2. Prepared By
Md. Nazmul Islam
ID: 1210020
Department of Statistics
Begum Rokeya University
Rangpur-5400
3. Types of Epidemiologic Research Chapter 3
Prepared for:
Sukanta Das
Lecturer
Department of Statistics
Begum Rokeya University, Rangpur.
4. Chapter Outline
Experimental study design
-Advantages, Disadvantages & limitation
Quasi-Experimental study design
-Advantages, Disadvantages & limitation
Observational study design
-Advantages, Disadvantages & limitation
Types & objectives of Epidemiologic Research
5. Experimental Study Design
Definition:
A study in which the study factor has been artificially manipulated and randomization is
used to allocate subjects are called Experimental study.
In other words, Experimental design is the process of planning a study to meet specified
objectives. Planning an experiment properly is very important in order to ensure that the
right type of data and a sufficient sample size and power are available to answer the
research questions of interest as clearly and efficiently as possible.
6. Experimental Study Design
Advantages:
There are several advantages of Experimental study design. These are given below:
1. It is a basic, straightforward, effective type of research that can be approach across a
variety of disciplines.
2. Experimental research designs a repeatable and therefore results be checked and verified.
3. Due to the controlled environment of experimental study, better results are often achieved.
4. The results of experimental research can be duplicated.
5. It provides researchers with a high level of control.
6. Experimental research provides conclusions that are specific.
7. Experimental research allows cause and effect to be determined.
7. Experimental Study Design
Disadvantages:
The disadvantages Of Experimental study design are given below:
1. Experimental research can create artificial situations that do not always represent real-life
situations.
2. Results are highly subjective due to the possibility of human error.
3. Experimental research can create situations that are not realistic.
4. It is a time-consuming process.
5. There may be ethical or practical problems with variable control.
6. Extraneous variables cannot always be controlled.
7. Human responses in experimental research can be difficult to measure.
8. Experimental Study Design
Limitations:
There are some limitations of Experimental study design. These are given below:
1. Experimental research is a powerful tool for determining or verifying causation, but it
typically cannot specify “why” the outcome occurred.
2. Experimental research designs help to ensure internal validity but sometimes at the
expense of external validity. When this happens, the results may not be generalizable to
the larger population.
3. If an experimental study is conducted in its natural environment, such as a hospital or
community, it may not be possible to control the extraneous variables.
9. Quasi-Experimental Study
Definition: A study in which the study factor has been artificially manipulated but for
which randomization has not been used are called quasi-Experimental study. These design
may involves one-group comparison, multiple-group comparisons, or a combination of these.
With a one-group (or internal) comparison, each experimental unit serves as its own control
by observing the response variable before and after one and more inventions
With a simple multiple group (or external) comparisons, treatment or invention groups are
compared with each other, as they are in a simple experiment without randomization. in this
design , treatment groups are formed form convenience or according to the voluntary
behavior or subjects.
10. Quasi-Experimental Study
Advantages:
There are several advantages of quasi-experimental study design. These are given below:
1. The main advantages of quasi experiment over the experiment is the smaller number
of obstacles. It is More feasible and less expensive for conducting larger studies.
2. Especially in social sciences, where pre selection and randomization of group is often
difficult, they can be very useful in generating results for general tends.
3. Quasi-experimental design is often integrated with individual case studies, and allow
some sort of statistical analysis to take place.
4. In addition, without extensive pre-screening and randomization needing to be
undertaken, they do reduce the time and resources needed for experimentation.
11. Quasi-Experimental Study
Disadvantages:
There are several disadvantages of quasi-experimental study design. These are given below:
1. Quasi-experimental estimates of impact are subject to contamination by cofounding
variables. Also It has no ability to show causal relationships.
2. The lack of random assignment in the quasi-experimental design method may allow
studies to be more feasible, but this also poses many challenges for the investigator in
terms of internal validity.
