Content uploaded by Indu Pankajakshan Vijayanthi
Author content
All content in this area was uploaded by Indu Pankajakshan Vijayanthi on Mar 24, 2020
Content may be subject to copyright.
64
Kerala Journal of Psychiatry // 32(1) Jan – Jun 2019
Column: Research Methods in Psychiatry
RESEARCH DESIGNS—AN OVERVIEW
Pankajakshan Vijayanthi Indu1, K Vidhukumar 2*
1Additional Professor in Psychiatry, Government Medical College, Kozhikode
2 Additional Professor in Psychiatry, Government Medical College, Thiruvananthapuram
* Corresponding Address: kumarv68@gmail.com
Submitted online: 24/12/2019 Published online: 3/1/2020
ABSTRACT
A research design is a systematic plan to study a scientific problem. The research problem determines
the type of design. Research designs can be qualitative or quantitative; the latter can be experimental
(interventional) and non-experimental (observational). Observational studies are further classified
into descriptive (such as case reports, case series and cross-sectional studies) and analytical studies
(like case-control and cohort studies). Experimental studies compare experimental groups exposed
to different treatments or interventions. All these are briefly discussed along with systematic reviews,
meta-analysis, qualitative research, basic sciences research, translational and implementation
research.
Keywords: design, research, qualitative, quantitative, translational, implementation
A research design is a systematic plan to study
a scientific problem. It is intended to provide
an appropriate framework for a study. The
choice of research design is very significant in
the process of designing research since it
determines how relevant information for a
study can be obtained.1 The research design
refers to the overall strategy that is chosen to
integrate the different components of a study
in a coherent and logical manner to ensure that
the research problem is addressed effectively.
It constitutes the blueprint for the collection,
measurement and analysis of data. The
research problem determines the type of
design and not the other way round. Research
designs can be qualitative or quantitative.
While qualitative research is primarily
exploratory research, used to gain an
understanding of underlying reasons, opinions
and motivations, quantitative research is used
to quantify the problem by generating data
that could be analysed statistically.
Quantitative Research Designs
In epidemiologic research, the basic
quantitative design strategies can be broadly
categorized into experimental (interventional)
and non-experimental (observational) studies.
Based on whether the studies focus on
describing the distribution of disease or
elucidating its determinants, the observational
studies can be further classified as descriptive
studies and analytical studies, respectively. See
Table.1 for the classification of quantitative
research designs. 2,3
Observational studies are those in which the
Please cite the article as: PV Indu, K Vidhukumar. Research designs—an overview (Column: Research Methods
in Psychiatry). Kerala Journal of Psychiatry 2019;32(1): 64-67.doi: 10.30834/KJP.32.1.2019.179
65
// www.kjponline.com
Table 1. Classification of quantitative research designs2,3
Research designs
Non-experimental studies/
Observational
Descriptive studies
Individual-based
Case reports
Case series
Cross-sectional surveys
Population-based
Ecological studies
Analytical studies
Cross-sectional studies
Case-control studies
Cohort studies
Experimental/ Interventional studies
Clinical trials
Field trials
Community intervention trials
the investigator is just observing the study
variables, not intervening or acting upon study
participants. The aim is to find the general
characteristics of the distribution of the disease
(the descriptive studies) or analyse the
relationship between factors and outcomes
(the analytical studies).
Descriptive studies
are primarily useful for the
development of hypotheses which can be
tested later by the analytical studies. They can
be population-based or individual-based.
Population-based studies include ecological
studies; while individual-based studies include
case reports, case series and cross-sectional
surveys.
Ecological studies
are observational studies in
which data is analyzed at the population level
rather than individual level. Health outcomes
studied are aggregates of individual health
data like prevalence, incidence or rate of
disease. The ecological risk or exposure data
could be aggregate measures like the
percentage of malnourished children,
environmental measures like mean annual
exposure to pesticides or global measures like
population density. 4
Case reports
are the most basic individual-
based, descriptive study design. A careful,
detailed report of the profile of a single patient
is provided by one or more clinicians. This can
also be expanded to a
case series
describing the
characteristics of a number of patients with a
given disease.
Cross-sectional surveys
assess the exposure
and outcome in the study participants at the
same point in time. They provide information
about the prevalence of outcomes or
exposures, but it cannot be distinguished
whether the exposure preceded the outcome or
the outcome affected the exposure.2
Analytical studies
involve an explicit
comparison of exposure and disease status.
There are two basic types of observational
analytical designs—case-control studies and
cohort studies. Either design can be used to test
a hypothesis. The association of exposure of
interest with the outcome is studied in both the
designs. The choice of design is based on the
characteristics of exposure and outcome, the
current status of knowledge and the resources
available like time and money.
Case-control studies:
In this, a group of
subjects with a disease and a control group,
without the disease, are chosen, and the
proportion of exposure of interest is compared
between the two groups.
66
Kerala Journal of Psychiatry // 32(1) Jan – Jun 2019
Cohort studies:
In this, subjects are classified
based on the presence or absence of exposure
to a particular factor and followed up for a
period of time to assess the incidence of the
outcome of interest in either group.
Experimental studies
are typical experiments
on human subjects in which experimental
groups are created that are exposed to different
treatments or agents. The investigator assigns
the exposure status of each participant. If each
subject is assigned treatment using a random
assignment mechanism like a coin toss, it is
called randomization. This strategy, on
average, controls for all the other, extraneous
factors, that could affect the outcome.
