quota Sampling

iv. Dimensional sampling

v. Convenience sampling

vi. Snowball sampling

1. Sequential sampling
The ultimate size of the sample is not fixed in advance but is determined according to
mathematical decisions on the basis of information yielded as survey progresses. The design is
usually adopted under acceptance sampling plan in the context of statistical quality control.
2. Convenience sampling: In this type of sampling (also called haphazard, fortuitous,
deliberate or accidental sampling), the researcher simply selects a required number from
cases that are conveniently available e.g., television stations and newspapers wanting to tap
public opinion in specific issues may interview conveniently available respondents.
3. Purposive sampling: The researcher relies on expert judgment to select units that are
representative or typical of the population. The general strategy is to identify important
sources of criteria in the population and then to select a sample that reflects the criteria. It
includes handpicking the cases to be included in the sample on the basis of one’s judgment

Page 46 of 78
Prepared by Mr. James
 of their typicality. The subjects are chosen according to a certain specified criterion e.g.
boys and girls, rural vs. urban.
4. Quota sampling: It resembles purposive sampling and has similar characteristics to the
proportionate stratified random sampling. Quota sampling begins with dividing the
population into relevant strata such as age, geographical region, years, and then the total
sample is allocated among the strata in direct proportion to their estimated or actual size in
the population. Finally to obtain correct proportions in the sample, interviewers are asked to
speak to a fixed quota of respondents in each stratum. To fill the quota, interviewers are free
to choose anyone who meets the quota requirements unlike stratified random sampling
where cases are chosen through simple random sampling.
5. Dimensional sampling: It is a further refinement of quota sampling where you identify
various factors of interest in a population and obtain at least one respondent for every
combination of the factors.
6. Snowball sampling: After identifying a small number of individuals who have the
required characteristics, you then use them as informants to identify others who qualify for
inclusion. These in turn identify yet others.

Errors Associated with Sampling

Sampling error - This is associated with using a sample rather than census, because no sample
is a true replica of the population. To reduce chances of sampling error, the researcher should
increase the sample size.
Sampling bias - This is associated with sample selection. It occurs when some
strata/individuals/objects have been included or excluded from the sample because of
researcher’s bias.
Non-sampling error - This is the error that occurs when an element of the sample does not
respond to a measurement instrument for whatever reason.
Some Common Mistakes Made in Sampling
i. The researcher uses a small sample which does not permit statistical
significance.

ii. Researchers fail to utilize stratified sampling technique when needed to obtain
adequate samples of subgroups.
iii. The researcher changes sampling procedure in order to make data collection
more convenient.
iv. Select a sample that is not appropriate for the research study.

Page 47 of 78
Prepared by Mr. James
 v. The researcher selects the experimental and control groups from different
population.

There is need for randomization to ensure equivalence.

TOPIC NINE
DATA COLLECTION INSTRUMENTS
Data Collection
This refers to gathering of information to serve or prove some facts. Data collection helps to
clarify the facts and therefore the researcher must have a clear understanding of what they hope
to obtain and how to obtain it. In this case the researcher must have a clear vision of the
instruments to be used, the respondents, and the selected area or location of the research. In
research, data collection is important in that it allows for dissemination of accurate information
and development of meaningful data that can be generalized to the population under study.

Primary and secondary data

Data is the plural of “datum” which is originally a Latin word meaning “something given”.
Data is used in English to mean “facts or pieces of information.” Hence in research, data are
pieces of information that can help us reach the research goal. In research we have two
types of data: Primary and secondary.
Primary data is data originally collected for a specific research goal. The researcher collects the
data from the first person basis; he can collect the data through surveys, interviews and
observation. The data is collected the first time for the purpose of the research being conducted.
Secondary data is data that is originally collected for a different research purpose and reused
for another research goal. For instance, data collected during the Kenya 2009 census. A
researcher can decide to use the data that was collected during that time for the purpose of
population census and use it to respond to a different research questions.

Purpose of data collection

• Stimulating new ideas by identifying areas related to research topic.
• Highlighting a situation thus creating awareness and improvement.
• To influence legislative policies and regulations.
• Providing justification for and existing program or need for a new one.
• Evaluating the responsiveness and effectiveness of the study.
• Promotes decision making and resource allocation that are based on solid
evidence.

Page 48 of 78
Prepared by Mr. James
Data Collection Instruments and Techniques
The purpose of a tool or research instrument is to measure the variables of the study. In social
science research, researchers develop measurement tools as part of the study. The type of tool
to be used depends on the design and type of the study. In order to guarantee quality data
collection, appropriate data collection tools and techniques must be applied.

Data collection techniques on the other hand refer to the way a given tool is applied to collect
information. For instance, interviewing as a data collection technique requires use of an
interview guide. However, a researcher can utilize a combination of tools and techniques to
collect data in a single study. Depending on the nature of the study, a researcher can select the
kind of data and target population from the following;
i. Questionnaires
ii. Interviews
iii. Focus Group Discussions (FGDs)
iv. Tests
v. Analysis of documents
vi. Observations

1. Questionnaires
This method of data collection is quite popular, particularly in the case of big enquiries. A
questionnaire consists of a number of questions printed or typed in definite order on a paper. It
can be mailed to respondents or administered directly to them. A questionnaire should be very
well constructed since it is considered as the heart of a survey operation. A good questionnaire
has the following characteristics:
• Deals with a significant topic or the accompanying letter.
• Only seeks information that is not obtained from other sources.
• Should be as brief as possible so as to enable the respondent respond to all items
with ease and clarity.
• Attractive in appearance, neatly arranged and clearly duplicated or printed.
• Good and clear directions that are accurate and not ambiguous (each question
should deal with a single idea).
• Questions should be objective.
• Presents questions in a good psychological order, proceeding from general to
more specific.
• It should be easy to tabulate and interpret. It is advisable to pre-construct a
tabulation sheet, anticipating how the data will be tabulated and interpreted.

Page 49 of 78
Prepared by Mr. James
Types of Questions Used in Questionnaires
Structured/closed-ended questions
These types of items refer to questions which are accompanied by a list of all possible
alternatives from which respondents select the answer that best describes their situation.

Unstructured/open-ended
These refer to questions which give the respondents complete freedom to respond. These free
response questions permit an individual to respond in his/her own words.

