You are on page 1of 74

Research Study Designs

Dr.Asokan.G.V./PH/CHSS/UoB
Objectives
By the end of this lecture, you will be able to:
• Differentiate various types of research/study designs both
Quantitative and Qualitative.
• Comprehend the strengths and limitations of the study
designs.
• Diagnose confounding in research.
• Get sensitized to Systematic Reviews and Meta analysis.

Dr.Asokan.G.V./PH/CHSS/UoB
What is a Research Study Design?

• To derive a valid and meaningful scientific conclusion using


appropriate statistical methods that can be translated to the
“real world” setting.

Before choosing a study design, one must establish:

• Aims, Hypotheses, Objectives and Research Questions of


the study
• Choose an appropriate target population

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Quantitative

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Case reports and Case Series

• A descriptive study of one (case study or case report) or a series of patients (case series)
defined by eligibility criteria, and where the unfolding course of events (disease
progression, therapies, outcomes, etc.) is described in detail.

• No manipulation of interventions.

• Provides a detailed description of an uncommon disease or condition, a unique situation,


or the introduction of a new technique.

• Leads to further exploration.

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Case reports and Case Series

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Ecologic Study:

• Provides a description of population group characteristics, describes characteristics to


a group but individual characteristics are unknown .

E.g: Incidence of breast cancer and per capita intake of dietary fat and found a
correlation that higher per capita intake of dietary fat was associated with an increased
incidence of breast cancer.

Limitation: Does not conclude specifically which subjects with breast cancer had a
higher dietary intake of fat.

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Ecologic Study:

• Ecological (or correlational) studies are useful for generating hypotheses.

• Ecological studies can also be done by comparing populations in different places at the
same time or, in a time series, by comparing the same population in one place at different
times.

• An ecological fallacy or bias results if inappropriate conclusions are drawn on the basis
of ecological data.

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Ecologic Study:

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Cross Sectional Study:

• Where exposure factors (e.g., individual or environmental risk factor, nutrition


education) and outcomes (e.g., disease occurrence, eating behavior) are observed or
measured at one point in time in a sample, usually by survey or interview.

• Examines the association among factors and outcomes using a statistical test for
association, cannot infer cause and effect.

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Cross Sectional Study:

• Cross-sectional studies measure the prevalence of disease and thus are often called
prevalence studies.

• In a cross-sectional study the measurements of exposure and effect are made at the same
time.

• Easy and inexpensive.

• Helpful in assessing the health care needs of populations.

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Cross Sectional Study:

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Case-control Study:
• Involves identifying patients who have the outcome of interest (cases) and matching
them with individuals who have similar characteristics, but do not have the outcome of
interest (controls), and then looking back to see if these two groups differed regarding
the exposure of interest (i.e., the hypothesized causal or contributing factors).

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Case-control Study:

• Case-control studies are the most efficient design for rare diseases but are not an
efficient means for studying rare exposures and require a much smaller study sample
than cohort studies.
• Cannot measure incidence of the health outcome or disease.

• Most difficult task is to select controls so as to sample the exposure prevalence in the
population that generated the cases.
• Case-control studies use new (incident) cases to avoid the difficulty of separating factors
related to causation and survival (or recovery).

• Case-control studies may be subject to recall bias if exposure is measured by


interviews and if recall of exposure differs between cases and controls.

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Case-control Study:

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Case-control Study - Exercise

1. Researchers in Papua New Guinea compared the history of meat consumption in people
who had enteritis necroticans, with people who did not have the disease. Proportionately
more people who had the disease (50 of 61 cases) reported prior meat consumption than
those who were not affected (16 of 57).

2. Researchers conduct a case-control study of pancreatic cancer. The study included 200
cases and 200 controls. Of the cases, 80% reported they smoked cigarettes. Among the
controls, 50% reported they smoked cigarettes.

a) Prepare a 2x2 table with these data


b) Calculate the exposure odds ratio
c) Interpret the exposure odds ratio in a sentence

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs

Case-control Study:

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Cohort Study:

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Cohort Study:

• Involves the identification of a group (cohort) of individuals with specific characteristics


in common and follows them over time to gather data about exposure to factors and the
development of the outcome of interest.

• Comparison groups can be defined at the beginning or created later using data from the
study (e.g., age group, smokers/non-smokers, amount of a specific food group
consumed).

• Prospective cohort studies enrol individuals and then collect data at many intervals.

• Retrospective cohort studies use an existing longitudinal data set to look back for a
temporal relationship between exposure factors and outcome development. In the
medical field, many studies labelled a “population-based clinical study” could be
classified as retrospective cohort studies.
Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Cohort Study:

• Framingham Cardiovascular Disease Study (CVD) used baseline measurements to divide


the population into categories of CVD risk factors.

