Chapter Four

Research

Design
1
 Research Design
• strategy used to answer research questions.

• framework that outlines the theories, models, and

methods used to gather and analyze data to produce
answers.
• arrangement of conditions for the collection and
analysis of data in a manner that aims to address the
research problem.
2
 Cont’d…
• Research design should be inline with:

• What is the study about? (Problem definition)

• Why is the study being made? (Justification)

• Where will the study be carried out? (Location)

• What type of data is required? (Quantitative, Qualitative,

Primary, Secondary)

3
 Cont’d…
• The research design should be inline with:

• Where can the required data be found (target population)

• What will be the sample design (technique chosen)

• What data collection techniques will be used?

(observation, interview, questionnaire, or document
analysis).
• How will the data be analysed (Data analysis techniques &
tools to be employed).
4
 Research Methodology
 involves activities as :
 identifying problems
 reviewing the literature
 formulating hypotheses
 the procedure for testing hypotheses
 measurement
 data collection
 analysis of data
 interpreting results and
 concluding
Research design outlines how to approach a
problem, while research methodology explains how 5
 Cont’d…
 We may split the overall research design into:
 Sampling Design - deals with the method of selecting items to be
observed for the given study.
 Statistical Design - concerns with the question of how many
items are to be observed and how the information and data
gathered are to be analysed (sample size and type of sampling);
 Observational Design - relates to the conditions under which the
observations are to be made
 Operational Design - deals with the techniques by which the
procedures specified in the sampling, Statistical, and
observational designs can be carried out. 6
Important concepts in Research Design
• Variable: A concept that can take on different values.
Continuous variable:
• Can take on quantitatively different values even in
decimal points.
• A variable that can assume any numerical value within
a specific range. (e.g. Age, weight).
Discrete variable:
• Can only be expressed in integer values
• A variable for which the individual values fall on the
scale only with distinct gaps. (e.g. Number of children).

7
 Cont’d…
 Dependent variable:
• A consequence of another variable (effect).
– It depends on another variable
 Independent variable:
• presumed cause of the dependent variable
– It is antecedent to the dependent variable
Example
Behavioral changes: dependent variable
Films, lectures, …: independent variable
 Extraneous variables:
• independent variables that are not related to the purpose of the study
but may affect the dependent variable
• Those uncontrolled variables that may have a significant influence on
the dependent variable. 8
 Cont’d…
Research design can be:-
 Quantitative
 Qualitative

• 9
 Quantitative Research Design
• method of collecting and analyzing numerical data to
understand and predict the relationships between
variables:
 Goal: To understand, describe, and predict a phenomenon
by identifying patterns and relationships between
variables
 Methods: Use structured instruments to gather data
through surveys or experiments
 Analysis: Use statistical models to analyze the data and
identify patterns, trends, and relationships
 Results: Draw objective and reliable conclusions based on
the analysis
10
 Cont’d…
 Quantitative research design is characterized by:
• Objective stance: The research is based on logic and
numbers, and the researcher seeks objective answers to a
clearly defined question.
• Large sample sizes: The data is collected from a
representative sample of the population.
• Replication: The study can usually be repeated because it
is highly reliable.
• Careful design: All aspects of the study are carefully
designed before data collection.

11
 Cont’d…
 Some types of quantitative research design include:

• Descriptive: Establishes associations between variables,

usually by measuring subjects once.

• Experimental: Establishes causality by measuring subjects

before and after a treatment.

• Quasi-experiment: Attempts to establish a cause-and-

effect relationship.

12
Qualitative Research Design
• methods goes through participant observation, and in-
depth interviewing that yield descriptive data.
• Qualitative research notions:
– Are concerned with the meanings people attach to
things in their lives.
– Qualitative researches develop concepts, insights, and
understandings from patterns in the data rather than
collecting data to assess preconceived models,
hypotheses, or theories.
13
Cont’d…
• Qualitative research is concerned with how people think
and act in their everyday lives
– In qualitative interviewing, researchers model their
interviews after a normal conversation rather than a
formal question-and-answer exchange.
– For the qualitative researcher, there is something to be
learned in all settings and groups.