Contingency questions
These questions are only applicable to certain groups of respondents. In cases where the
respondents want to probe for more information from certain respondents in the population
he/she can have follow-up questions that are used to probe for more information from the
relevant sub-group only. The purpose of these questions is to probe for more information; they
also simplify the respondents’ tasks in that they do not require them to answer questions that
are not relevant to them.

Rules for Constructing Questionnaires and Questionnaire Items

a) Before constructing a questionnaire, list the objectives that you would like the
questionnaire to accomplish. Each question in the questionnaire must be related or
relevant to your research questions to ensure that they are valid.
b) Determine how information obtained from each question in the questionnaire
will be analyzed.
c) Ensure your questions are clear and unambiguous. Terms like several,
frequently or most have no precise meaning and should be avoided. Try as much as
possible to have terms quantifiable, e.g. when asking about the frequency of an
occurrence instead of having option like frequently, seldom, always etc give more
definite options e.g., once, twice, more than three times, every day, etc.
d) If a concept has several meanings, it must be used in a question; the intended
meaning must be defined. Hence, avoiding misinterpretation of the question.
e) Short questions are preferred to long ones since they are easily understood.

Page 50 of 78
Prepared by Mr. James
 f) Double-barreled items should be avoided. These are items that have two
separate ideas in one question.
g) Misleading or biased questions should be avoided e.g., questions that suggest
that one answer may be better that the other. Hints as to preferable answers should be
avoided.
h) Very personal or sensitive questions should be avoided

i) Use simple words over difficult understandable words.

j) Questions that assume facts with no evidence should be avoided. Such questions
offend and discourage the respondents e.g., “have you stopped buying goods and
services on credit?”
k) Avoid psychologically threatening questions e.g., “ Are you worried about the
consequences of contracting HIV?”
l) Include enough information in each item so that it is meaningful to the
respondents.

Ordering Items in the Questionnaire

They should be arranged in a logical sequence. This helps to put the respondent at ease when
responding to the questionnaire and coding, and final analysis of the data.
a) Begin with non-threatening, interesting items. Very touchy, sensitive items should not
be put at the beginning of the questionnaire as they may put off the respondent.
b) It is not advisable to put important questions at the end of a very long questionnaire.
Such questions might be overlooked or answered in a hurry.
c) Have some logical sequence when putting items together. For example group together
a. related items or items that will elicit a similar response.
d) Some researchers arrange their questions according to the themes being studied.
e) If the questionnaire is arranged into content sub-sections, each section should be
introduced with a short statement concerning its content and purpose.

Presentation of the Questionnaire

1. The questionnaire should be of quality paper and well organized.
2. Organize and lay out questions so that the questionnaire is easy to complete.
3. All pages and items in the questionnaire should be numbered.
4. Instructions should be brief but clear. If items are similar or follow the same
format, general instructions can be used.

Page 51 of 78
Prepared by Mr. James
 5. The questionnaire should be of reasonable length. Very long questionnaires may
be redundant and may not interest the respondent.

Matrix Questions
These questions share same set of response categories e.g., likert scales. For instance, if you
wanted to do a study on student’s perception of an institution, you can ask a set of questions
that share the same response categories e.g. strongly agree, agree, indifferent, disagree, and
strongly disagree.

2. Interviews
An interview is in a sense an oral questionnaire. Instead of writing the response, the respondent
or interviewee gives the needed information orally and face to face (or via the telephone). To
use this method it requires a skilled interviewer in order to gather information. In some
interviews, the response is recorded. The main requirement for successful data collection using
this technique is the ability to approach identified respondents to persuade them to participate
in the study. Once the respondent’s cooperation is guaranteed, the interviewer must maintain it
while collecting the data. The following are the guidelines for successful interview:
• Planning in advance and full knowledge of the problem under consideration.
This
includes choice of suitable time and place.

• Friendly and an informal approach as well as explaining the purpose of the

interview.
• Attempt to establish a proper rapport with the interviewee (cultivating a
favourable atmosphere).
• Ability to listen with understanding, respect and curiosity in the gateway to
communication.
• Cultivating the full cooperation of the interviewee through free-flowing
questions while controlling the course of the interview as per the study objective.
• An interview guide particularly where the task of collecting information is to be
accomplished by several interviewers. This ensures uniformity.

3. Focus Group Discussions (FGDs)

These are informal interviews with small groups zeroing on specific topics or subjects. In
FGDs the researcher should have specific topics to be discussed and a recording list of the
discussions is made. The technique is however not successful in eliciting information
considered private, or concerning behavior that might be subject to disapproval, since people
are reluctant to share such information in a group setting. The technique has the following
characteristics:

Page 52 of 78
Prepared by Mr. James
 • It is a qualitative technique involving a small group of people talking
spontaneously and freely on themes considered important to an investigation or
research
• It has a moderator and a researcher

• Lasts between one hour and one and half hours.

4. Tests
Psychological tests are the most useful tools for educational research for they provide data for
most experimental and descriptive studies in education. A psychological test is an instrument
designed to describe and measure a sample of certain aspects of human behavior. Tests and
inventories are used describe status, measure changes in status produced by modifying factors,
or predicting future behavior on the basis of present performance. They can be classified as
follows:
a) Performance tests - administered individually and require that the subjects
manipulate objects or mechanical apparatus while their actions are being observed
and recorded by the examiner.
b) Paper and pencil tests – administered in groups and require the subjects to
mark their response on a prepared sheet.

c) Power tests – have no time limit and the subjects attempt progressively more
difficult tasks until they are unable to continue successfully.

d) Timed or speed tests – basically involve the element of power but in addition
they limit the time the subjects have to complete certain tasks.

e) Standardized tests – the content, administration and scoring have been set in
one pattern so that those taking it will do so under similar conditions.

f) Non-standardized – they are teacher made and designed for use with specific
group of persons.

5. Analysis of Documents/ Document Analysis

It consists of analyzing the contents of documentary materials such as books, magazines,
newspapers and the contents of all other verbal materials which can be either spoken or printed.
The analysis of content is a central activity whenever one is concerned with the study of the
nature of the verbal materials. The analysis may be a simple level when we pursue it on the
basis of certain characteristics of the document or verbal material that can be identified and

Page 53 of 78
Prepared by Mr. James
counted. It can also be a subtle level when the researcher makes a study on the attitude, e.g., the
press towards education by feature writers.

