1

RESEARCH METHODS

DEFINITION OF TERMS
Research - is a process of inquiring. It is to carry out a diligent inquiry or critical examination of
a given phenomena

It also involves a critical analysis of existing conclusions or theories with regard to newly
discovered facts.

Variable means a measurable characteristic that assumes different values among the subjects.
Some variable are attributes that can be expressed quantitatively like height, while others can be
expresses in categories like sex. They can either be dependent of independent or confounding.

Dependent variable
The behavior measured by the end of the study to see how it has been affected by
administration of the independent variable.
Independent variable -The variable that a researcher manipulates

Confound variable is a variable that is not deliberately manipulated by the researcher that
systematically biases the research.

Types of variables
Discrete variables
This is a variable that can take only certain values and none in-between e.g. numbers of times a
student have attend ended classes can only take whole numbers. In discrete variables you can only
count events such that can only result to a whole number.

Continuous variables
The characteristic of a continuous variable is that within a certain limit, its values may range and
any value at all may be possible within those limits height, weight, temperature, age.

Assumption- ideas that are tentatively accepted as being true without further explanation

Data –this refers to all the information that a researcher gathers for her or his study

Primary data-this is the information that one obtains from the field

Secondary data this is information obtained from research articles or books or official
records and reports.

Data collected can be either qualitative or Quantitative form

Qualitative data: Categorical or nominal data where there is no discrete data and observations are
made in form of words [Link] status, sex, education level
 2

Quantitative data: numerical data that is quantifiable e.g age, weight, score

Population: Whole set or entire group of individuals, events or objects having common observable
characteristics where a sample is drawn from
e.g
• All women of reproductive age in the country
• All university students in Kenya
• All children under five years in the country

a researcher first defines a population to which she wants to generalize the results to the
absolute population-also refers to as the target population.

Since the population may be large or scattered over a large area a researcher draws samples
from the accessible population.

The accessible population should be comparable to the target population for generalization in
the characteristics relevant to the study.

e.g
Women of reproductive age in the district
University students at Kenyatta University
Under-five children in the district

Sample – A subset and a representation of a population. A researcher selects a certain number of

members or cases from the accessible population

Sampling – Process of selecting a stated number of individuals from a larger group in such a way
that the individuals selected represent the large group from which they were selected.

INTRODUCTION TO RESEARCH CONCEPT

Research is the procedure which is used systematically and with the support of demonstrable fact,
the answer to the question or the resolution of a problem. Basic or pure research is the method of
problem solving using the principles of scientific methods. This procedure is what referred to as
research methodology. The research process starts with formulating a research problem that can
be investigated through research procedures.

PURPOSE OF RESEARCH
1. To discover or to obtain new knowledge- This involves discovery of new facts, correct
interpretation of these facts. This is the main source of knowledge. It is the most reliable
and efficient sources
2. It helps to describe a phenomenon. Description provides knowledge which is the basis of
other purposes of research. Any event needs thorough description like age, shape, types.
 3

3. It helps in predicting the outcome of a particular phenomenon. If one is able to know a

particular phenomenon you can predict another on the basis of another. Research can be
extended to a wider group.
4. It enables control, one can manipulate one phenomena to estimate its impact on another
phenomena
5. It enables us to explain a phenomenon. The explanation involves carrying out accurate
observation and measurements of phenomena. For you to be able to explain a particular
phenomenon you need to be able to describe it and observe factors of its occurrence
6. It enables us to develop theories. Theory development involves formulating concepts, laws
and generalization about a given phenomena
7. Research can be done to validate existing theories

RESEARCH PROPOSAL DEVELOPMENT

Research process starts by formulating a research problem that can be investigated through
research procedure

Identifying a research problem

Identify the broad area that one is interested in-should be related to your profession and goals of a
researcher.

Identify the specific problems in that area that can form a basis of research study i.e narrow down
from broad area to specific problem

Factors to consider:-

Research problem should be an important one in such that;-

• Lead to findings that have widespread implication in a particular area
• Challenge some commonly held truisim
• Review inadequacies of existing laws, views or policies
• Cover a reasonable scope-not too wide or too narrow

NB/scope of the study is determined by

• Time available to carry out the research
• Finances available
• Availability of equipment
• Availability of subjects of study

Ways of identifying a research problem

1. from existing theories
2. from literature
3. discussion with experts-gives out current problems that can be researched
4. previous research studies-add to the knowledge that has been built by others
5. replication-to find out whether findings hold over time and across regions
 4

6. personal experiences
7. media-issue frequently reported in the media-discussed in public fora

Introduction to Research proposal development

▪ Research proposal is a summary of the steps of a research design. It is important to develop a
formal proposal before a research is done. It is a written plan that identifies the major elements
of the study.