Advantages
• Subjects in cohorts can be matched, which limits the influence of confounding variables
• Efficient for Rare Exposures
• Multiple outcomes could be studied.

Disadvantages
• Cohorts can be difficult to identify due to confounding variables
• Requires Large Sample Size, Expensive and Time-Consuming.
• Outcome of interest could take time to occur

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Cohort Study:

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Cohort Study - Exercise

1. Researchers are conducting a prospective cohort study of the association between being
an office worker who uses a computer daily and carpal tunnel syndrome (a hand/ arm
nerve condition). A total of 300 exposed and 300 unexposed participants are enrolled
and followed for 10 years. A total of 25 exposed and 17 unexposed had the outcome of
interest over the follow-up period.

a) What is the risk of developing carpal tunnel syndrome among the exposed?
b) What is the risk of developing carpal tunnel syndrome among the unexposed?
c) What is the risk ratio and risk difference for developing carpal tunnel syndrome?

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Prospective Cohort Study:

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Retrospective Cohort Study:

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Case-control studies based within a defined Cohort Study:

• A defined cohort is embedded in a case-control study design.


• All the baseline information collected before the onset of disease like interviews, surveys,
blood or urine specimens, are used and the cohort is followed onset of disease.

Nested case-control study


• A nested case-control study consists of defining a cohort with suspected risk factors and
assigning a control within a cohort to the subject who develops the disease. Cases and
controls are identified and followed as per the investigator’s protocol.

Case-cohort Study
• It is similar to a nested case-control study except that there is a defined sub-cohort which
forms the groups of individuals without the disease (control), and the cases are not
matched on calendar time or length of follow-up with the control.

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Case-control studies based within a defined Cohort Study:

Nested case-control study

Dr.Asokan.G.V./PH/CHSS/UoB
Observational Study Designs
Case-control studies based within a defined Cohort Study:

Case-cohort study

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Randomized Controlled/Clinical Trial:

• Involve randomizing subjects with similar characteristics to two groups (or multiple
groups): the group that receives the intervention/ experimental therapy and the other
group that received the placebo (or standard of care).

• Considered gold standard for research.

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Randomized Controlled/Clinical Trial:

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Design of a Randomized Controlled/Clinical Trial:

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Phases in Clinical Trial:

Phase I: We aim to assess the safety of the drug (is it safe ?)

Phase II: We aim to assess the efficacy of the drug (does it work ?)

Phase III: We want to know if this drug is better than the old treatment (is it better ?)

Phase IV: We follow-up to detect long-term side effects (can it stay in the market ?)

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Non- Randomized Controlled/Clinical Trial:

• Involves an approach to selecting controls without randomization.

• Since this design depends on already collected data from different sources, the
information obtained may not be accurate, reliable, lack uniformity and/or completeness
as well.

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Non- Randomized Controlled/Clinical Trial:

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Cross Over Clinical Trial:

• Two or more experimental therapies are administered, one after the other, in a specified
or a random sequence, to the same group of patients.

• There is a washout (no treatment) period between therapies.

• Individuals serve as their own controls.

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Cross Over Clinical Trial:

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Factorial Trial:

• Adopted when the researcher wishes to test two different drugs with independent
effects on the same population. Typically, the population is divided into 4 groups, the
first with drug A, the second with drug B, the third with drug A and B, and the
fourth with neither drug A nor drug B.

• The outcomes for drug A are compared to those on drug A, drug A and B and to those
who were on drug B and neither drug A nor Drug B.

• It saves time and helps to study two different drugs on the same study population at
the same time

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Factorial Trial:

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Community Trial:

• Also known as cluster-randomized trials, involve groups of individuals with and


without disease who are assigned to different intervention/ experiment groups.

• Groups of individuals from a town or city, or school or college, will undergo the same
intervention/ experiment.

• Results will be obtained at a larger scale.

• Not be able to account for inter-individual and intra-individual variability.

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Community Trial:

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Field Trial:

• Also known as preventive or prophylactic trials, and the subjects without the disease
are placed in different preventive intervention groups.

• E.g: Randomly assign to groups of a healthy population and to provide an intervention to


a group such as a vitamin and following through to measure certain outcomes. The
subjects are monitored over a period of time for occurrence of a particular disease
process.

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Field Trial:

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Meta Analysis and Systematic Reviews

Meta Analysis

• A systematic, quantitative method that


combines the results of all relevant studies to
produce an overall estimate.

A meta-analysis can be part of a systematic review,


but not all systematic reviews include meta-analysis.

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Meta Analysis and Systematic Reviews

Meta Analysis

Forest plot of positive chest CT imaging in asymptomatic participants

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Systematic Reviews
• A summary of the scientific literature on a specific topic or question that uses explicit
methods to conduct a comprehensive literature search and identify relevant studies,
critically appraise the quality of each study, and summarize the body of literature or
evidence to answer the question.
– Specific research question
– Standardized review protocols that
often include trained reviewers
– Detailed inclusion and exclusion
criteria for selection studies
– Preestablished quality criteria with
which to rate the value of the
individual studies.