6. Observations
This is the most commonly used method especially in studies related to behavioral sciences. It
is systematically planned and recorded and is subjected to checks and controls on validity and
reliability. Information is sought by way of investigator’s own direct observation without
asking from the respondents. While using this method, the researcher should keep in mind what
should be observed. How should the observation be recorded? How accurate is the
observation? This observation can be:
• Structured - characterized by a careful definition of the units to be observed,
the style of recording the observed information, standardized conditions of
observation and the selection of pertinent data of observation.
• Unstructured – This is when observation takes place without thinking of the
characteristics (structured) in advance.

The main advantages of this method include:

1. The subjective bias is eliminated, if it is done accurately.
2. The information obtained relates to what is currently happening.
3. It is independent of respondents’ willingness to respond thus relatively less
demanding.

Limitations include:
1. It is expensive
2. The information provided by this method is very limiting
3. Some unforeseen factors may interfere with the observation task.

Steps in Data Collection

• Defining the target population, the sample as well as the respondents and their
accessibility.

• Reflection on the research design for clarity of the format in which the data will
be collected e.g., survey, case study or experiment.
• Readiness of the instruments and ensuring that they are in order.
• Definition of the data to be collected and ensuring the same on formation is
clear to the research assistants if to be used.

Page 54 of 78
Prepared by Mr. James
 • Clearance from relevant authorities before collecting any information as well as
sending an advance letter to sample respondents.
• Pre-testing of the instruments in a pilot study to find out their effectiveness.

Self-Assessment Question
1. In regards to data collection methods discussed, which ones are appropriate to
collect quantitative and qualitative data?

Page 55 of 78
Prepared by Mr. James
 TOPIC TEN

TESTS OF SOUND MEASUREMENTS AND LEVELS OF

SCALE.
Concept of Sound Measurement in Research
A measurement tool in research is any instrument that is used to collect data such as a
questionnaire. It is important that the tool or instrument is sound in that it should be able to
collect valid, reliable and also practical data. If you are collecting data on students’ attitudes
and motivation, it is important that the questions measure those concepts accurately e.g., for
such a case, you cannot use a personality questionnaire no matter how well its organized to
collect data on attitudes and motivation.

Characteristics of a Sound Measurement Instrument

A good measurement instrument should be valid, reliable and practical.

Validity
Test of validity refers to the degree at which an instrument measures what it is supposed to
measure. Validity is determined by the presence or absence of systematic errors/non-random
error in data e.g., a faulty scale that either adds or reduces weights in one consistent direction.

There are three types of validity

a) Construct validity - This is a measure of the degree to which data obtained from an
instrument meaningfully and accurately reflects/represents a theoretical concept e.g., the
extent to which an instrument has been accurate in measuring what it ought to measure e.g.,
motivation scale etc.
b) Content validity - This is a measure of the degree to which data collected using a
particular instrument represents a specific domain of indicators or contents of a particular
concept. It provides adequate coverage of the topic under study e.g., an instrument
measuring management skills might involve factors such as decision making, planning,
financing, marketing etc.
c) Criterion-related validity - Refers to the use of a measure in assessing subjects’
behavior in specific situations for predictive purposes. For example, if an instrument
measures job satisfaction, the respondent who scores high on the instrument must also
perform well in the job.

Page 56 of 78
Prepared by Mr. James
Reliability
This refers to the degree to which a research instrument yields consistent results or data after
repeated trials. Reliability in research is influenced by random error. Random error is the
deviation from a true measurement due to factors that have not effectively been addressed by
the researcher. Methods of assessing reliability include: test-retest, equivalent-form, split-half
techniques.
a) Test-Retest Method
One of the easiest ways to determine the reliability of empirical measurements is by the retest
method in which the same test is given to the same people after a period of time. The reliability
of the test (instrument) can be estimated by examining the consistency of the responses
between the two tests. If the researcher obtains the same results on the two administrations of
the instrument, then the reliability coefficient will be 1.00. Normally, the correlation of
measurements across time will be less than perfect due to different experiences and attitudes
that respondents have encountered from the time of the first test.

The test-retest method is a simple, clear cut way to determine reliability, but it can be costly
and impractical. Researchers are often only able to obtain measurements at a single point in
time or do not have the resources for multiple administration.
b) Equivalent form/Alternative Form Method
Like the retest method, this method also requires two tests with the same people. However, the
same test is not given each time. Each of the two tests must be designed to measure the same
thing and should not differ in any systematic way. One way to help ensure this is to use random
procedures to select items for the different tests. The alternative form method is viewed as
superior to the retest method because a respondent’s memory of test items is not as likely to
play a role in the data received. One drawback of this method is the practical difficulty in
developing test items that are consistent in the measurement of a specific phenomenon.
c) Split-Halves Method
This method is more practical in that it does not require two administrations of the same or an
alternative form test. In the split-halves method, the total number of items is divided into
halves, and a correlation taken between the two halves. This correlation only estimates the
reliability of each half of the test. It is necessary then to use a statistical correction to estimate
the reliability of the whole test. This correction is known as the Spearman-Brown prophecy
formula.

Page 57 of 78
Prepared by Mr. James
Factors affecting Internal Validity
Internal validity is threatened whenever there exist the possibilities of uncontrolled extraneous
variables that might otherwise account for the results of the study. These extraneous variables
that can endanger the internal validity of a study include:
a) History
During the time that a research is taking place, some events may occur that confuse the
relationship studied. These events may either increase or decrease the expected outcome. For
instance, the longer the interval between the pre-test and post-test, the more viable the threat.
b) Maturation
Changes in physical, intellectual or emotional characteristics that occur naturally over time
may influence the results of the study. In longitudinal studies for instance, individuals grow
older, hence become more mature and more sophisticated and hence pose a threat to internal
validity of the results.
c) Testing
The process of taking a test can affect the scores of a second test. This is also referred to as
“pretest sensitization” meaning the effects of taking a test upon performance on second test.
The exposure of the first test (pre-test) might automatically affect the performance of the
second (post-test).
d) Instrumentation
This refers to any changes in the way the instrument or test is administered. For instance, if
different instruments are used for the same research, and then this would threaten in the
internal validity of the test.
e) Differential selection
This occurs when intact groups are compared. If the groups being compared are different to
begin with, there could be differences in their evaluations.