14
Cont’d…
• Research setting
– The ideal research setting is one in which the
observer obtains easy access
• Literature
– You can not be sure what literature might be
relevant to your study until you have
completed your research.

15
Quantitative Vs Qualitative Research Design

• Qualitative research design differs from

quantitative research design in the type of data
collected and analyzed, the research goals, and
the methods used.

16
Cont’d…
Characteristics Quantitative Qualitative
uses non-numerical
Data type uses numerical data. data like words,
images, and sounds,
aims to understand
aims to understand
the "why" and "how"
the "what" and "how
Research goals of human behavior
often" of human
behavior.

uses methods like

uses methods like
interviews,
Research methods surveys, experiments,
observations, and
and statistical models.
focus groups
17
Cont’d…
Characteristics Quantitative Qualitative
often uses a large often uses a small
Sample size
sample size. sample size
analyzes data by
analyzes data categorizing
Data analysis statistically to identify information to
patterns. understand themes
and insights
aims to produce
objective, empirical aims to produce
data that can be detailed descriptions
outcome
measured and and uncover new
expressed insights
numerically.
18
 Research Method and Methodology
• Research Method: describes the specific technique used in a given
study.
• Research Methodology
 A science of studying how research is done scientifically.
 A way to systematically solve the research problem by logically
adopting various steps.
 helps to understand not only the products of scientific inquiry
but the process itself.
 Aims to describe and analyze methods, throw light on their
limitations and resources.
19
Sampling Design
 Sampling: act, process, or technique of selecting a suitable sample
or representative part of a population for the purpose of
determining parameters or characteristics of the whole population.
 Population: entire group under study as defined by research
objectives
– Sometimes called the “universe.” or Reference population
• Researchers define populations in specific terms such as heads of
households, individual person types, families, types of retail
outlets, etc.
 Population, geographic location and time of study are also
considered. 20
21
Cont’d…
 Sample: subset of the population that should represent the entire
group.
• is “a smaller (but hopefully representative) collection of units from a
population used to determine truths about that population”.
 Sample unit: the basic level of investigation…consumers, store
managers, shelf-facings, adolescence, etc.
– The research objective should define the sample unit
 Sampling frame: the property that we can identify every single
element and include any in our sample
 the list from which the potential respondents are drawn
– Registrar’s office, Class rosters, Must assess sampling frame errors
 must be representative of the population
 Census: counting the complete population

22
Calculating sample frame error (SFE):
– Subtract the number of items on the sampling list from the
total number of items in the population
– Take this number and divide it by the total population.
Multiply this decimal by 100 to convert to percent (SFE
must be expressed in %)
– If the SFE was 40%, this would mean that 40% of the
population was not in the sampling frame
• Practical considerations (in sampling design):
– Cost and population size
– Nature & purpose of the study
– Inability of researcher to analyze large quantities of data
potentially generated by a census
• Samples can produce sound results if proper rules are
followed for the draw.
23
Why is sampling?
• Economy: Save resources (money, manpower…)
• Timeliness : Save time
• provides more timely data than a census
• Completeness and accuracy
–It is possible to collect more detailed information,
because more time can be spent in asking respondents.
• Destructiveness of the observation/study: When
Experiments are to result in the destruction of the
materials that undergo the experiment.
• When population size is very large
• Inaccessibility of some of the population: In cases of
inaccessible population
24
Cont’d…
three factors that influence sample
representativeness:-
• Sampling procedure
• Sample size
• Participation (response)
When might you sample the entire population?
• When your population is very small
• When you have extensive resources
• When you don’t expect a very high response

25
 Types of Sampling Methods/Designs
1. Probability Sampling
•every unit in the population has a chance (greater than
zero) of being selected in the sample, and this probability
can be accurately determined.
•When every element in the population has the same
probability of selection,  'equal probability of selection'
(EPS) design.
• also referred to as 'self-weighting' because all
sampled units are given the same weight.
•Each members of the population have a known chance
(probability) of being selected.
– Each unit of population will be represented in the sample.
26
Probability sampling includes:
1. Simple random sampling
2. Systematic sampling
3. Stratified sampling
4. Proportional stratified sampling
5. Cluster Sampling

27
1. Simple random sampling
– each element of the population has an equal, known and
independent chance of being included in the sample.
– The least sophisticated of all sampling designs.