Dr.Asokan.G.V./PH/CHSS/UoB
Experimental Study Designs
Systematic Reviews

Dr.Asokan.G.V./PH/CHSS/UoB
Levels of Evidence Pyramid

Dr.Asokan.G.V./PH/CHSS/UoB
Overview of methodologies used within a
study design
Randomization

• Adopted in research to prevent bias due to subject selection, which may impact the result
of the intervention/experiment being studied.

• ensures scientific validity.

• ensures comparability between groups as most baseline characteristics are similar prior
to randomization and therefore helps to interpret the results.

• There are three types of randomization: simple randomization, block randomization


and stratified randomization.

Dr.Asokan.G.V./PH/CHSS/UoB
Overview of methodologies used within a
study design
Blinding
• is a methodology adopted in a study design to intentionally not provide information
related to the allocation of the groups to the subject participants, investigators and/or
data analysts.

• There are 3 forms of blinding: single-blinded, double-blinded and triple-blinded.

• In single-blinded studies, otherwise called as open-label studies, the subject


participants are not revealed which group that they have been allocated to.

• In double-blinded studies, both the study participants and the investigator will be
unaware of the group to which they were allocated to.

• In triple-blinded studies, the subject participants, investigators and data analysts will
not be aware of the group allocation.

Dr.Asokan.G.V./PH/CHSS/UoB
Study Design Variables - Bias
Confounding
• Variables that cause/prevent an outcome from occurring outside of or along with the
variable being studied. These variables render it difficult or impossible to distinguish
the relationship between the variable and outcome being studied).

Dr.Asokan.G.V./PH/CHSS/UoB
Study Design Variables - Bias
Confounding

Confounding
variable

Affects the relationship


between the two variables

Dr.Asokan.G.V./PH/CHSS/UoB
Study Design Variables - Bias
Confounding
Researchers have conducted a cohort study in country A to examine the association between a diet high in
fat and the risk of colon cancer. The researchers believe that vitamin use may be a confounder. Use the 2x2
tables below to determine if vitamin use is a confounder in the high fat diet colon cancer association.

Dr.Asokan.G.V./PH/CHSS/UoB
Study Design Variables - Bias
Confounding

Dr.Asokan.G.V./PH/CHSS/UoB
Study Design Variables - Bias
Confounding
1. Is vitamin use an independent risk factor or protective factor for colon cancer?

2. Is vitamin use differentially distributed between the high fat diet and low-fat diet
groups?

3. Compare the crude risk ratio with the risk ratios stratified by vitamin use.

Dr.Asokan.G.V./PH/CHSS/UoB
Study Design Variables - Bias
Confounding

1. Risk ratio of vitamin users getting colon cancer among the non-exposed group: (50/850) /
(100/800)= 0.47

A risk ratio of 0.47 shows that vitamin use is a moderate inverse predictor of colon cancer. In this
study population, vitamin use was protective for colon cancer.

2. Among people who eat a high fat diet there are 1980/2474= 80% vitamin users.
Among people who do not eat a high fat diet there are 850/1650= 52% vitamin users .

So, vitamin use is differentially distributed among the high fat and low-fat diet exposure
groups.

Dr.Asokan.G.V./PH/CHSS/UoB
Study Design Variables - Bias
Confounding

3) The crude risk ratio (not stratified by vitamin use) is the risk of colon cancer from high fat diet exposure / the
risk of colon cancer from low fat diet exposure. Crude risk ratio = (254/2474) / (150/1650) = 1.13

The risk ratio for colon cancer among vitamin users with a high fat diet is: Risk ratio = (150/1980) /
(50/850)= 1.29

The risk ratio for colon cancer among non-vitamin users with a high fat diet is: Risk ratio = (104/494) /
(100/800) =1.68

The crude risk ratio of 1.13 and the vitamin-specific risk ratio of 0.47 (from question 1) are not in between the
stratified risk ratios, they are both lower than the stratified risk ratios.

Thus, the crude risk ratio is confounded by vitamin use.

Dr.Asokan.G.V./PH/CHSS/UoB
Study Design Variables - Bias
Controlling Confounding

During Study Design


1. Randomization
2. Restriction
3. Matching

During analysis
4. Stratification
5. Adjustment (Statistical Modeling)
a) Simple / standardization
b) Multiple / multivariate adjustment
c) Best case / worst case analysis

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
• Qualitative research explores and provides deeper insights into real-world problems.

• Helps generate hypotheses as well as further investigate and understand quantitative


data

• Gathers participants' experiences, perceptions, and behaviour. It answers the hows


and whys instead of how many or how much.