▪ The process of writing a proposal consist of number of closely related activities that overlap
continuously rather than following strictly prescribed sequences
▪ The proposal format differs from one department to another or the purpose either academic
proposal or for funding. In this lecture we will confine ourselves to development of academic
proposals.

▪ The content of the proposal is in future tense except the areas dealing with literature review.
In proposal writing one should avoid personal pronouns like I, me she, he etc. In proposal
writing the researcher should discuss the contemplated research, why it is being contemplated
and how the study will be carried out

▪ A research proposal should stipulate the anticipated research process which consist of a series
of action or steps necessary to effectively carry out a research and the co sequencing of these
steps

▪ The major process in proposal writing involves the identification and definition of the
problem

▪ Proposal focuses on discussing the main body of research,

Components of research proposal

The proposal has the following main components;-
▪ Preliminary section-this contains the title, acknowledgement, list of figures and
abbreviation, abstract, acronyms and abbreviations
▪ Introduction (chapter one) –this has several sections such as background to the problem
,problem statement, objectives, purpose and justification of the study
▪ Literature review (chapter two)-this contains literature related to the study topic
▪ Methodology (chapter three) has several sections namely research design, sample and
sampling criteria, population. data collection, study procedure and data analysis

NB/ there are other minor sections such as preliminary section, time plan, budget appendices
and references which are also very important in a proposal

PRELIMINARY SECTION
Title
The title is supposed to be informative.
 5

Functions of a title are that

▪ It gives readers some initial information about the area of research.
▪ Should give indication of the major variables of research
▪ should indicate target population and if possible the geographical area
NB/ Title should not exceed twenty words

Dedication

This section comes after the title, its optional. You dedicate the work to a person you deem special
in your life
Abstract
Abstract should present the purpose of the study, population studied, major results and conclusion
of the study and should not be more than one page.

Table of content
It indicates which page each of the section or chapter is located
Guides the reader in locating various sections of the proposal
It contains the chapter heading, the main heading and subheading and the corresponding page of
each in the body of the document

List of tables
It indicates where tables are located within the proposal and thus guides the reader in locating the
tables

List of figure
Figures include maps, diagrams and photographs or any other pictorial representation used in the
document. It indicates where figures are located within the proposal thus acts as a guide to the
reader in locating the figures.

Acronyms and list of abbreviations

This section will give the meaning of all acronyms and abbreviations used in the report to improve
the understanding of the reader.

When using an acronyms, write in full the first time that phrase is used thereafter use the acronym
Abbreviate units of measure only when they are used often in the document
Use only those abbreviations that the reader will understand

INTRODUCTION
In the introduction the background of the research concept is described. It also gives the
background information of the problem, objectives, hypothesis and the limitations of the study.
The topic under investigation is well introduced.

Introduction outlines the gaps that exists in the area of study and presents the rationale of the study.
The researcher should quote existing studies and theories to support the problem statement
 6

This is a from a global, national and local context perspective. It also describes the origin of the
problem that is to be solved by the research. Back ground information provides an insight and an
idea of what is being investigated.

STATEMENT OF THE PROBLEM

It is a specific statement that clearly conveys the purpose of the research study. It focuses on the
phenomena that the researcher desires to describe, predict or control or explain.

Problem statement contains what exactly will be studied by the researcher. It states a situation that
requires a solution. It brings out the gap that the current study want to address.

The problem should be stated precisely and in clear terms, concisely and definitely by identifying
independent and dependent variables. It should also find out how they relate to each other.
A good research problem statement should have the following criteria
1. Express a relationship between two or more variables
2. Should identify the population of interest
3. Identify the problem area of the respective study

STATING THE RESEARCH PROBLEM

Starts with a brief introductory section where one introduces the general area of study, then narrow
to specific problem of study.
Characteristics of a good research problem
1. Clearly written and in such a way that the readers interest is captured immediately
2. The specific problem identified in the problem statement is objectively researchable
3. The scope of the specific research problem is indicated
4. The importance of the study in adding to new knowledge is stated clearly
5. Must give the purpose of research
1. Always state the problem in a complete grammatical sentence with as great economy of
words as possible.

OBJECTIVES OF RESEARCH
Objective is any kind of desired end or condition. Or the specific aspects of the phenomena under
study that the researcher desires to bring out at the end of the research study

It should be stated clearly and should be testable. They are based on measurable variables of the
study and they should be specific.

Importance of objectives
▪ They determine the kind of the questions to be asked thus assist in questionnaire development
▪ They determine the data collected and the data analysis method
▪ They also determine the study design

Examples of neutral words used in stating the objective

✓ To determine
 7

✓ To compare
✓ To investigate
✓ To differentiate
✓ To explore
✓ To find out
✓ To examine
✓ To establish
✓ To inquire
✓ To test

PURPOSE OF RESEARCH

This section conveys the focus of the research study in one or two sentences.