– Applicable when population is small, homogeneous & readily

available/known
– Impractical for very large populations

– A table of random number or lottery system is used to

determine which units are to be selected.

28
1. Simple random sampling….
• all subsets of the frame are given an equal
probability.
– Each element of the frame thus has an equal
probability of selection
• done by assigning a number to each unit in the
sampling frame
Some of examples are
Lottery Method
Throwing a dice/cube
Tossing a coin
29
2. Systematic sampling:
– Relies on arranging the target population
according to some ordering scheme and then
selecting elements at regular intervals through
that ordered list
– more efficient than simple random sampling
– Selecting elements of the population in
predetermined sequence.

30
2. Systematic sampling….
• Randomness element is in picking up the starting
point.
– Involves a random start and then proceeds with
the selection of every kth element from then
onwards.
– In this case, k=(population size/sample size).

 Example: to select every 10th name from the telephone

directory ('every 10th' sample, also referred to as 'sampling
with a skip of 10').
31
 3. Stratified random sampling
• divides a population into homogeneous groups based on specific
traits, like race, gender, or socioeconomic status.
• Then, some units are randomly selected from each group to ensure
that the sample represents all groups.
• It is used to improve precision and representation.
• Where the population embraces several distinct categories, the
frame can be organized into separate "strata."
– Each stratum is then sampled as an independent sub-population,
out of which individual elements can be randomly selected.
• Every unit in a stratum has the same chance of being selected
• Applied when the population has different layers (strata).
32
 Stratified random
sampling….
• The researcher take samples from each one of the layers
(stratum) equally.
– Examples
• Sampling of school children from grades 4, 5 and 6
• Sampling of customers (customer frame)
– Corporate customers
– Residential customers, etc.…
• Since each stratum is treated as an independent population,
different sampling approaches can be applied to different
strata.

33
 4. Proportional stratified sampling
• ensures a sample accurately reflects the population by
selecting a proportional number of items from each stratum.
• often used to estimate population parameters.
• preferable when number of the elements of the strata are
different in size
• 2,000 corporate customers
• 400,000 residential customers
• Adequate representation of minority subgroups of interest can
be ensured by stratification and varying the sampling fraction
between strata as required.

34
5. Cluster sampling
• Divides a population into heterogeneous groups, often based
on geography.
• all units are randomly selected from entire groups.
• used to improve cost-effectiveness and operational
efficiency.
• Once clusters are established, a random draw is done to select one
(or more) clusters to represent the population
• Sampling units are groups rather than individuals.
• A sample of such clusters is then selected.
• All units from the selected clusters are studied.

35
Cluster sampling….
– Grouping the population into clusters and then
select members of clusters.

Population Random selection

of clusters

C1 C2 C3 C4 C5

C5 C6 C7 C8 C8
C9 C10 C11 C12 C11

36
Two types of cluster sampling methods.
[Link]-stage sampling
• All of the elements within selected clusters are
included in the sample.

2. Two-stage sampling
• A subset of elements within selected clusters are
randomly selected for inclusion in the sample.
37
Strata Vs. Clusters
• Although strata and clusters are both non-overlapping
subsets of the population, they differ in several ways.
– All strata are represented in the sample; but only a subset
of clusters are in the sample.
– With stratified sampling, the best survey results occur
when elements within strata are internally homogeneous.
– However, with cluster sampling, the best results occur
when elements within clusters are internally
heterogeneous.
38
 Stratified Vs Cluster Sampling
Characteristics Stratified sampling Cluster sampling
Group homogeneous (units heterogeneous (individual
homogeneity share characteristics). characteristics vary).

Group Selection some units are all units are selected from
selected from all randomly selected groups.
groups.

