DISCUSSION ON THE

FOUR RESEARCH DESIGN

TYPES USED IN THE
SOCIAL SCIENCES.

By
Bryan Kauma
BEFORE EXAMINING TYPES OF RESEARCH DESIGNS, IT IS IMPORTANT TO BE
CLEAR ABOUT THE ROLE AND PURPOSE OF RESEARCH DESIGN. WE NEED TO
UNDERSTAND WHAT RESEARCH DESIGN IS AND WHAT IT IS NOT. WE NEED
TO KNOW WHERE DESIGN FITS INTO THE WHOLE RESEARCH PROCESS FROM
FRAMING A QUESTION TO FINALLY ANALYZING AND REPORTING DATA.
DESCRIPTIVE RESEARCH (WHAT IS GOING
ON?)
Although some people dismiss descriptive EXPLANATORY RESEARCH (WHY
research as `mere description', good description QUESTIONS)
is fundamental to the research enterprise and it For example, it is one thing to describe the
has added immeasurably to our knowledge of
crime rate in a country, to examine trends
the shape and nature of our society.
over time or to compare the rates in different
Descriptive research encompasses much countries. It is quite a different thing to
government sponsored research including the
develop explanations about why the crime
population census, the collection of a wide range
rate is as high as it is, why some types of
of social indicators and economic information
crime are increasing or why the rate is
such as household
higher in some countries than in others.
expenditure patterns, time use studies,
employment and crime statistics and the like. Answering the `why' questions involves
Descriptions can be concrete or abstract. A developing causal explanations. Causal
relatively concrete description might describe explanations argue that phenomenon Y (e.g.
the ethnic mix of a community, the changing age income level) is affected by factor X (e.g.
profile of a population or the gender mix of a gender). Some causal explanations will be
workplace. simple while others will be more complex.
Alternatively For example, we might argue that there is a
the description might ask more abstract direct effect of gender on income
questions such as `Is the level of social
inequality increasing or declining?' How secular
is society?' or `How much poverty is there in this
community?'
 WH AT IS R ESEA RCH DE SIGN
A research design is a set of logical procedures that (when followed) enables
one to obtain evidence to determine the degree to which a theoretical
hypothesis (or set of hypotheses) is/are correct.
To come up with a good research output, a good research design is needed.

Without a good research design, the researcher will find himself flooded
with information which may not be appropriate in meeting his objectives.
Choosing the correct research design will enable the researcher to gain a

better understanding of social phenomena. Thus, familiarity with these

different research designs is a requisite for a well-guided research study.
Social research is aimed towards an understanding of social phenomena.

Applying the appropriate research design in gathering the required data

about people and their behavior is essential in understanding the
complexities of human behavior.
Social research uses both quantitative and qualitative approaches; the

former approach focuses on quantifying evidence and usually applies

statistics in analyzing the data gathered to reveal generalities while the
latter aims to achieve understanding through subjective analysis of subjects
and emphasizes the context by which things happen.
 TYPES OF RESEARCH DESIGNS
Experimental

Case Study

Longitudinal Design

Cross Sectional Design

 EXPERIMENT DESIGN
An experiment is a research design where a certain degree of control over a given
set of variables is exercised by the researcher when conducting an investigation.
Experiments are used to test new hypothesis or existing theories with the end in

view of confirming or refuting them.

The experiment starts off with a problem statement, a hypothesis is formulated,

then an experiment is carried out to find out if the hypothesis is correct or not.
The results are analyzed using statistics that form the basis in coming up with a

conclusion. When many experiments have already been done getting the same
results, a theory may be formed which are then conveyed through publication of
findings.
For example, an experiment is carried out to find out which amount of a toxin will

cause symptoms to experimental animals referred to generally as guinea pigs.

Experimentation need not be done only in laboratories.
SeedCo/ Pannar testing new hybrid seed in areas with different climatic and soil

conditions.
In social studies it is difficult to use this design because it involves the use of

people, and may have hazardous implications, albeit drug companies for example
DatLabs/ CAPS may administer a trail drug test on different people to find out
weather a drug is suitable for public use.
PREDOMINATELY USED BY
Advantages Disadvantages

Largely Subject To Human Errors

Just like anything, errors
can occur. This is especially
A High Level Of Control
true when it comes to