It is a broad statement of what the study is focusing on. It identifies why the study will be conducted
and spells out the reason or objectives of the research. In the purpose the variables and the
population must always be indicated. The purpose should indicate the concepts or variables in the
study and where possible the relationship between the variables should be stated, purpose should
state the target population and should be consistent with the variables and target population
operationalised in the methods’ section of the study.

e.g
• The purpose of this study is to investigate the resource management skills of women in
small scale business in Kenya
• To establish the effect of complementary feeding practices on nutrition status of children
under-five years in Kenya
• To find out the relationship between cattle grazing and land degradation in marginal areas
of kenya

RESEARCH QUESTIONS
This section outlines the questions that the researcher want outlined in the study. They are included
in the research to deal with issues that are not covered by the objectives. They give a basis for
conclusions once the answers are provided.

HYPOTHESIS
A hypothesis is defined as a researcher’s prediction regarding the outcome of the study or an
educated guess which the researcher has to test or validate.
It states possible differences, relationships or causes between two different variables or concepts

They are derived from existing theories, previous researches or personal observations or
experiences
 8

A researcher needs to formulate a hypothesis or hypotheses for the research. It can either be one
or many depending on the nature of research. One can either accept or reject the hypotheses.

Characteristics of hypothesis
▪ It must clearly state the expected relationship between the variables
▪ Must be in continuous tense or generally accepted truth
▪ Must be testable
▪ Must be related to an empirical phenomena
▪ Must be testable within a short period of time
▪ State hypotheses such that replication can be received in form of empirical operation
▪ They must be consistent with common sense or generally accepted truths

Types of hypothesis
A hypothesis can either be;
1. Null hypothesis (HO)
2. Alternative hypothesis (HA)

Null hypothesis (HO)

It states that there is no relationship or difference in concepts being tested. Null hypothesis signifies
no difference and any relationship is due to error.

e.g there is no relationship between complementary feeding practices and nutrition status of
children under-five years- states no relationship

Alternative hypothesis (HA)

This states that there is a relationship or a difference between variables. It can either be non-
directional

e.g
High caffeine content in the blood affects brain performance-this is non directional relationship
There is a difference in nutrition status between children who are exclusively breastfed and those
on replacement feeding- not told which group has better nutrition status

High caffeine content in the blood improves brain performance-gives the direction of the effect

SIGNIFICANCE
This section describes how the results of the study can add to the theory of knowledge in the area
identified. It also outlines the implication of the finding in the area of the study. It outlines how
various sectors associated with the research can actually use the information.

JUSTIFICATION
This provides the rationale of the research. It answers question like;
• Why do we undertake the research?
• What is the importance of carrying out the research?
 9

If someone told you not to undertake the research, and you feel you want to continue to do it, what
adequate treason would you give? The detailed reason you can give is a justification of the
research.

LIMITATION
Aspect of research study that influence results negatively and researcher has no control over them.
For example, a study may be focusing on children under-fives but is limited to only the well
children thereby excluding the sick ones.

ASSUMPTIONS
An assumption is any fact a researcher takes to have some truth without verifying it. They help
explain a situation and help in forming boundaries.

CONCEPTUAL FRAMEWORK
It is an organisation of the concepts that are related to the problem of the research. It simply links
the concepts variables and how they relate to the problem. The researcher conceptualizes the
relationship between variables in the study and shows the relationship graphically. It is may also
be done in diagrammatic format.

OPERATIONAL DEFINITION OF TERMS

This is definition of key words as pertains to the intended meaning in the research. Words are
defined as they have been used in the text.

INTRODUCTION TO LITERATURE REVIEW

Involves the systematic identification, location and analysis of documents containing information
related to the research problem being investigated

Literature review gives overall information about the general area then narrows to specific area. It
expounds upon the background of the study and in further definition of problem of the study. It
provides the basis for subsequent development of hypotheses.

As a guideline for literature review you look at journals or publications with studies or researches
that are dealing with each of the variables in your study. You need to be critical when analyzing
literature. Check for point of weakness, strength validity and adequacy of the truth.

Note the gaps left out in already done studies, which the study want to address. If you are dealing
with many variables it is important to organize your literature into sections and each should deal
with a particular variable.

TOOLS OF RESEARCH
1. The library and its resources
2. Measurement techniques
3. Statistics
4. The computer and its software
5. Language that may be critical to the execution of the research project.
 10

SOURCING FOR INFORMATION

Where do you get information for reference?
▪ Government documents-policy papers, research reports owned by government,
▪ Thesis and dissertations
▪ Papers presented at conferences
▪ Scholarly articles
▪ Books
▪ References quoted in books
▪ International indices
▪ Developmental agencies e.g. UN, NGO, s International agencies etc.
▪ Archives – historical and anthropological data to show trends.
▪ Local records and Registries land titles, register of births, death, marriages, local firms etc.
▪ Maps
▪ Newspapers
▪ People – individuals with particular interests.
Time spent in collecting secondary data is very valuable as it helps in directing the research and
saving time on unnecessary primary data.