Research goals used to improve used to improve cost-

precision and effectiveness and
representation. operational efficiency 39
Summary
Population characteristics Appropriate sampling technique

•Simple random sampling

1. Homogeneous members
•Systematic random sampling

2. Stratified population with

Stratified random sampling
approximately equal in size

3. Stratified population, strata

Proportional stratified sampling
different in size

4. Population with discrete clusters

Cluster sampling
with similar characteristics
Cont’d…
2. Non-probability Sampling
•Instances in which the chances (probability) of selecting
members from the population are unknown
– The researcher has no way of forecasting that each
member of the population will be represented in the
sample.
– Some member of the population have little or no
chance of being selected.
•Any sampling method where some elements of population
have no chance of selection referred to as 'out of
coverage'/'under covered'), or where the probability of
selection can't be accurately determined
41
Non-probability sampling includes:
1. Convenience sampling
2. Judgment or purposive sampling
3. Quota sampling

42
1. Convenience sampling:
– Sometimes known as grab or opportunity sampling or
accidental or haphazard sampling.
– involves the sample being drawn from that part of the
population that is close to hand.
– readily available and convenient.
 Taking People/samples who are available, volunteer, or can
be easily recruited.
E.g. those who arrive on a scene by coincidence
– Appropriate for some less demanding research.
– Use results that are easy to get
43
 Convenience sampling…
• The researcher cannot scientifically make generalizations
about the total population from this sample because it
would not be representative enough.

• Example: if the interviewer were to conduct a survey at a shopping

center early in the morning on a given day, the people that he/she
could interview would be limited to those given there at that given
time, which would not represent the views of other members of
society in such an area, if the survey was to be conducted at different
times of day and several times per week.

44
2. Judgment/purposive sampling:
• choose based on who they think would be appropriate for the study.
• used primarily when there is a limited number of people who have
expertise in the area being researched.
• involves selecting a group/individuals from the population based on
available information thought.
• Samples require a judgment or an “educated guess” on the part of
the interviewer.
• Also, “judges” (informed individuals) may be asked to suggest who
should be in the sample.
• A technique to pick out the sample in relation to some criterion that
are considered important for the particular study.
• Units of the sample are chosen purposively.
• Choosing people whom we have decided are “typical” of a group;

45
3. Quota sampling
– A variation of convenience sampling
– Elements are selected in the same proportion as in the
population.
• Example: There is an equal number of IT and SE students.
– 20 IT and 20 SE students can e chosen using Quota
sampling without any attempt to random selection.
 Size of Sample
• Size of the sample depends upon the precision the researcher
desires in estimating the population parameter at a particular
confidence level.
• There is no single rule that can be used to determine sample size.
• The best answer to the question of size is to use as large a
sample as possible.
• A larger sample is much more likely to be representative of the
population.

47
 Size of Sample …
• with a large sample, the data are likely to be more
accurate (value) and precise (sample error).
• It was pointed out in that:
 the larger the sample, the smaller the standard error (high
precision).
 the larger the sample, the higher the representative (high
accuracy)

48
 Steps in the sampling process
1. Identify the population: Define the target population
2. Specify a sampling frame: Create a list of the people or items that
make up the population
3. Specify sampling method: Choose a method for selecting the
sample (random sampling, stratified sampling, cluster sampling, or
systematic sampling)
4. Determine the sample size: Decide on the number of items to
include in the sample
5. Implement the plan: Collect the sample data.
 It's important to choose the right sample size.
 A sample that's too small may not accurately represent the
population, while a sample that's too large may be impractical.

49
 Data collection Techniques/Tools
• Applying the chosen method (s).

• The means to collect data for analysis.

• a number of different data collection tools available and

one should be selected which is most likely to meet the
objective of the research and gather the correct type of
information for your study.

