Week
Research Methodology in IT
Semester I -2025
Lecturer : Dr. Mbemba HYDARA
1
Research Design &
Sampling
2
Re-cap on Exploratory Research
Extensive literature Review: Once the problem is formulated
Undertake extensive literature survey connected with the
problem
First consult Indexing journals using search online engines for
Academic journals articles, bibliographies, conference
proceedings, government reports, books etc., must be tapped.
Remember in this process, one source will lead to another,
A good library will be a great help to at this stage
3
3
Developing a Working Hypothesis
Here researcher should state clearly the
working hypothesis or hypotheses c. The role of the hypothesis is to
guide the researcher
a. A hypothesis is an assumption intended to
d. Delimiting the area of research
draw out and test its logical or empirical
and to keeping researcher on
outcomes
b. Hypothesis usually serve as the focal point right track.
for research. e. Indicates type of data required
c. Hypothesis should be very specific and
and methods of data analysis to
limited to the piece of research in hand to
be tested. be used.
4
Examples of Hypothesis
Scientific Hypothesis Social Hypothesis
1. If a plant has more sun 1.People who exercise
light, it will grow higher. regularly are happier than
2. Drinking coffee before those who don’t.
studying will improve 2.Increasing the minimum
memory retention. wage reduces poverty levels
5
Developing Working Hypotheses contd.
Discuss with colleagues and experts Review similar studies in the area
about the problem, its origin and the or other studies on similar
objectives in seeking a solution; problems; and
Examine data and records, Conduct an exploratory personal
concerning the problem for investigation. Include original field
possible trends, interviews on a limited scale.
peculiarities and other clues; • Purpose to have greater insight
into the practical aspects of the
problem.
6
Research Design
7
Why Research Design?
After research problem is formulated, Success of design depend on Research
researcher will be required to prepare a purpose which may be grouped into four
research design.
categories
Meaning to state the conceptual
(i) Exploration,
structure within which research would
be conducted. (ii) Description,
Design facilitates research to be (iii) Diagnosis, and
efficient yielding maximal (iv) Experimentation.
information.
8
Meaning of Research Design
• Research design refers to the overall strategy
a researcher follow to integrate different
elements of a study in a logical and coherent
manner.
• It outlines how data will be collected,
analyzed, and interpreted to ensure that the
research question is effectively addressed.
9
Need for Research Design
Well-structured research design is thus essential
because:
• It provides clarity on how the study will be
conducted.
• It helps minimize biases and errors.
• It ensures resources (time, money, effort) are used
efficiently.
• It guides researchers in obtaining reliable and valid
results.
10
Features of a Good Design
An effective research design should include:
Clarity and Precision:
• The objectives and methodology should be clear.
Flexibility:
• It should accommodate changes if necessary.
Validity and Reliability:
• The results must accurately reflect reality.
Ethical Considerations:
• It must adhere to ethical research principles.
Feasibility:
• It should be practical and manageable within
available resources.
11
Different Research Design Types
The different research designs types are:
Descriptive Research:
• Focuses on describing characteristics of a population or phenomenon.
Experimental Research:
• Examines cause-and-effect relationships through controlled
experiments.
Exploratory Research:
• Used when little information is available, helping to generate
hypotheses.
12
Different Research Design Types Contd.
Cross-Sectional Research:
• Studies different groups at a single point in time.
Longitudinal Research:
• Observes the same subjects over an extended period.
Case Study:
• Provides a detailed analysis of a specific entity or
situation.
13
Basic Principles of Experimental Design
When designing an experiment, researchers follow several key
principles:
Replication:
Repeating experiments to verify results.
Randomization:
Assigning subjects randomly to groups to reduce bias.
14
Basic Principles of Experimental Design
Control Groups: Comparing treated subjects with
untreated ones.
Blocking: Organizing subjects into similar groups to
control variability.
Factorial Design: Examining multiple variables
simultaneously.
15
Factors to consider in Research Design
Research design, appropriate for a particular research
problem, must consider:
means of obtaining the information;
availability and skills of the researcher
Explain the way and means of obtaining information
How it will be organized and justified
Duration of the research; and
Cost factor relating to research.