ROLE OF LITERATURE REVIEW

Why do we review literature?
▪ Determine what has been done already- this helps to
a. Avoid duplication
b. From the framework within which research findings will be interpreted
c. Demonstrate familiarity with the existing body of knowledge
▪ Reveals strategies, procedures and measuring instruments which have been found useful
in the investigating the problem in question-to avoid mistakes that have been done by other
researchers
▪ LR also can suggest other approaches and procedures and the researcher can opt to try the
suggested approaches
▪ Make the researcher familiar with previous studies and thus facilitate interpretation of
results easier.
▪ To identify any gaps in knowledge so that to provide on entry point for the research. You
should examine the gaps very carefully and determine how your research is going to fill in
these gaps. It helps you to come up with other new approaches to the problem.
▪ To study the methods and techniques used by other researchers to collect or conduct the
research and analyze their strengths and weaknesses.
▪ To see the connections and relationships between the different findings of the studies in
the same area of your interest.
▪ To look at the conceptual frameworks from other studies and see if you could adopt it to
your study.
▪ To sharpen and deepen your understanding of possible factors that can serve as guides in
designing your research.
▪ Helps the research to narrow down a specific problem
▪ To know more about subject matter
 11

STEPS IN GETTING LITERATURE REVIEW

▪ Familiarize with the library
▪ List key wards to guide you in literature search
▪ Read, analyze and organize information in orderly manner
▪ Summarize major points in articles
▪ Make outline of the main topic and things in order and how to be presented
▪ Analyze each reference where it would fit, in the heading or subheading
▪ Note the aspects which seem to contradict what other people has done

Keeping a systematic record

Once the researcher has identified and located the pertinent literature, it is necessary that he or she
establishes a systematic method for recording pertinent information.
Initially, the approach was to write notes onto index cards. Each article would be entered
separately on a card. Each entry would include the following information.
1. Author (s) name (s)
2. Date of publication
3. Title of the article, report or book
4. Name of the journal or publisher
5. Volume and number of the journal
6. Place of publication (if a book)
7. Pages on which the material appears and
8. The notes you have made about it.

CHAPTER THREE: METHODOLOGY/ MATERIALS AND METHODS

RESEARCH DESIGN
The research design refers to the overall strategy that you choose to integrate the different
components of the study in a coherent and logical way, thereby, ensuring you will effectively
address the research problem; it constitutes the blueprint for the collection, measurement, and
analysis of data.

The design can also be defined as the plan for the study, providing the overall framework for
collecting data. Once the problem has been concretely formulated, a design is developed in order
to provide a format for the detailed steps in the study. The design is relatively specific consisting
of a series of guidelines for systematic data gathering. The type of design depends upon the
statement of the problem.
There are four main questions that the researcher must answer in order to bring the research
planning and design into clear focus. These are;
Research design has two basic purposes;
 12

1. To provide answers to research questions

2. To control variance
Research design are set to enable the researchers to answer research questions as validly,
objectively, accurately and economically as possible.
The design tells us;
▪ What observations to make?
▪ How to make them?
▪ How to analyse the quantitative representation of the observations.
Design does not tell us precisely what to do, but rather it suggests the directions of the observation
making and the analysis. An adequate design suggests the directions of observation making and
analysis.

An adequate design suggests e.g.

▪ How many observations should be made?
▪ Which variables are active
▪ Which are attribute

This will help us to act to manipulate the active variables and to categorize the attribute variables.
Design tells us what kind of statistical analysis to use. Finally, an adequate design outlines possible
conclusions to be drawn from the statistical analysis.

.TYPES OF STUDY DESIGNS

Research designs depends on the type of research
A. Non experimental stduy design
1. Descriptive studies
i. Case study
ii. Cross-sectional/analytical study design
2. Correlation studies/Exploratory
i. Cohort study/longitudinal design-In this design, a single group is
followed over some time period
ii. N Retrospective (or Case Control Studies)
B. Experimental studies
i. True experimental -They test Efficacy: the benefit of an intervention compared to a
control or standard program under controlled, randomized conditions
Principles of true experimental design: There are three basic principles of experimental design
which were developed by Sir Ronald A. Fisher.
(i) Randomization
(ii) Replication
(iii) Local control
Types of true experimental study designs
i. Completely randomized design
ii. Block design
iii. Latin square
iv. Solomon Four-Group design
v. Pre-test posttest control randomized group design
ii. Quasi-experimental -do not use randomized assignments for comparisons
 13

Examples
i. One group post-test only design
ii. One-group pretest-posttest design
iii. Comparison Group Design

POPULATION AND SAMPLE

Target population refers to the population to which a researcher wants to generalize the results
of the study. E.g a study on factors affecting study progression among University students
The target population here is University students.