With experimental research groups, the

people conducting the research have a very research and experiments.
high level of control over their variables. By Any form of error, whether a
isolating and determining what they are
looking for, they have a great advantage in systematic (error with the
finding accurate results. experiment) or random error
Can Span Across Nearly All Fields Of (uncontrolled or
Research
It is a basic, but efficient type of research
unpredictable), or human
design and is very academically flexible and errors such as revealing who
can be used in many different types of the control group is, they
situations. Just as pharmaceutical
companies may utilize it, so can teachers who can all completely destroy
want to test a new method of teaching. the validity of the
experiment.
PREDOMINATELY USED IN MEDICAL SECTOR WITH ANIMALS
ETC.
Advantages
Clear Cut Conclusions
Since there is such a high level of control,
and only one specific variable is being tested
at a time, the results are much more relevant
than some other forms of research. You can
clearly see the success, failure, of effects
when analyzing the data collected.
Many Variations Can Be Utilized
The investigator has the ability to tailor
make the experiment for their own unique
situation, while still remaining in the
validity of the experimental research design.
Disadvantages
Can Create Artificial Situations
By having such deep control over the
variables being tested, it is very possible that
the data can be skewed or corrupted to fit
whatever outcome the researcher needs.
This is especially true if it is being done for a
business or market study. (The case of
harmful drugs hitting the market)
Can Take An Extensive Amount of Time To
Do Full Research
With experimental testing individual
experiments have to be done in order to fully
research each variable. This can cause the
testing to take a very long amount of time
and use a large amount of resources and
finances. These costs could transfer onto the
company, which could inflate costs for
consumers.
 CASE STUDY
Focuses on a single case rather than dealing with a sample of a large population. For example, a careful
determination of the factors that led to the success or failure of a community project may be conducted.
According to T. Babbie* : the in-depth examination of the single instance of some social phenomenon,

such as a village, a family, or a juvenile gang.

Yin** : Is an empirical inquiry that investigates a contemporary phenomenon within its real-life

context, especially when the boundaries between phenomenon and context are not clearly evident.
Copes with the technically distinctive situation in which there will be many more variables of interest

than data points. As a consequence, it relies on multiple sources of evidence, with data needing to
converge in a triangulating fashion. And thus, it benefits from the prior development of theoretical
propositions to guide data collection and analysis.
Are most useful for descriptive/exploratory research. E.g. field research. From your field notes (or other

type of data) you can examine the logic of change over time and compare the results of your study with
others described in the literature.
It brings out the unique aspects of the area of study. A community may be rural, (a non-unique factor)

but the means and trends of livelihood patterns differ from other rural communities. For example,
Masvingo and Binga are both rural tourism communities, but a case study approach will reveal that in
the latter fishing is a main mode of livelihoods as compared to tourism that dominates on the former.
A study to access the success and failures of an implemented project/ policy in a nation. Projects have

differential impacts according to community and setting, therefore in an effort to analyze the feasibility
of the program as a whole from an abstract stand point, before placing it in comparison vis--vis other
regions, a case study approach is ideal. For example, a study on the impact of the Information
Communication Technology Policy in Zimbabwe from 2010-15, using a case study approach, will allow
for an depth inquiry focusing on an independent region/community using a reasonable sample size and
access the impact of the policy and will allow for hidden nuances to be unearthed.
Offer validity because of the naturalness of the research setting. Generalizations to other groups is

difficultand this a notable strength.

 ADVANTAGES
Good source of ideas about behavior
Good opportunity for innovation

Good method to study rare phenomena

Good method to challenge theoretical

assumptions
Good alternative or complement to the group
focus of psychology
 DISADVANTAGES
Hard to draw definite cause-effect conclusions
Hard to generalize from a single case (often need
two or more case studies for comparative analysis
sake)
Possible biases in data collection and
interpretation (since single person gathers and
analyzes the information)

Often used by Historians and humanity studies

analysts.
 LONGITUDINAL RESEARCH
DESIGN
Involves studies, with multiple observations are made over time, for example
survey research.
These types of researches are carried out mainly by Non-governmental

organizations with long term goals for example eradicating poverty in Africa e.g.
in Zimbabwe the World Vision Amalima Project. A baseline survey conducted to
understand agricultural trends and habits in Zimbabwe, before the second phase
of introduction of sustainable livelihoods is introduced based on the outcomes of
the baseline.
Because baseline results will have a huge impetus on the permanent culture of

the region/area, continuous surveys are conducted prior to implementation of a

anticipated program for example, in Bulilima -Mangwe District, the construction
of the Sanzuku Dam took close to 5 years of prior baseline surveying because
seasonal trends had to be studied and captured to value feasibility of the project.
Furthermore, prospects of growth and development of other economic enterprises
that could complete or compliment the presence of the dam had to be placed into
consideration in line with political and economic legislation and policies.
Mass Public Opinion Institute caries out opinion surveys to determine public

opinions on socio-economic and political matters in Zimbabwe e.g. the annual

Perceptions on Citizens in Socio-Economic and Political Issues Survey carried out
across Zimbabwe every July.
 This is subdivided into three types namely:
Trend study
Cohort study
Panel study
 TREND STUDY
Study that looks into the dynamics of a particular
characteristic of the population over time for example, a
researcher might want to study the peoples preference for
projects, whether government or non-government, in their
community.
Respondents of the study vary across study periods.