Concept of Measurement of Scale

The concept of measurements of scales involve the quantification of various variables in a numerical
method as a way of describing phenomena e.g., assigning male and female as numbers 1 and 2, for
purposes of creating categories to enable statistical computations. This process involves the
researcher carefully planning the study by developing tests or data collection instruments with
measurable questions. Each subject is identically studied, and there is little room for human bias to
create problems with the data. When a defined portion of the material or characteristics used as a
standard for measuring any sample, a valid and precise method of data description is provided.

Page 58 of 78
Prepared by Mr. James
One of the primary purposes of classifying variables according to their level or scale of measurement
is to facilitate the choice of a statistical test used to analyse the data. There are certain statistical
analyses which are only meaningful for data which are measured at certain measurement scales. For
example, it is generally inappropriate to compute the mean for nominal variables such as gender.
Suppose you had 20 subjects, 12 of which were male, and 8 of which were female, if you assigned
male a value of '1' and female a value of '2', could you compute the mean sex of subjects in your
sample? It is possible to compute a mean value, but how meaningful would that be? How would you
interpret a mean sex of 1.4? When you are examining a nominal variable such as sex, it is more
appropriate to compute a statistic such as a percentage (e.g., 60% of the sample was male). Hence in
research there is a classification system to categorize the variables: Nominal, ordinal, interval, and
ratio.

Levels of measurement
The following are the levels of measurement used:

a. Nominal scale

A nominal scale describes differences between things by assigning them categories. Nominal data
are counted data and each individual can be a member of only one set, and all other members of the
set have the same defined characteristic e.g., nationality, gender, socioeconomic status, race,
occupation or religious affiliation. For example,

Please tick your gender:

1. Male

2. Female

b. Ordinal scale

At times we can indicate that things not only differ but that they differ in amount or degree. Ordinal
scales permit the ranking of items or individuals from highest to lowest. The criteria for highest to
lowest ordering are expressed as a relative position or rank in a group. Ordinal measures have no
absolute values, and the real differences adjacent ranks may not be equal. Ranking spaces them
equally, although they may not actually be equally spaced. For example, the following are the factors
that one may consider when choosing an institution of higher education; please list in a descending
order which of these factors influenced your choice of an institution

1. Cost

2. Reputation

3. Quality

4. Programs

Page 59 of 78
Prepared by Mr. James
5. Accessibility

c. Interval scale

An arbitrary scale based on equal units of measurements indicates how much of a given
characteristic is present. It represents a decided advantage over nominal and ordinal scales because it
indicates the relative amount of a trait or characteristic. Its primary limitation is that it does not have
a true zero. It does not have the capacity to measure the complete absence of a trait e.g.
psychological tests and inventories. For instance, on a scale of 1-5, 5- strongly agree and 1- strongly
disagrees; to what extent did the following factors influence your choice of an institution?

Strongly Agree Neither Agree Disagree Strongly

nor Disagree
Agree Disagree

Cost

Reputation

Program

Accessibility

Quality

d. Ratio scale

A ratio scale has the equal interval properties of an interval scale but has a true zero. Its numerals
have the qualities of real numbers and can be added, subtracted, multiplied, and divided and
expressed in ratio relationships. It is therefore the most precise scale. For instance, What is your
annual salary?

a) 30,000 and below

b) 31,000-40,000

c) 41,000- 50,000

d) Above 51,000

Page 60 of 78
Prepared by Mr. James
 TOPIC ELEVEN
DATA ORGANIZATION, ANALYSIS AND PRESENTATION
Introduction to Data Analysis
Once data has been collected it has to be processed and analyzed in accordance with the
outline. This is important for developing the research plan that is essential for a scientific study
and ensuring that we have all the relevant data for making contemplated comparisons and
analysis. This process basically entails; editing, coding, classification and tabulation of
collected data for analysis. Analysis on its part, refers to the computation of certain measures
along with searching for patterns of relationship that exists among data groups.

Data Organization
The collected data is known as raw information and therefore it has to be well organized in
various stages. This refers to the orderliness in the research data. It involves putting the data
into some systematic form. This can be summarized as follows:
• Raw data to information relevant to the problem identified by the researcher

• Information to facts that the data reveals (data can support it)

• Facts to knowledge or new information

• Knowledge that is expressible with some statistical degree of confidence.

Processing Operations
a) Editing/pre-processing – The primary purpose is to correct problems that are identified
in the raw data. It includes elimination of non-usable data and interpretation of ambiguous
answers.
b) Coding – Refers to the process of assigning numeric or other symbols to answers so that
the responses can be put into a limited number of categories or classes. Such classes must be
appropriate to the research problem under consideration. Coding is necessary for efficient
analysis and through it several replies may be reduced to a small number of classes which
contain theoretical information required for analysis.
c) Classification – It involves reducing large volume of raw data into homogenous groups
on the basis of common characteristics. This can be done depending on attributes or class
intervals.
d) Tabulation - This is the arrangement of mass data that has been assembled into some
kind of concise and logical order. It summarizes raw data and displays the same in compact
form such as statistical tables for further analysis. Tabulation is essential in that:
Page 61 of 78
Prepared by Mr. James
 • It conserves space and reduces explanatory and descriptive statement to a
minimum

• Facilitates the process of comparison

• Facilitates the summation of items and the detection of errors and omissions

• Provides a basis for various statistical computations.

Data Storage
After coding the data, it can be stored for a short term or long term before analysis. This can be
in electronic form or non-electronic (paper) form. The electronic form is most popular today
and then the researcher chooses the appropriate software package for analysis. Choosing a
statistical package depends on the characteristics of the data to be used (descriptive) or analysis
of relationships) to be performed, technical and financial constraints. There are various types of
statistical software to select from e.g., word processor such as Microsoft Word and Excel or
Spreadsheet. In addition, one can also choose to use the statistical systems such as the SPSS.

Data Analysis
Data analysis refers to examining what has been collected in a survey or experiment and
making deductions and inferences. It involves uncovering underlying structures; extracting
important variables, detecting any anomalies and testing any underlying assumptions. It also
involves scrutinizing the acquired information and making inferences.