If the researcher decides to do his/her study among JKUA students then this becomes the
Accessible population

Accessible population - should not be influenced by convenience. The rationale must be based
on some theories, previous studies or professional experiences. The accessible population must be
the most representative of the target population.

The target population and the accessible population must be comparable in most characteristics
which are important to the study (population validity)
The accessible population must be defined accurately so that others can determine how far ones
result should be generalized.

Sample size

After defining the target population and accessible population the next thing is to determine a
sample from it

Sample size depends on the number of variables in the research, the type of research design, data
analysis and the size of the accessible population

for descriptive studies, there are various methods of determining sample size
A. 10% of the accessible population and for experimental studies at least 30 cases for each group.

NB where time and resource allows the sample size should be as big as possible-it gives the
research strength
A small sample size may not produce silent characteristics of the accessible population to an
acceptable degree and can result to sampling error (differences btwn the sample and the accessible
population)

B. In social science research the following formula can be used in determining the sample size
(Fishers et al., 1983)

Fisher’s formula is used to determine the sample size

 14

For population more than 10,000, the formula is n= [z²pq/d²]

Where,
n- The desired sample size
z- The standard normal deviate at the required confidence interval (95 probability error equal
to 1.96)
p- The proportion of occurrence of the phenomenon (0.5 for unknown)
q- The proportion of non-occurrence is (1-p) = 0.5
d- The level of statistical significance (0.05 for 95 percent level of significance)

n= [(1.96)² (0.5) (0.5) / (0.05)²]1= 384

n= 384

When the population is less than 10,000 the formula is Nf = n/1+ (n/N)

Where;
Nf - is desired sample when population is less than 10,000
n- is sample when the total population is more than 10,000
N- is the estimated population of the area being studied
For example if the population is 800
Therefore, the sample consisted of 219 female students from the following calculation:
nf = 384
1+ (384/800)

= 259.
Therefore, the sample should consist of 259
NOTE- one should always add 10 % to the calculated sample to cater for attrition ot non response

SAMPLING TECHNIQUES/ PROCEDURES

Sampling is the act, process, or technique of selecting a suitable sample, or a representative part
of a population for the purpose of determining parameters or characteristics of the whole
population.

Methods Sampling
Methods of Sampling can be categorized into two; Random/probability sampling and non-
random/non-probability sampling.

1. non-random/non-probability sampling.

This involves selecting a sample that is not a representative of the population. It is mainly used in
qualitative studies since they focus on in-depth information and not making inferences or
generalisations. Under non-probability sampling we have the following sampling techniques.
 15

A. Purposive sampling

In this method the researcher uses the cases that have the information that the researcher requires.
The cases are selected intentionally handpicked because they have the characteristic which are
required by the researcher. The disadvantage of this method is that results may be easily dismissed
for being extreme although they may be representative of an extreme group.
Can be used as part of multistage sampling procedure to get to the location of where the unit of
study are

B. Snow ball sampling

Initial subject with the required characteristics are identified using purposive sampling technique.
The identified subjects then helps in naming the others who have the same characteristics required
until the researcher gets the number of cases he or she requires. This method is mainly used when
the population that possess the characteristics under study is not well known and there is need to
find the subjects.

C. Convenience or accidental sampling

This method takes the units or subjects as they arrive and there is no attempt to control bias. For
example, one can pick every tenth customer that comes to restaurant and interview them, or every
10th patient that comes to the antenatal clinic. You do this until you have covered the required
number of subjects for the study.

2. Probability sampling/random sampling

This involves any method of sampling that utilizes some form of random selection. In order to
have a random selection method, you must set up some process or procedure that assures that the
different units in your population have equal probabilities of being chosen. In this type of sampling
the researcher can specify in advance that each segment of the population will be represented in
the sample. This is done by selecting subjects from a larger population. Random sampling allows
generalization to a larger population. It allows the use of inferential statistics
The manner in which these are selected is very important. Probability sampling involves the
following techniques

A. Simple Random Sampling technique

This is the simplest form of random sampling. Its main objective is to select units out of population
such that each has an equal chance of being selected. The procedure uses a table of random
numbers, a computer random number generator, or a mechanical device to select the sample.
Simple random sampling is simple to accomplish and is easy to explain to others. Because simple
random sampling is a fair way to select a sample, it is reasonable to generalize the results from the
sample back to the population.

B. Stratified Random Sampling,

Also sometimes called proportional or quota random sampling, it involves dividing your
population into homogeneous subgroups and then taking a simple random sample in each
 16

subgroup. It’s objective is to divide the population into non-overlapping groups. There are several
major reasons why you might prefer stratified sampling over simple random sampling.
First, it assures that you will be able to represent not only the overall population, but also key
subgroups of the population, especially small minority groups. If you want to be able to talk about
subgroups, this may be the only way to effectively assure you'll be able to.