• Stand-alone OR Mixed method

• Open-ended

• Themes and patterns

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
• Qualitative and quantitative work are not necessarily opposites nor are they
incompatible.

• Qualitative and quantitative approaches are different, they are not necessarily
opposites, and they are certainly not mutually exclusive.

• Qualitative research can help expand and deepen understanding of data or results
obtained from quantitative analysis.

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Types of Qualitative Study Designs

• Ethnography

• Grounded Theory

• Phenomenology

• Narrative Research

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Types of Qualitative Study Designs

Ethnography

• Has its origins in social and cultural anthropology. It involves the researcher being
directly immersed in the participant’s environment and come out of it with accounts of
actions, behaviours, events, etc.

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Types of Qualitative Study Designs

Ethnography

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Types of Qualitative Study Designs

Grounded Theory

• is the “generation of a theoretical model through the experience of observing a study


population and developing a comparative analysis of their speech and behavior.”

• Grounded theory research is inductive.

• explain how and why an event occurs or how and why people might behave a certain
way.

• using the Grounded Theory approach can then develop a theory to explain the
phenomena of interest

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Types of Qualitative Study Designs

Grounded Theory

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Types of Qualitative Study Designs

Phenomenology

• is the “study of the meaning of phenomena or the study of the particular”

• looking into the ‘lived experiences’ of the participants and aims to examine how and
why participants behaved a certain way, from their perspective.

• Grounded Theory aims to develop a theory for social phenomena through an


examination of various data sources whereas Phenomenology focuses on
describing and explaining an event or phenomena from the perspective of those
who have experienced it.

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Types of Qualitative Study Designs

Phenomenology

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Types of Qualitative Study Designs

Narrative Research

• is rife with the possibilities of ‘thick’ description as this approach weaves together a
sequence of events, usually from just one or two individuals, in the hopes of
creating a cohesive story, or narrative.

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Types of Qualitative Study Designs

Narrative Research

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Research Paradigm

• The assumptions, norms, and standards that underpin different approaches to research.
Research paradigms (different ontology and epistemologies) are the ‘worldview’ that inform
research.

• Ontology is defined as the "assumptions about the nature of reality”

• Epistemology is defined as the “assumptions about the nature of knowledge” that


inform the work researchers do.

• A research paradigm is not complete without describing positivist, postpositivist, and


constructivist philosophies.

Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Research Paradigm Philosophies

Positivist/ Positivism
• is a philosophy that the scientific method can and should be applied to social as well as
natural sciences

Postpositivist

• positivist philosophies value hypothesis-testing, whereas postpositivist philosophies value


the ability to formulate a substantive theory.

Constructivist

• a subcategory of postpositivism, focuses on how ‘reality’ is not a fixed certainty and


experiences, interactions, and backgrounds give people a unique view of the world.
Dr.Asokan.G.V./PH/CHSS/UoB
Research Study Designs -Qualitative
Qualitative Data Analysis
• Qualitative research could amount to a large amount of data. Data is transcribed, coded
manually or with the use of Computer Assisted Qualitative Data Analysis Software or
CAQDAS such as ATLAS.ti or Nvivo

Clinical Significance
• Provides an opportunity to generate and refine hypotheses and delve deeper into the data
generated by quantitative research.

Enhancing Healthcare Team Outcomes


• May help develop a theory or a model for health research that can be further explored by
quantitative research.

Dr.Asokan.G.V./PH/CHSS/UoB
Summary

• Choosing the right research/study design is an important


methodological process.
• Avoid confounding in research studies by appropriate research designs
and methodology.

Dr.Asokan.G.V./PH/CHSS/UoB
References
• Chidambaram AG, Josephson M. Clinical research study designs: The essentials. Pediatr Invest. 2019;3:245-252.
https://doi.org/10.1002/ped4.12169
• Levels of Evidence Pyramid created by Andy Puro, September 2014. https://guides.himmelfarb.gwu.edu/ebm/studytypes
• Treasure Island (FL): StatPearls Publishing; 2024 Jan-.
• Dr. Carl M. Shy, Epidemiology 160/600 Introduction to Epidemiology for Public Health course lectures, 1994-2001, The
University of North Carolina at Chapel Hill, Department of Epidemiology
• Rothman KJ, Greenland S. Modern Epidemiology. Second Edition. Philadelphia: Lippincott Williams and Wilkins,1998.
• The University of North Carolina at Chapel Hill, Department of Epidemiology Courses: Epidemiology 710, Fundamentals of
Epidemiology course lectures, 2009- 2013, and Epidemiology 718, Epidemiologic Analysis of Binary Data course lectures,
2009-2013

Dr.Asokan.G.V./PH/CHSS/UoB

You might also like