50
Cont’d…..
• Each technique is designed to get certain types of
information and not others.
• Viable methods/tools should be weighed up in terms of
their advantages and disadvantages.
• Some of the data collection techniques/tools are
Observation
Questionnaires
Interviews
Document analysis

51
Observation
• the process of observing and recording events or
situations.
• Particularly useful for discovering how individuals or
groups of people or animals (and in some instances
inanimate objects) behave, act or react.
• two main types of observation:
1. Participant
2. Non-participant

52
 Cont’d…..
• Participant observation: researcher becomes part of the group
studied and participates in their daily life and activities:
– Observing their everyday situations and their behavior in these
situations.
– usually limited to studies of human subjects.
• non-participant observation: researchers simply observe the
activities without taking part themselves.
– Has the advantage of preventing the researcher from unduly
influencing or becoming involved in activities they may not wish
to take part in (for example dangerous or criminal actions)
– But they are less likely to understand fully the meanings behind
behavior in the group studied.
– Besides the study of human subjects, non-participant
observation can also be used to study animal behavior.
53
Advantages and disadvantages of observation
Advantages Disadvantages
Requires little training or familiarization. Time consuming.
Can understand meanings behind Problems with recording data.
actions.
Behavior can be observed in its natural Can only study a small group.
environment, the subject is
undisturbed.
Can study deviant groups. Cannot make generalizations - no
way of judging whether the group is
typical.
Flexibility - researcher may come across If secret is it ethical?
conditions and events previously
not comprehended.
Moral, legal and injury risks associated
with this method.
54
 Questionnaires
• A type of survey where respondents write answers to
questions posed by the researcher on a question form.
• extremely flexible and can be used to gather information
on almost any topic involving large or small numbers of
people.
• two approaches of questionnaires:
1. Close-ended questionnaire
2. Open-ended questionnaire

55
Cont’d…..
• Close-ended questionnaire: the respondents are required to
answer by choosing an option from a number of given answers
– Usually by ticking a box or circling an answer.

• They only gather straightforward, uncomplicated information,

and only simple questions can be asked.
• Open-ended questionnaire: allows the respondent to formulate
and record their answers in their own words.
– Are more qualitative and can produce detailed answers to
complex problems.
56
 Advantage and disadvantages of questioners:
Advantages Disadvantages
Quick Limited answers only can be given.
Cheap Lack of qualitative depth results in superficiality.
Efficient No way of probing/searching for more
information in
superficial responses.
Can reach a large number of Not always accurate - not possible to verify
people. what appears to be an inaccurate answer and
little check on honesty of responses. Questions
may mean different things to different people.
Consistent format means there is Predetermined boxes may not be appropriate.
little scope for bias introduced by
different researchers.
Low response rate.
Construction difficult - instructions must be
clear and unambiguous and questions carefully
ordered. 57
 Interviews
• limited to cases where the subjects of study are
humans.
• type of survey where questions are delivered in a
face-to-face encounter by an interviewer.

58
 Advantages and disadvantages of Interview
Advantages Disadvantages
High response rate. Limited sample only.

Can collect complex Can be difficult to analyze (especially

information. in-depth interviews).

High degree of researcher May be a hostile reaction.

control achieved.

Can be made more responsive Whole process is time consuming.

to early results.

Relaxed environment. Recording techniques may cause

59
problems.
 Document Analysis
• the process of using any kind of document, films, television programs
and photographs as well as written sources (books, papers and letters)
for analysis in relation to a particular research question.
• also referred to as content analysis, differs from the majority of
research methods in two major ways.
– indirect form of research; it is something that has been produced,
so the investigator is not generating original data.
– 'unobtrusive', or 'non-reactive' method. This refers to the fact that
the document will not be affected in any way by your research; it
cannot react as a human can.

60
 Advantages and Disadvantages of Document Analysis
Advantages Disadvantages
The data never alters and Subject to bias and subjectivity - impossible
can be subject to reanalysis. to allow for biases introduced by the fact
that the document studied has been written
for a particular purpose and is the author's
own particular account; events may be
sensationalized, subject to political bias etc.

Unobtrusive/triangulation Evidence may be out of date.

Events can be compared over time May not be accurately recorded.
and cultures.
Gives an expert understanding. Documents available may be limited.

Cheap. Can be laborious and time-consuming.

Computers can aid analysis and lead
to complete reliability in applying the
rules you set down for coding the
text. 61
The end

62