E.g dividing the students in JKUAT according to the colleges they come from, then select a
representative sample from each college randomly. If calculated sample size is 392 and you have
5 college then you divide 392/5=78.4 thus you randomly select 79 students from each college -
this is called
C. Proportional stratified sampling
In the simple stratified random sampling design, all the strata of the population were equal in size.
But let us now look at a population which is different. For example; religious groups in the
community.
• 3000 protestants
• 2000 Catholics
• 1000 Muslims

In this situation the research has a proportional mixture in the ratio of 3:2:1. First step is to select
from each of the individuals groups a random sample proportionately representative of the
numerical strength of each of the components within the entire population.

D. Systematic Random Sampling

In this method every Kth case in the population frame is selected for inclusion in the sample. Here
are the steps you need to follow in order to achieve a systematic random sample:
• number the units in the population from 1 to N
• decide on the n (sample size) that you want or need
• k = N/n = the interval size
• randomly select an integer between 1 to k
• then take every Kth unit

First sample is picked randomly and the remaining units are picked at predetermined intervals.
Given an inclusive list of a population, the first name for the sample must be chosen randomly,
and then in the procedure known as systematic, every nth name would be taken until the full
complement is reached. This is easy but can create a bias.
Odd and even numbers can be used to choose predetermined sequence clusters for sampling. Or
Toss a coin, heads dictates that we begin with the first number in the arithmetic progression of
odd- numbered clusters. Tails demands that we begin with the even numbered digit and follow the
arithmetic progression in that mode (4, 6, 8, 10, 12).
Caution should be exercised in choosing the appropriate sampling design. The design should be
considered as a tool of research; care should be taken to address the characteristics of the research
population
 17

E. Cluster (Area) Random Sampling

The problem with random sampling methods when we have to sample a population that's disbursed
across a wide geographic region is that you will have to cover a lot of ground geographically in
order to get to each of the units you sampled.
Imagine taking a simple random sample of all the residents of New York State in order to conduct
personal interviews. By the luck of the draw you will wind up with respondents who come from
all over the state. Your interviewers are going to have a lot of traveling to do. It is for precisely
this problem that cluster or area random sampling was invented.
In cluster sampling, we follow these steps:
• Divide population into clusters (usually along geographic boundaries)
• Randomly sample clusters
• Measure all units within sampled clusters
The units of the population are divided into clusters, such as city estates or residential areas and
clusters are randomly sampled. In Cluster sampling it is important that each cluster be as similar
to the others as possible and that within the clusters the individuals be heterogeneous.

From all the clusters, a random selection of specific clusters is made as the nucleus from which
the sample population is ultimately derived again by random selection. This method, although cost
effective, increases the sampling error for a given sample size whenever people living within a
cluster are similar in ways relevant to the purposes of the survey.

DATA COLLECTION TECHNIQUES AND TOOLS

Data-collection techniques allow us to systematically collect information about our objects of
study (people, objects, phenomena) and about the settings in which they occur.

Observations -obsrvation checklist

Observation is a technique that involves systematically selecting, watching and recording
behaviour and characteristics of living beings, objects or phenomena.
Observations are normally made on objects. For example, the presence or absence of a latrine and
its state of cleanliness may be observed. Here observation would be the major research technique.
If observations are made using a defined scale they may be called measurements.

Measurements usually require additional tools. For example, in nutritional surveillance we

measure weight and height by using weighing scales and a measuring board. We use thermometers
for measuring body temperature.
Observations are done using observation checklist.

Interviewing
An interview is a data-collection technique that involves oral questioning of respondents, either
individually or as a group. Answers to the questions posed during an interview can be recorded by
writing them down (either during the interview itself or immediately after the interview) or by
tape-recording the responses, or by a combination of both. Interviews can be conducted with
varying degrees of flexibility. The two extremes, high and low degree of flexibility, are described
below

TOOLS
 18

Questionnaires
A written questionnaire (also referred to as self-administered questionnaire) is a data collection
tool in which written questions are presented that are to be answered by the respondents in written
form.
A written questionnaire can be administered in different ways, such as by:
• Sending questionnaires by mail with clear instructions on how to answer the questions and
asking for mailed responses;
• Gathering all or part of the respondents in one place at one time, giving oral or written
instructions, and letting the respondents fill out the questionnaires- researcher administered
questionnaire
• Hand-delivering questionnaires to respondents and collecting them later.
The questions can be either open-ended or closed (with pre-categorised answers).