Data analysis in qualitative research

Qualitative research involves intensive data collection over an extended period in a natural
setting. Such findings are not always computable by arithmetic relations. The responses can be
categorized into various classes called categorical variables which include:
• Quick impressionist summary which involves summarizing key findings,
explanation, interpretation and conclusion

• Thematic analysis which refers to topical or subject discussions

• Content analysis which systematically describes the form or content of written
and /or spoken material. there are various forms of content analysis such as:

- Pragmatic content analysis - classifies signs according to their probable

causes and effects.
- Designation analysis - determines the frequency with which certain
objects, persons or institutions or concepts are mentioned.
Page 62 of 78
Prepared by Mr. James
 - Systematic content analysis - classifies signs according to meaning.

• Attribution analysis - examines the frequency with which certain

characterization or descriptions are used.

• Assertion analysis - provides the frequency with which certain objectives are
characterized in a particular way.

Data analysis in quantitative research

Quantitative data analysis consists of measuring numerical values from which descriptions
such as mean and standard deviations are made. The data can be further divided into discrete
data (countable data such as the number of defective items produced during a day’s production)
or continuous data (parameters or variables that are measured and are expressed on a
continuous scale such as the height of a person). This depends on the type of the study namely:
• Correlational studies: They are mainly analyzed using the correlation
coefficient where the researcher indicates the degree of relationship between two
variables. An example is the Pearson Product Moment Correlation. Another type of
correlation studies is the reliability coefficient which provides information about
validity and reliability of the test.

• Prediction studies – The researcher uses the degree of relationship that exists
between two variables to predict one from the other.

• Causal-comparative research - these attempts to identify a causative

relationship between an independent variable and a dependent variable. An
inferential statistic used is the t-test or the chi-square test.

Statistical techniques
Statistics are set of mathematical methods used to extract and clarify information from
observed data. Statistics generate simple numbers to describe distributions, either grouped or
ungrouped.
Some of the statistical techniques used to present analyzed data include:
• Frequency distributions

• Measures of central tendency such as mean, median and mode

• Measures of dispersion such as range, standard deviations and variance.

Procedure for Hypothesis Testing

i. Make a formal statement
Page 63 of 78
Prepared by Mr. James
 ii. Select a significance level

iii. Decide the distribution to use

[Link] a random sample

v. Calculation of the probability - calculate the probability that the sample result could
diverge as widely as it has from expectations, if the null hypothesis were in fact true. vi.
Compare the probability - compare the calculated probability with a specified value of
alpha (the significant level). If the calculated probability is equal to or smaller that the
alpha value then reject the null hypothesis.

Limitation of Tests of Hypothesis

a) Testing is not decision making rather the hypothesis aid in decision making.
b) The test does not explain reason for differences which could be accounted for by
sampling fluctuations or other reasons.

c) Result of the significance is based on probability. It cannot be expressed in full

certainty.

d) Statistical inferences are based on the significant tests, they cannot be entirely
correct evidences especially if drawn from small samples.

Self-Assessment Questions
1. How do we analyze quantitative data? Explain giving relevant examples.
2. How do we analyze qualitative data? Explain giving relevant examples
3. When is it more appropriate to collect qualitative data over quantitative data?
4. What precautions do you have to take when analyzing both types of data?

TOPIC TWELVE
ETHICAL AND LOGISTICAL ISSUES IN RESEARCH

Page 64 of 78
Prepared by Mr. James
Logistical Issues in Research
Conducting research is a process that needs careful planning. It should be done before starting
the research process to minimize the problem often encountered by the researcher in the field.
Logistics refer to all those processes, activities, or actions that a researcher must address or
carry out to ensure successful completion of a research project. The logistics of conducting
research can be divided into three categories: Pre-field work logistics, field work logistics and
post-field work logistics.

i. Pre-field work logistics

Pre-field work logistics encompass those activities that a researcher must carry out before
embarking on data collection in the field. The main items to consider in pre-field work
logistics include: Obtaining a research permit, establishing a work-plan or research protocol,
training enumerators, pre-testing the instrument, sampling, and distribution of the instrument.
ii. Field-work logistics
These are the activities that need to be addressed during the research. A researcher can develop
a very good instrument but if the data collection is poor, the results may be inaccurate and
therefore invalid. It is therefore crucial for researchers to ensure that all the mechanics of data
collection are efficient. Issues regarding transportation, language barrier, climate, health
hazards such as malaria prone areas and respondent’s hostility, need to be adequately
addressed.

Tips on conducting field work

1. The researcher, supervisor and enumerator should familiarize themselves as
much as possible with the geographical area in which the research is to take place.
2. Enumerators and researchers should create sufficient rapport with the
respondents, by explaining the purpose of research and informing them of the need
for confidentiality and how it will be ensured.
3. Researchers should take precaution against common diseases such as typhoid
and malaria.

4. Researchers and enumerators should be courteous.

5. Researchers should not be over inquisitive, otherwise they may be perceived

with suspicion.
6. Enumerators should be familiar with the instruments so as not to appear
confused.

Page 65 of 78
Prepared by Mr. James
 iii. Post-Field Work Logistics
These include the process of getting the completed instruments from the field to the office
where data coding and analysis will be done. During data collection, the researcher must
establish an efficient system of collecting completed instrument on regular basis. One approach
is to have several centers in the field where enumerators take the completed instruments and
the supervisors check through to ensure they instruments are completed before dispatching
them for analysis. Data coding and entry should start as soon as the instruments are
completed.

Activity
Discuss some logistical issues you would be concerned about with doing your research.

Ethical Issues Related to Research

What is Ethics? When you hear that someone exhibited an unethical behavior at your work
place, what comes to your mind? Ethics refer to a branch of philosophy which deals with one’s
conduct and serves as a guide to one’s behavior. There are three research considerations:
a. Ethical issues related to the individual researcher

b. Ethical issues concerning research subjects

c. Ethical issues concerning the research process.

A. Ethical Issues Related to the Researcher

Researchers must uphold high ethical and integrity standards especially when dealing with
human subjects.

Research plagiarism and fraud

Plagiarism refers to situations where researchers refer to another person’s work as theirs
without acknowledging the author. Fraud refers to situations where the researcher fakes data
that has not actually been collected or makes false presentation of research methodology and
results. Both issues are punishable by law and can result to disqualification of one’s academic
records.

