Hawassa University
Hawassa Institute of Technology
Department of Electrical &
Computer Engineering
Research Methods and Presentation
Chapter Four: Process in
Conducting Research
4. Process in Conducting
Research
There are a number of stages in the research
process, although their number and description
tends to vary between authors/disciplines.
One simplified view would see these as five stages
which include:
conceptualization,
contextualization,
data collection and/or generation,
data analysis and
reporting conclusions
2
Cont’…
Conceptualization includes:
Defining the 'problem';
establishing the research questions;
identifying the aims;
specifying the testable hypotheses; deciding on the
research approach;
identifying the most appropriate way of undertaking the
data collection and/or generation.
This stage is the most difficult one for
novice/beginner researchers.
Linking the problem and objective/aim of the
research with appropriate data collection method
often requires careful thinking and advice from
3
senior researchers.
Cont’…
Contextualization includes:
Putting the research in the context of similar
research that has been done in the past.
If there is similar research which was done
elsewhere, looking carefully the methodology used
and the way data collected and the limitation of
the work may help.
4
Cont’…
Data Collection/Research Design method:
You need to operationalise the research problem by
choosing the most suitable research method for your
specific study.
There are different research data collection methods
available one should be selected which is most likely
to meet gather the correct type of information.
Below follows a list of individual data collection
research methods (observation studies, questionnaires,
interviews, focus groups, document analysis,
experimental research, and mathematical
modelling)
incorporating a brief description, advantages &
disadvantages, ways of collecting data, general hints
for carrying out the research & some examples of their5
Sampling in Data Collection
Sampling is the process of selecting a subset of individuals or items (a
sample) from a larger group (a population) to estimate characteristics
of the whole population.
It's crucial when studying large groups is impractical or impossible.
There are two primary categories:
1. Probability Sampling(Quantitative Data), where each member
has a known chance of being selected (e.g., simple random, stratified,
cluster, systematic)
2. Non-probability sampling(Qualitative Data), where selection isn't
random and relies on convenience or judgment (e.g., convenience,
quota, snowball, purposive).
The choice of sampling method depends on the research objectives,
available resources, and desired level of accuracy and
6
generalizability.
Probabilistic Sampling
Probability sampling is a cornerstone of robust research,
as it guarantees that every individual or element within
the target population has a known, non-zero chance of
being selected for the sample.
1. Simple Random Sampling (SRS)
offers a baseline approach where every individual has an
equal chance of selection
2. Stratified Sampling
divides the population into homogeneous subgroups (strata)
before random sampling occurs within each stratum,
improving precision when dealing with diverse populations7
Cont…
3. Cluster Sampling
involves randomly selecting entire groups (clusters)
and including all members within those clusters, often
used when the population is geographically dispersed.
4. Systematic Sampling
selects every kth member from a list after a random
starting point, providing a simpler alternative to SRS.
The optimal choice depends on factors like population
heterogeneity, geographical distribution, and available
resources, aiming to balance accuracy with feasibility.
8
Non-Probabilistic Sampling
Non-Probability Sampling: Selection isn't random.
1. Convenience Sampling: Easiest access.
2. Quota Sampling: Pre-defined groups (strata), non-random
selection within those groups until quotas are met.
3. Snowball Sampling: Participants refer other participants. Think
chain reaction or networking. Useful for hidden/hard-to-reach
populations.
4. Purposive Sampling (Judgmental Sampling): Researcher uses
their judgment to select specific participants who fit the study's
9
purpose.
a. Mathematical Modelling
Mathematical modelling can be used to analyze
relationships between different variables and to predict
possible outcomes, or causal effects.
Experiments can be designed from models of systems,
which aim to define links between variables and
outcomes.
10
b. The experimental method
It involves setting up an experiment in order to
test a particular theory or hypothesis.
It is concerned with seeing what changes occur if
something new is tried out and with the effects of
these changes on something else.
General tips for carrying out experiments:
Careful preparation is essential and
experienced researchers should be consulted
before experimentation begins.
Project design, sample selection and
measurement of dependent variables are
crucial to the success of the research.
11
Cont’...
Different research designs/methods have different attributes.
The design is the structure of any scientific work. It gives
direction and systematizes the research.
The method you choose will affect your results and how you
conclude the findings. 12
Data Analysis:
Method to collect data and the following data
analysis technique should match;
occasionally problem may emerge as one
start to do data analysis.
Reporting Conclusions: Writing up and / or
further dissemination.
13