Rules of constructing a questionnaire

• list the objectives that you want the questionnaire to accomplish
• determine how each information obtained from the questionnaire will be analyzed
• Clarity of questions. Do not use terms such as “several” ‘most”-they have no precise
meaning
• if term has several meaning and it has to be used in the questionnaire then it has to be
defined
• short questions are preferred than long questions
• state questions positively as much as possible
• biased questions must be avoided-questions that suggest one answer may be better than
the other
• sensitive questions must be avoided
• avoid important questions at the end of the questionnaire
• arrange questions according to themes

Focus group discussions (FGD)

A focus group discussion allows a group of 8 - 12 informants to freely discuss a certain subject
with the guidance of a facilitator or reporter. The interviews are selected from the study
participants

Key informants interviews- this are individuals who have authority of informtaion in a particular
subject area. E.g managers, student leader, nurses etc. They are not part of the calculates sample
(study participants)
 19

ETHICAL STANDARDS IN RESEARCH.

ETHICAL PRINCIPLES IN RESEARCH

1. The Principle of Justice
The concept of justice in research is interpreted to mean a fair distribution of the benefits of
research. For example, though most of the researches on vaccines in HIV and AIDS are conducted
in the developing world, developing countries and the population originally researched may not
be able to afford these vaccines and will thus not get the benefit of the research.

2. The Principle of Beneficence

In general, this principle requires that the actions of researchers are directed at improving the well-
being of study participants, and they should not cause harm to the participant. While this may
sound obvious, there are several important issues in research that violate or may potentially violate
this principle. For example, participation in a research may mean offering time which may result
in other priorities not being met. Interviewing rural women may reduce time they have for child
care or to collect firewood or water.

3. Respect for autonomy

This principle states the requirement that those who are capable of deliberating personal choices
should be treated with respect for their capacity of self-determination or decision. On the other
hand, persons with diminished or impaired autonomy or those in dependent or vulnerable positions
should be protected against harm or abuse.
 20

4. Voluntary participation
This principle dictates that all subjects should be recruited into the study upon their informed
consent. Participation should be voluntary and should be free of coercion, and there should be not
be under undue influence, inducement or intimidation. Informed decision decision-making
requires that the information from the investigator be:
• Comprehensive. This should involve; the study procedures, the risks, benefits and compensation
if any.
• Comprehensible (simple language should be used)
• The decision by the subject should be based on competence and the ability to understand.
Participant should give either verbal or written consent. Those who are illiterate should give
consent based on thumbprint. It is recommended that written or thumb rather than verbal consent
be solicited. Ethical review committees will usually expect a statement on how informed consent
will be solicited from the prospective study participants.

5. Confidentiality
Participants usually expect the information from them to remain confidential. Efforts to ensure this
are essential, such as not obtaining personal information unless it is absolutely necessary and
deleting personal information as soon as there is no longer need for it. This also includes results
of any specimens that may have been collected. Researchers should clearly stipulate in the research
proposals how confidentiality will be maintained. The prospective participants should also be
informed how confidentiality will be maintained.

6. Risk of Harm
Ethical standards also require that researchers not put participants in a situation where they might
be at risk of harm as a result of their participation. Harm can be defined as both physical and
psychological.
As we develop our data collection techniques, we need to consider whether our research
procedures are likely to cause any physical or emotional harm. Harm may be caused, for example
by;
• Violating informants’ right to privacy by posing sensitive questions or by gaining access
to records which may contain personal data;
 21

• Observing the behaviour of informants without their being aware (concealed observation
should therefore always be crosschecked or discussed with other researchers with respect
to ethical admissibility);
• Allowing personal information to be made public which informants would want to be kept
private, and
• Failing to observe/respect certain cultural values, traditions or taboos valued by your
informants.
Several methods for dealing with these issues may be recommended:
• Obtaining informed consent before the study or the interview begins
• Not exploring sensitive issues before a good relationship has been established with the
informant
• Ensuring the confidentiality of the data obtained
• Learning enough about the culture of informants to ensure it is respected during the data
collection process.

Professional code ethics

1. Make sure all the research you do is necessary.
▪ Inform subjects of all procedures and expectations
▪ Do not deceive them. If deception is essential, consider the possibility of warning
subjects that they may be deceived.
▪ Do not intrude their privacy.
▪ Do not expose them to any harm
▪ Every person is entitled to the right of privacy and dignity of treatment.
2. Researchers must maintain scientific objectivity
3. Researchers should recognize the limitations of their competence and not attempt to engage
in research beyond such competences. Ask friends, colleagues and potential subjects to
review your research proposal and comment on common ethical problems.
4. Research findings should be presented honestly and without distortion.
5. Keep subjects identities confidential, as soon as names can be separated from data, do so.
6. The researcher must not use the prerogative of a researcher to obtain information for other
than professional purposes.
7. The researcher must acknowledge all assistance, collaboration of others, or source from
which information was borrowed from others.
8. The researcher must acknowledge all financial assistance/support in research report.
9. The researcher must not accept any favours, grants, or other means of assistance that would
violate any of the ethical principles mentioned above.
10. Do pilot studies and ask participants for their detailed reactions.
11. A researcher should have mastered the common skills and abilities to write and
communicate effectively. These include the ability to spell correctly, to write a
grammatically correct and effective sentence and to construct a unified and coherent
paragraph. Asking someone to ghost your document is mythical and academic dishonest.
12. Any use of writings that belongs to another demands full acknowledgment to avoid
plagiarism.
 22