Page 66 of 78
Prepared by Mr. James
Misuse of privileges
A researcher has some power over the subjects owing to the training they have, their expertise,
their legal authority to undertake research and their perceived ability to help. Researcher should
not misuse the power they have over their subjects whether intellectual, legal, expertise or
authority to ask the research subjects to perform activities put them in that could trouble or
stigmatize them.

B. Ethical Issues related to the Research Subjects

Research subjects refer to the people or the respondents who will be surveyed in the research.
They need to be protected, their rights maintained and any consent given.

Confidentiality and privacy

Respondents should be protected by keeping the information given confidential, especially if
confidentiality has been promised. Lack of confidentiality and mishandling of information may
cause physical and psychological harm.

Anonymity
Anonymity refers to the identity of individuals being protected either by using numbers, third
parties or pseudo names. The identity of the individual should not be disclosed and any
identifying information other than name should also not be used. Researchers should use other
ways to code the instruments without asking for the respondents’ names or other identifying
information.

Physical and psychological harm

A researcher should never undertake research that may cause physical or psychological harm.
Psychological harm can be caused by asking embarrassing questions, expressing shock or
disgust while collecting data, using threatening statements or compelling people to say
something that they do not believe in thus causing fear and anxiety among respondents. Any
action that lowers the subject’s self-worth or self-esteem is considered unethical and should be
avoided. In addition, respondents should not be forced to remember any unpleasant
occurrences against their will that may cause resentment or discomfort.

Voluntary and informed consent

A researcher must confirm to the principle of voluntary consent where the respondents
willingly participate in research. Unethical behavior could occur if the researcher fails to

Page 67 of 78
Prepared by Mr. James
disclose the real purpose of the research fearing the subjects’ refusal to participate. A subject
must be told the truth and be given all the facts about the research in order to make an informed
decision about participation or not. Informed consent should be based on information
regarding: the purpose of research study, any foreseen risks, guarantee of anonymity and
confidentiality, identification of the researcher, an indication of the number of subjects
involved, and the benefits and compensations available.

Use of vulnerable and/or special population

It is unethical for researchers to use disadvantaged populations without their consent or the
consent of their guardians. Special populations include children, mentally disabled people, sick
people, and poor people. Permission from those who care for these special populations must be
sought and must be based on the principle of informed consent.

Financial issues and sponsored research

In some cases, a sponsor of a particular research may demand some compromises on quality of
research to save money and time or to distort findings for selfish self- interests. A researcher
should observe ethics by not accepting bribes or kick-backs from sponsors aimed at influencing
the research process in any way. Researchers should observe high ethical and integrity
standards to be able to generate sound and generalizable data.
Dissemination of findings
It is unethical to conceal research findings after completion of research. Some researchers may
decide not to reveal findings if they are contrary to their expectations or their sponsor’s
expectations.

Academic freedom
Academic freedom is the existence of an open and unrestricted atmosphere for free exchange
of ideas and information. Academic freedom is very important in research because the
researcher must be free to discuss and publish findings without fear of intimidation, losing
one’s job, or being victimized. Researchers should be sensitized about their rights to academic
freedom and on issues of intellectual property.

C. Ethical Issues Concerning the Research Process

Page 68 of 78
Prepared by Mr. James
Ignoring pertinent issues
One of the methodological issues that has been debated in relation to ethics is the choice of
topic. It is considered unethical to purposely avoid a pertinent research issue for fear of
repercussions or because of conflict of interests. A researcher is expected to be honest in search
of genuine research problems and should exercise academic freedom to discuss any findings.

Ethical issues in experimental design

In experimental designs, where control and treatment groups are used to provide meaningful
comparisons, some experts have argued that such differential treatment of the groups is unfair
and discriminative.

Use of tests in research

Although controversial, some experts have argued that the use of tests in research could cause
undue distress to the respondent as they may feel as though they are getting submitted to a
rigorous examination which they are likely to either pass or fail. A researcher should ensure
that the respondents provide the needed information with ease, without the fear of being picked
on or feeling pressurized to give information.

Activity
Discuss some ethical issues you would be confronted with when conducting research and how
you would do it?

Self-Assessment Questions

1. Discuss ethical and logistical considerations you would bear in mind when
conducting research
2. Plagiarism is a very serious offense; in what ways can you ensure that you do
not plagiarize your research?
3. A friend of yours is conducting a study about a certain vulnerable group. She
has requested you to respond to her questionnaire even though you know for sure you
do not belong to that vulnerable group; what should be your response?
4. You are doing a study about the street children in Meru. What do you need to do
to ensure that you are following the appropriate ethical guidelines?

Page 69 of 78
Prepared by Mr. James
Appendix I: APA Guidelines

WHAT IS A REFERENCE CITATION?

A reference citation is the documentation needed to make your paper acceptable for academic
purposes. It gives authoritative sources for your statements, helps the reader gain access to
those sources, and acknowledges the fact that the information used in a paper did not originate
with the writer.

WHAT IS APA STYLE OF REFERENCE CITATION?

APA style uses the author/date method of citation in which the author's last name and the year
of the publication are inserted in the actual text of the paper. It is the style recommended by the
American Psychological Association and used in many of the social sciences. The American
Psychological Association addresses new electronic formats in a separate guide, which you can
access in book format or online through the library. Several of the examples in this guide come
from one of these sources. The American Psychological Association offers some guidance and
examples at [Link] This guide only summarizes a few main points regarding
APA style.

Publication Manual of the American Psychological Association (5th ed.) by the American Psychological
Association.

APA Style Guide to Electronic References by The American Psychological Association.

WHEN USING APA STYLE, DO I NEED TO USE FOOTNOTES AT THE BOTTOM

OF THE PAGE?
No, by inserting reference citations in the text, you eliminate the need to use footnotes at the
bottom of the page or at the end of your paper. The citations in your paper and end-of-paper
references list should give readers enough information to locate each source.
NOTE: It is suggested that you consult with your instructor or advisor for the style preferred by
your department. Be consistent and do not mix styles!

Page 70 of 78
Prepared by Mr. James
EXAMPLES OF REFERENCE CITATIONS IN TEXT--APA STYLE
1. If author's name occurs in the text, follow it with year of publication in parentheses.
Example: Piaget (1970) compared reaction times...

2. If author's name is not in the text, insert last name, comma, year in parenthesis.
Example: In a recent study of reaction times (Piaget, 1978)…

3. If author's name and the date of publication have been mentioned in the text of
your paper, they should not be repeated within parentheses.
Example: In 1978, Piaget compared reaction times...