16
Sampling Design
17
Sampling Design
Sample design in research refers to:
• Sampling design refers to the framework
and method used to select the sample from
a population
• Researchers use sample designs to ensure
that the selected subset accurately
represents the larger group.
18
Steps in Sampling Design
Steps typically involved in designing a sampling process
include:
Define the Target Population:
• Clearly identify the entire group from which the sample will
be drawn. This ensures relevance and accuracy in results.
Determine the Sampling Frame:
• The sampling frame is the list or database of individuals or
units from the population that are accessible for selection.
Select the Sampling Method:
• Choose between probability and non-probability sampling
based on research objectives.
19
Steps in Sampling Design
Decide Sample Size:
• The number of observations needed for reliable
analysis, often determined using statistical formulas
and practical considerations.
Specify Sampling Procedure:
• Establish a systematic approach for selecting units,
including details like randomization, stratification, or
clustering.
Collect the Data:
• Implement the sampling process in a structured
manner, ensuring accuracy and minimizing bias.
20
Steps in Sampling Design
Assess Sampling Error and Bias:
• Analyze potential errors in selection and
ensure the sample represents the broader
population.
Finalize and Report:
• Ensure the sample is valid, process the data,
and report findings with confidence in
representativeness.
21
Determining Sample Design
All items under consideration in any field of inquiry constitute
a ‘universe’ or ‘population’
A complete enumeration of all the items in the ‘population’
is known as a census inquiry.
Assumption in the inquiry is that when all the items are
covered no element of chance is left and highest accuracy is
obtained.
This is difficult to achieve in practice and may not be true.
22
Sample Design Contd.
A sample design is a definite plan
Determined before any data sample is actually
collected from a given population.
Samples can be either probability samples or
non-probability samples.
23
Probability Samples
Probability samples:
Each element has a chance of being selected in the sample.
Random sampling, systematic sampling, stratified sampling, and
or cluster/area sampling
Non-probability samples:
Non-probability samples do not allow the researcher to determine
probability.
It is based on convenience sampling, judgement sampling and
or quota sampling techniques.
24
Important Sample Designs
Deliberate sampling: purposeful, or
convenience sampling
Simple random sampling:
Systematic sampling:
Stratified sampling:
Cluster sampling
25
Deliberate or Convenience Sampling,
Known as purposive or non-probability sampling
It involves purposive selection of particular units of the
population to constitute a sample
Sample selected based on ease of access is called convenience
sampling
Example: To secure data from gasoline buyers, you may select
a fixed number of petrol stations and conduct interviews at
these stations.
This procedure may also give very biased results
26
Simple Random Sampling
Is a known probability or chance sampling where each and
every item in the population has an equal chance of inclusion
in each one of the possible samples.
For example, to select a sample of 300 items from a universe
of 15,000 items, then we can put the names or numbers of all
the 15,000 items on slips of paper and conduct a lottery.
Procedure gives each item an equal probability of being
selected.
27
Systematic Sampling:
• Systematic sampling involves using random numbers
to pick up the unit with which to start.
• Example to select every 15th name on a list, every
10th house on one side of a street and so on.
• Useful when sampling frame is available in the form
of a list
28
Stratified Sampling:
• Use when population from which a sample is to be drawn does not
constitute a homogeneous group,
• The technique is applied so as to obtain a representative sample
• The population is stratified into a number of overlapping
subpopulations or strata and sample items are selected from each
stratum.
• First stratification and then simple random sampling is known as
stratified random sampling
29
Cluster Sampling
• Cluster sampling involves grouping the population and
• Selecting the groups or the clusters rather than individual elements for
inclusion in the sample
Example; some departmental store wishes to sample its credit card
holders. It has issued its cards to 15,000 customers. The sample size
is to be kept say 450. For cluster sampling this list of 15,000 card
holders could be formed into 100 clusters of 150 card holders each
• Three clusters might be selected for the sample randomly.
30
End of Lecture
31