This study is essential in understanding how infrastructure is

often abandoned upon completion by a community, or is

converted for alternative use for example, the Machipisa Long
Distance Bus Terminus. Respondents in 1999 argued the need
for a bus terminus to service long distance transport routes.
However, a separate study in the same region revealed that
the community would rather have had a local route taxi rank
accompanied with a local market stalls in the same area.
Consequently, the area has been redesigned to suite the latter.
 COHORT STUDY
A cohort study is a type of longitudinal research
design where a cohort is tracked over extended
periods of time.
It examines more specific subpopulations (cohorts)

as they change over time.

A cohort is a group of individuals who have shared a

particular time together during a particular time

span, for example, a group of indigenous peoples
living in the forest for decades.
Largely used in historical studies for example, the

study of the Tshwao minority ethnic group of

Tsholotsho by the University of Zimbabwe African
Languages Research Institute.
 PANEL STUDY
Involves collection of data from a panel, or the same set of people over several points in time
by measuring specific dependent variables identified by the researcher to achieve a study
objective.
Panel studies are similar to trend and cohort studies except that the same set of people is
studied each time.
From the data gathered, it is possible to predict cause-effect relationship after a given time.

Are usually done when it is difficult to analyze a case-study which is only a one-shotdeal.

Peoples shifting attitudes and behavior can be detected for example, cause-effect

relationship may be investigated between the number of faculty research outputs and the
amount of time given for research as work load over three years.
Uses same variables over a period of time.

Used to determine success or failure patterns, identifying gaps and strengths with project
over time.
In 2012, Catholic Relief Services Zimbabwe and Dabane Trust conducted a Water and

Sanitation Hygiene survey in Bulawayos 3 urban wards to assess the methods used by local
women and girls when disposing of sanitary pads. Environmentally friendly methods where
introduced and taught and studies where carried out to assess the rate of adoption by the
community analyzing the environmental and socio-economic impact of the use of the new
methods.
In 2009 January, Zimstat assessed primary schools in Harare, Bulawayo and Gweru to

determine relevance of the ZIMSEC examination syllabus with regards to preparing

students for eventual tertiary institution curriculum.
 CROSS-SECTIONAL RESEARCH
DESIGN
Is the most common research design used by social scientists. It gathers
data from a cross-section of a population.
Is based on observations made at one point in time for example survey

research, secondary literature or oral traditional trends.

Usually such studies are done for exploratory and descriptive research,

but sometimes also for explanatory studies.

In particular, when the data collection strategy is broader in scope

(involves considerably more than one case or a small group) and involves
systematic data collection we use the term cross sectional instead of
case study to describe it.
For example, a contingent valuation study asks a sample of a population

regarding their willingness-to- have pre-paid water or ZESA meters in

their residential homes. Bulawayo Agenda carried out one such study
with a result that most urban dwellers are against the idea of
installation of prepaid water meters, but welcome ZESA prepaid meters.
This study depending of the questionnaire used, too can reveal factors

for outcomes e.g. ZESA prepaid meters were welcomed because public
opinion was that ZESA was extorting clients under the old fixed meter
system.
 Advantages Disadvantages

Difficult to determine historical

Less time-consuming than case-control or
cohort studies
Inexpensive
Good, quick picture of prevalence of exposure
and prevalence of outcome
relationship between exposure
and outcome (lacks time element)
May have excess prevalence from
long duration cases (such as cases
that last longer than usual but
may not be serious)
VARIATIONS AMONG THE STUDY DESIGNS

Panel studies give a more complete picture of how

individuals change over time.
Cohort and Trend studies uncover only net changes

for example public opinion studies.

Longitudinal studies have an obvious advantage

over cross-sectional ones in providing information

describing processes over time.
But often this advantage comes at heavy cost in both

time and money especially in large scale surveys.

Panel studies are the best type of longitudinal

design to study cause and effect. (Explanatory

studies.)
Click icon to add picture

Ngiyabonga

Tatenda