4. Because material within a book or on a web page is often difficult to locate,

authors should, whenever possible, give page numbers for books or paragraph
numbers for web pages in the text to assist readers. Page numbers (preceded by p. or
pp.) or paragraph numbers (preceded by ¶ or para.) follow the year of publication, and
are separated from it by a comma. For websites with neither page numbers nor
paragraph numbers, cite the heading and the number of the paragraph following it.
Examples: Hunt (1974, pp. 25-69) confirms the hypothesis... (Myers, 2000 ¶ 5) (Beutler, 2000,
Conclusion section, para. 1)

5. If there are two authors, always cite both names every time the reference occurs in
the text. Connect both names by using the word "and." Examples: Piaget and Smith
(1972) recognize...

Finberg and Skipp (1973, pp. 37-52) discuss...

6. If there are two authors and they are not included in the text, insert within
parentheses, the last names of the authors joined by an ampers and (&), and the year
separated from the authors by a comma.
Examples: ... to organize accumulated knowledge and order sequences of operations (Piaget &
Smith, 1973).
...to organize accumulated knowledge and order sequences of operations (Piaget &
Smith, 1973, p. 410)

Page 71 of 78
Prepared by Mr. James
 7. If there are more than two authors (but fewer than six), cite all authors the first
time the reference occurs; include the last name of the first author followed by "et al."
and the year in subsequent citations of the same reference.
Example: First occurrence:
Williams, French and Joseph (1962) found...
Subsequent citations:
Williams et al. (1962) recommended...

8. Quotations: Cite the source of direct quotations by enclosing it in parentheses.

Include author, year, and page number. Punctuation differs according to where the
quotation falls. 1) If the quoted passage is in the middle of a sentence, end the passage with
quotation marks, cite the source in parentheses immediately, and continue the sentence.
Example: Many inexperienced writers are unsure about "the actual boundaries of then
grammatical abstraction called a sentence" (Shaughnessy, 1977, p. 24) or about which form of
punctuation they should use.

2) If the quotation falls at the end of a sentence, close the quotation with quotation marks,
and cite the source in parentheses after the quotation marks. End with the period outside the
parentheses.
Example: Fifty percent "of spontaneous speech is estimated to be non-speech" (Shaughnessy,
1977, p. 24).
3) If the quotation is longer than forty words, it is set off without quotations marks in an
indented block (double spaced). The source is cited in parentheses after the final period.
Example:
This is further explained by Shaughnessy's (1977) following statements:
In speech, pauses mark rates of respiration, set off certain words for rhetorical emphasis,
facilitate phonological maneuvers, regulate the rhythms of thought and articulation and suggest
grammatical structure. Modern punctuation, however, does not provide a score for such a
complex orchestration. (p. 24)
4) If citing a work discussed in a secondary source, name the original work and give a
citation for the secondary source. The reference list should contain the secondary source, not
the unread primary source.
Example: Seidenberg and McClelland’s study (as cited in Coltheart, Curtis, Atkins, &
Haller, 1993).

Page 72 of 78
Prepared by Mr. James
THE REFERENCE LIST
APA style suggests using a reference list for references cited in the text of a paper rather than a
bibliography. A reference list includes only those references which were actually cited in the
text of one's paper. There must be total agreement between the two. (See an example of a
reference list on the last page). A bibliography includes all literature consulted which was
"immediately relevant" to the research process, even though the material was not cited in the
text of one's paper. When compiling a reference list, one needs to pay particular attention
to the following: 1) sequence; 2) punctuation and spacing; 3) capitalization; and 4)
underlining.

ORDER OF REFERENCES IN THE REFERENCE LIST

1)Arrange entries in alphabetical order by surname of the first author.

2)Single-author entries precede multiple-author entries beginning with the same

surname:

Kaufman, J. R. (1981).
Kaufman, J. R., & Cochran, D. C. (1978).
3)References with the same first author and different second or third authors are
arranged alphabetically by the surname of the second author, and so on:

Kaufman, J. R., Jones, K., & Cochran, D. F. (1982).

Kaufman, J. R., & Wong, D. F. (1978)

4)References with the same authors in the same order are arranged by year of
publication, the earliest first:
Kaufman, J. R., Jones, K. (1977).
Kaufman, J. R., Jones, K. (1980).

5)The order of several works by different authors with the same surname is
arranged alphabetically by the first initial:
Eliot, A. L. (1983).
Eliot, G. E. (1980).

Page 73 of 78
Prepared by Mr. James
EXAMPLES OF ITEMS IN A REFERENCE LIST
Although the format for books, journal articles, magazine articles and other media is similar,
there are some slight differences. Items in a reference list should be double-spaced. In addition,
use hanging indents: entries should begin flush left with subsequent lines indented.

BOOKS:
One author:
Castle, E. B. (1970). The teacher. London: Oxford University Press.

Two authors:
McCandless, B. R., & Evans, E. D. (1973). Children and youth: Psychosocial development.
Hinsdale, IL: Dryden Press.

Three or more authors: (list each author)

Smith, V., Barr, R., & Burke, D. (1976). Alternatives in education: Freedom to choose.
Bloomington, IN: Phi Delta Kappa, Educational Foundation.

Society, association, or institution as author and publisher:

American Psychiatric Association. (1980). Diagnostic and statistical manual of mental
disorders (3rd ed.). Washington, D.C.: Author.

Editor or compiler as author:

Rich, J. M. (Ed.). (1972). Readings in the philosophy of education (2nd ed.). Belmont, CA:
Wadsworth.

Chapter, essay, or article by one author in a book or encyclopedia edited by another:

Medley, D. M. (1983). Teacher effectiveness. In H. E. Mitzel (Ed.), Encyclopedia of
educational research (Vol. 4, pp. 1894-1903). New York: The Free Press.

JOURNAL ARTICLES:
One author:
Herrington, A. J. (1985). Classrooms as forums for reasoning and writing. College
Composition and Communication, 36(4), 404-413.

Two authors:

Page 74 of 78
Prepared by Mr. James
Horowitz, L. M., & Post, D. L. (1981). The prototype as a construct in abnormal psychology.
Journal of Abnormal Psychology, 90(6), 575-585.