3. The study groups may provide weaker evidence because of the lack of randomness.
4. The validity of quasi experimental designs is limited and there is great potential for bias.
12. Quasi-Experimental Study
Limitations:
There are some limitations of quasi-experimental study design. These are given below:
1. Without proper randomization, statistical tests can be meaningless.
2. Do not explain any pre-existing factors and influences outside of the experiment
3. The researcher needs to control additional factors that may have affected the results.
4. Some form of pre-testing or random selection may be necessary to explain statistical
results thoroughly.
13. Observational Study
Definition:
A study in which the study factor has not been artificially manipulated are called
Observational study. While an observational study can take many forms, the simplest design
closely resembles an experiment or quasi experiment. Observational studies are central to
epidemiologic research.
Observational studies are commonly divided into two subtypes on the basis of the degree of a
priori knowledge regarding the disease. These are:
(i) Descriptive study and (ii) Analytic study
A descriptive study usually is conducted when little is known about the occurrence, the
natural history or the determinants of a disease.
An analytical study is conducted when enough is known about the disease before the
investigation so that specific a priori hypothesis can be tested.
14. Observational Study
Advantages:
There are several advantages of observational study design. These are given below:
1. Observational research is often more practical or feasible to conduct because the study
factor is not manipulated.
2. Another potential advantageous that observational studies are often carried out to more
natural setting so that the study population is more representative to the target population.
3. The study is not uniformly expensive nor do they always take less time than other studies.
4. This feature has important implications to health planners and policymakers who base
their decisions partly on the results of epidemiologic investigators.
15. Observational Study
Disadvantages:
There are several advantages of observational study design. These are given below:
1. It can be viewed as too subjective.
2. It is time-consuming & depends on the role of researcher.
3. Overt: may affect the situation and thus validity of findings.
4. High potential for role conflict for practitioner researchers.
5. Data more likely to be incomplete and of poorer quality.
6. Non-randomised allocation to exposure of interest so strong likelihood of bias and
confounding.
16. Observational Study
Limitations:
There are several limitation of observational study design. These are given below:
1. The major limitations of observational study is that they affords the investigator the
least control over the study situation.
2. Results are generally more susceptible to distorting influences.
3. A greater burden is placed on the investigator, particularly in the analysis stage, to deal
with these potential sources of error that threaten the validity of his or her findings.
4. The investigator achieves relatively little control in the design stage.
5. Observational study tends to unique, making them very difficult to replicate and making
scientific generalization less secure.
17. Types and Objectives of Epidemiologic Research
Type Subtype Objectives
Experimental
(artificial
manipulation
of study factor
with
randomization)
Laboratory
Clinical trial
Community
Intervention
Test etiologic hypothesis and estimate acute behavioral and
biological effects.
Suggest efficacy of intervention to modify risk factors in a
population.
Test etiologic hypothesis and estimate long-term health effects.
Suggest efficacy of intervention to modify health status.
Suggest feasibility of population intervention.
Identify persons at “high risk”.
Test efficacy and effectiveness of clinical society interventions.
To modify health status within a particular population.
Suggest public health policies and programs.
18. Cont…..
Type Subtype Objective
Quasi-
Experimental
(artificial
manipulation of
study factor
without
randomization)
Clinical
Laboratory
Program/
policy
Test etiologic hypothesis and estimate long-term health
effects.
Suggest efficacy of intervention to modify health status.
Suggest feasibility of population intervention.
Same as laboratory experiment.
Evaluate extent to which public health goals are achieved.
Determine unanticipated problems or consequence of imple-
mentation and reasons for success or failure of the
intervention.
Compare cost and benefits of intervention.
Suggest changes in current health policies or programs.
19. Cont….
Type Subtype Objective
Observational
(no artificial
manipulation of
the factor)
Descriptive
Analytic
(etiologic)
Estimate disease frequency and time trends and identify
diseased individuals.
Generate etiologic hypothesis and suggest rationale for
new studies.
Test specific etiologic hypothesis and estimate chronic
health effects .
Generate new etiologic hypothesis and mechanism of
causation.
Generate preventive hypothesis and suggest potential for
disease prevention.