Experimental studies can be randomized or
non-randomized (quasi-experimental). They
can be clinical trials, field trials or community
intervention trials. Health economic
evaluation studies are generally piggybacked
on experimental studies.
Clinical trials
are conducted with patients as
subjects. The goal is to evaluate a potential
treatment or cure for a disease or to assess a
medication to prevent the sequelae of the
disease. In
field trials
, the subjects are not
defined by the presence of disease or the need
for clinical care. They are conducted on
subjects “on the field,” without the disease, to
evaluate whether an intervention (like
vaccination) reduces the risk of developing a
disease. In field trials, if treatment is assigned
randomly to a group of participants, it is said
to be a
cluster-randomized trial
.
Community
intervention trials
are an extension of the field
trial, in which intervention is assigned to the
whole community as a unit (like water
fluoridation).
Economic Evaluation
Health economic evaluation informs
policymakers, payers and others on how to
make the efficient allocation of resources
(which are obviously scarce) over competing
health care interventions. These analyses
answer the question of efficiency of allocation,
i.e., the opportunity cost (health gains when a
particular intervention is given up for the
alternative intervention). Economic
evaluation can be
partial
when it considers the
cost of an illness or cost comparison of
different interventions without considering
their health effects; while
full
economic
evaluation compares costs and effects of
competing alternatives.5
Systematic reviews and meta-analyses are at
the top of the pyramid in the hierarchy of
evidence. Systematic reviews attempt to
answer a specific research question by
collecting and combining empirical evidence
that meets pre-specified eligibility criteria.
The focus is on selecting the right articles for
the clinical question than the analysis per se.
Meta-analyses are a subset of systematic
reviews. It is a statistical procedure that
integrates the results of several independent
studies. It often results in valid conclusions
about a question from multiple studies, the
results of which may be conflicting. Usually,
randomized controlled studies are included in
the meta-analysis. But cohort and case-control
studies could also be used.6
Qualitative Research
The goal of qualitative research is to develop
concepts related to social phenomena in real
settings through the meanings, experiences
and views of all the participants. These
methods do not provide quantified answers to
research questions. Qualitative techniques
include participant observation, in-depth
interviews and focus group discussions.
Qualitative work can be conducted
67
// www.kjponline.com
preliminary to quantitative research and also
to supplement it as in ‘triangulation’. It is also
used to identify the terms and concepts to
develop questionnaires for quantitative
research.7
Scale development and validation (including
diagnostic test evaluation)
Scale development and validation involve
qualitative research and descriptive
epidemiologic methods. Still, the process is
unique, and it has its own methodology.8
Diagnostic test evaluation has certain
similarities to the process of development and
validation of the scale.
Now, let us have a peek into some of the
nascent and perennial research strategies
which provide insights into disease processes
and health care.
Basic Sciences Research includes a rigorous
enquiry at the molecular level relative to the
fundamental biology. (for example, how a
virus is produced, how the virus invades the
cell, how the cell responds etc.) It gives a
foundation for disease diagnosis, treatment
and prevention. Basic science research
provides insights only into the biological
processes as opposed to social, psychological,
environmental and care delivery issues. They
are usually done at the laboratory and not by
clinicians.
In translational research, either basic science
research is tapped to benefit patients in terms
of new diagnostic tests or treatments10 or
translation of results from clinical studies to
everyday clinical practice.9
Implementation research attempts to study
implementation strategies that support the
health services, programmes and policies.
They aim to understand what, why and how
interventions work in the “real world” settings
and to test approaches to improve them.11
REFERENCES
1. Jilcha Sileyew K. Research Design and
Methodology. In: Text Mining - Analysis,
Programming and Application [Working Title]
[Internet]. IntechOpen; 2019. Available from:
http://dx.doi.org/10.5772/intechopen.85731
2. Rothman KJ, Greenland S, Lash TL. Modern
epidemiology: Third edition. Philadelphia, PA:
Lippincott Williams & Wilkins. 2011
3. Hennekens CH, Buring JE, Mayrent SL.
Epidemiology in medicine. First edition. Boston:
Little, Brown. 1987
4. Levin KA. Study design VI – Ecological studies.
Evid Based Dent 2003;7:60-1.
5. Kuyten J, Naci H, Knapp M. Economic evaluation
of mental health interventions: an introduction to
cost-utility analysis. Evid Based Ment Health
2016;19(2):49-53.
6. Haidich AB. Meta-analysis in medical research.
Hippokratia 2010;14(Suppl 1):29–37.
7. Pope C, Mays N. Qualitative Research: Reaching
The parts other methods cannot reach: An
introduction to qualitative methods in health and
health services research. BMJ 1995; 311(6996):42–
45. doi:10.1136/bmj.311.6996.42
8. Boateng GO, Neilands TB, Frongillo EA, Melgar-
Quiñonez HR, Young SL. Best practices for
developing and validating scales for health, social,
and behavioral research: A primer. Front Public
Health 2018;6:149. Available from:
https://www.frontiersin.org/article/10.3389/fpu
bh.2018.001497.
9. Hudson MF. A primer of research strategies
undertaken in health centers. J Multidiscip Healthc
2013;6:93–8.
10.Machado-Vieira R. Tracking the impact of
translational research in psychiatry: state of the art
and perspectives. J Transl Med 2012;(10):175.
11. Peters DH, Adam T, Alonge O, Agyepong IA.
Implementation research: what it is and how to do
it. BMJ 2013;347:f6753.