Society, association, or institution as author:

Institute on Rehabilitation Issues. (1975). Critical issues in rehabilitating the severely
handicapped. Rehabilitation Counseling Bulletin, 18(4), 205-213.

NEWSPAPER ARTICLES:
No author:
More jobs waiting for college grads. (1986, June 17). Detroit Free Press, pp. 1A, 3A.
MAGAZINES:
One author:
Powledge, T. M. (1983, July). The importance of being twins. Psychology Today, 19, 20-27.

No author:
CBS invades Cuba, returns with Irakere: Havana jam. (1979, May 3). Down Beat, 10.

MICROFORMS:
ERIC report:
Plantes, Mary Kay. (1979). The effect of work experience on young men's earnings. (Report No.
IRP-DP-567-79). Madison: Wisconsin University. Madison Institute for Research on Poverty.
(ERIC Document Reproduction Service No. ED183687)

ERIC paper presented at a meeting:

Whipple, W. S. (1977, January). Changing attitude through behavior modification. Paper
presented at the annual meeting of the National Association of Secondary School
Principals, New Orleans, LA. (ERIC Document Reproduction Service No. ED146500)

AUDIOVISUAL MEDIA AND SPECIAL INSTRUCTIONAL MATERIALS:

This category includes non-book materials: Audio-record Flashcard; Motion picture
Videorecording Slide Kit; Chart Game Picture Transparency Realia Filmstrip.

A bibliographic/reference format for these non-print materials is as follows:

Author's name (inverted. ----Author's function, i.e., Producer, Director, Speaker, etc. in
parentheses. ----Date of publication in parentheses----Title. ----Medium in brackets after title,
[Filmstrip].
Page 75 of 78
Prepared by Mr. James
HOWEVER, if it is necessary to use a number after a medium for identification or retrieval
purposes, use parentheses instead of brackets, e.g.
(Audio record No. 4321). ----Place of publication: Publisher.
Maas, J. B. (Producer), & Gluck, D. H. (Director). (1979). Deeper in hypnosis [Motion
Picture].
Englewood Cliffs, NJ: Prentice-Hall.

ELECTRONIC MEDIA:
Materials available via the Internet include journals, newspapers, research papers, government
reports, web pages, etc. When citing an Internet source, one should:
1. Provide as much information as possible that will help readers relocate the
information.

In addition, try to reference specific documents rather than web pages when possible.
2. Give accurate, working addresses (URLs) or Digital Object Identifiers.

References to Internet sources should include at least the following four items:
1. A title or description

2. A date (either date of publication or date of retrieval)

3. An address (URL) or Digital Object Identifier

4. An author's name, if available

In an effort to solve the problem of changed addresses and broken links, publishers have begun
to assign Digital Object Identifiers (DOI) to documents, particularly to scholarly journal
articles. DOIs should be used in reference lists when they are available. A DOI may be pasted
into the DOI Resolver to confirm a citation. For journal articles, if no DOI is available, a
database name or URL may be added for particularly difficult to find publications. Since
journal articles, unlike many web pages, are unlikely to change, a retrieval date is not
necessary. Electronic book citations only need source information when the book is difficult to
find or only available electronically.

Internet article based on a print source (exact duplicate) with DOI assigned:
Stultz, J. (2006). Integrating exposure therapy and analytic therapy in trauma treatment.
American Journal of Orthopsychiatry, 76(4), 482-488. doi:10.1037/0002-9432.76.4.482

Page 76 of 78
Prepared by Mr. James
Article in an Internet only journal with no DOI assigned:
Sillick, T. J., & Schutte, N. S. (2006). Emotional intelligence and self-esteem mediate between
perceived early parental love and adult happiness. E-Journal of Applied Psychology, 2(2), 38-
48. Retrieved from

Daily newspaper article, electronic version available by search:

Botha, T. (1999, February 21). The Statue of Liberty, Central Park and me. The New York
Times.
Retrieved from.

Webpage:
Raymon H. Mulford Library, The University of Toledo Health Science Campus. (2008).
Instructions to authors in the health sciences. Retrieved June 17, 2008, from

Annual report:
Pearson PLC. (2005). Reading allowed: Annual review and summary financial statements 2004.
Retrieved from [Link]

References
American Psychological Association. (2008). Electronic resources. Retrieved June 17, 2008
from [Link]
American Psychological Association. (2008). Frequently asked questions. Retrieved June 17,
2008 from [Link]
Bloom, B. S. (Ed.). (1956). Taxonomy of educational objectives: The classification of
educational goals, by a committee of college and university examiners. New York:
McKay.D. Botha, T. (1999, February 21). The Statue of Liberty, Central Park and me. The
New
York Times. Retrieved from [Link]
CBS invades Cuba, returns with Irakere: Havana jam. (1979, May 3). Down Beat, 10.
Herrington, A. J. (1985). Classrooms as forums for reasoning and writing. College
Composition and Communication, 36(4), 404-413.
Kerlinger, F. N. (1986). Foundations of Behavioral Research. (3rd Ed.). New York: Holt,
Rinehart and Winston Publishers.
Maas, J. B. (Producer), & Gluck, D. H. (Director). (1979). Deeper in hypnosis [Motion
Picture].
Englewood Cliffs, NJ: Prentice-Hall.
Page 77 of 78
Prepared by Mr. James
Mandel, B. J. (1978). Losing one's mind: Learning to write and edit. College Composition and
Communication, 29, 263-268.
Medley, D. M. (1982). Teacher effectiveness. In H. E. Mitzel (Ed.), Encyclopedia of
educational research (Vol. 4, pp. 1894-1903). New York: The Free Press.
Raymon H. Mulford Library, The University of Toledo Health Science Campus. (2008).
Instructions to authors in the health sciences. Retrieved June 17, 2008, from
[Link]
Sillick, T. J., & Schutte, N. S. (2006). Emotional intelligence and self-esteem mediate between
perceived early parental love and adult happiness. E-Journal of Applied Psychology,
2(2), 38-48. Retrieved
from[Link]
Stultz, J. (2006). Integrating exposure therapy and analytic therapy in trauma treatment.
American Journal of Orthopsychiatry, 76(4), 482-488. doi:10.1037/0002-9432.76.4.482
revised 06/23/08 jam 1

Page 78 of 78
Prepared by Mr. James