ETHICAL CLEARANCE TO CONDUCT RESEARCH

The researcher should seek clearance from authorized ethics review committee
LEGAL AND ADMINISTRATIVE ISSUES IN RESEARCH
Legal Issues in Research

Plagiarism: Defined in the from the Oxford English Dictionaries as "the wrongful
appropriation, close imitation, or purloining and publication, of another author's language,
thoughts, ideas, or expressions, and the representation of them as one's own original work."
Plagiarism is now considered academic dishonesty/academic fraud and a breach of journalistic
ethics, subject to sanctions like expulsion and other severe career damage
([Link]/wiki/Plagiarism, accessed on 08/10/209). Within academia plagiarism is
punished by sanctions ranging from suspension to termination, along with the loss of
credibility and integrity (Kock, 1999; Kock and Davidson, 2003).

Administrative Issues in Research

It is a requirement in Kenya and other countries that any research be authorized by an appointed
government department/organization. For academic researches, the Universities have a body
mandated to authorize and give permission for any student to conduct research upon submission
of an acceptable research proposal.

For undergraduate, the department reviews and approves the research proposals after which the
student receives a letter of authorization to conduct the research.

Further permission from the administration leaders from where the research is to be conducted.
For example, if the research is to be conducted in a City Council School or Hospital in Nairobi,
the researcher will have to seek and obtain permission to conduct to the research from the Local
Authority Officials in charge of Health and Education in Nairobi. In addition, it is also necessary
that the researcher informs the local administration such as the District Officers and Chiefs of their
intention to conduct a research in their areas of jurisdiction
 23

Measurements scales

The operational definition of variables yields information or data which can be analysed.
The choice of statistical procedure to be applied is largely determined by the type of measurements
scale used in operationalization of variables. There are four measurements scales: nominal, ordinal,
interval and ratio

Nominal scales

This is the lowest level of measurement this measurement merely groups subjects into or cases
from the sample into categories. Cases in each category has some common set of characteristics.
Variables which can only be measured at nominal level include; sex, marital status, employment
status, religion, shape, colour.
Numbers or numerical values are usually assigned to various categories for the purpose of
identification. NB/ the numerical assigned to various categories do not represent any order or
quantities

Statistics applied-measures of central tendency-mode

Ordinal scale
This is an improvement on the nominal scale. It is used when one detects a differing degree of the
attribute being measured among the subjects. Ordinal scale do not only categorise subjects but into
also ranks them into some orders. In ordinal scale numerical are used to represent relative position
or order among the values of the variables examples of variables that be measured at ordinal level
Social class, military rank

Statistics applied-measures of central tendency-mode

Interval scale
The numerical assigned to each measure are ranked in order and the intervals between the
numerical are equal. Numerical used represent quantities and mathematical operations on the
numerals would yield meaningful values.

However this mathematical operations are limited to additions and deductions. Multiplications and
divisions are not applicable.

In interval scales there is no true zero pint. The maximum and the minimum points of the scale are
only arbitrary

e.g a student who get 80% in HCU 300 does not mean that he has twice the knowledge as one who
get 40%. And the one who gets 0% does not reflect total absence of knowledge in the same subject
Examples of interval scales e.g temperature, test scores
 24

Statistics applied-measures of central tendency-mode, median

Measure of dispersion-range, standard deviation, variance

Ratio scale
This is the highest level of measurement. It is also the most precise method of measuring variables.
A ratio scale would have all the characteristic of the other scales.
It has true zero point and mathematical operations can be applied to yield meaningful values

Examples height, weight, age, blood pressure etc

Intervals between numerical are equal

Statistics applied-measures of central tendency-mode, median and mean

Measure of dispersion-range, standard deviation, variance

DATA ANALYSIS
A researcher should describe the intended techniques to be used in analysing the data she is
collecting. In most case one may use more than one method. Method of analyses chosen is
dependent on the type of research, hypotheses to be tested and the research objectives. Most studies
use descriptive and inferential statistics.

Descriptive statistics summarizes and describes the sample -e.g frequencies, percentages, mean
and the data can be presented inform of tables, charts, graphs etc

Inferential statistics will enable the researcher to infer the sample results to the population
researcher should state what he hopes to achieve by using the data analyses techniques chosen. For
example if Pearson product moment correlation, chisquare, odds ratio, t-test, ANOVA, ANCOVA
etc