The document discusses different study designs used in research, including observational studies like case reports, case series, cross-sectional studies, and cohort studies, as well as experimental studies like randomized controlled trials. It describes the key characteristics and advantages and disadvantages of each design. The highest level of evidence comes from randomized controlled trials, while observational studies are useful for initial hypothesis generation.

1. STUDY DESIGNS
PRESENTED BY: Dr. Parth K. Vachhani

2. INTRODUCTION
 A study design is a specific plan or
protocol for conducting the study, which
allows the investigator to translate the
conceptual hypothesis into an
operational one.
7/10/2015
2

3. 7/10/2015
3

4. CONTD.
 Observational: Studies that do not
involve any intervention or
experiment.
 Experimental: Studies that entail
manipulation of the study factor
(exposure) and randomization of
subjects to treatment (exposure)
groups.
7/10/2015
4

5. HIERARCHY OF STUDY DESIGN

6. OBSERVATIONAL STUDIES
7/10/2015
6

7. OBSERVATIONAL STUDIES
 Non-experimental
 Observational because there is no
individual intervention
 Treatment and exposures occur in a
“non-controlled” environment
 Individuals can be observed
prospectively, retrospectively or
currently.
7/10/2015
7

8. DESCRIPTIVE STUDIES
7/10/2015
8

9. CASE REPORTS
 Detailed presentation of a single case or
handful of cases
 Generally report a new or unique finding
e.g. previous undescribed disease
e.g. unexpected link between
diseases
e.g. unexpected new therapeutic
effect
e.g. adverse events
7/10/2015
9

10. CASE SERIES
 Experience of a group of patients with a
similar diagnosis
 Cases may be identified from a single
or multiple sources
 Generally report on new/unique
condition
7/10/2015
10

11. CONTD.
 Advantages
 Useful for hypothesis generation
 Informative for very rare disease with
few established risk factors
 Disadvantages
 Cannot study cause and effect
relationships
 Cannot assess disease frequency
7/10/2015
11

12. Case Report
Case Series
One case of unusual
findings
Multiple cases of
findings
7/10/2015
12

13. ANALYTICAL STUDIES
7/10/2015
13

14. BASIC QUESTION IN ANALYTIC STUDY
 Are exposure and disease linked?
Exposure Disease
7/10/2015
14

15. ANALYTIC STUDY
 Group data
Ecologic study
 Individual data
Cross-sectional study
Case-control study
Cohort study
7/10/2015
15

16. ECOLOGICAL STUDY
16
 An investigation of the distribution of
health and its determinants between
groups of individuals.
 Unit of study is the aggregate data not
individual level.
 It is usually be conducted as the first
step study for research.
 The result is difficult to interpret
because of confounding and bias.
7/10/2015

17. CONTD.
 Advantages
 Cheap, quick and convenient since it
usually come from existing data
 Disadvantages
 Inability to link exposure with disease in
individual (ecological fallacy)
 Limit to control effect of other factors
7/10/2015
17

18. CROSS-SECTIONAL STUDIES
 An “observational” design that surveys
exposures and disease status at a single
point of time (a cross-section of the
population)
time
Study only exists at this point in time
7/10/2015
18

19. CONTD.
time
Study only exists at this point in time
Study
population
No Disease
Disease
factor present
factor absent
factor present
factor absent
7/10/2015
19

20. CONTD.
 Often used to study conditions that are
relatively frequent with long duration of
expression (nonfatal, chronic
conditions)
 It measures prevalence, not incidence
of disease
 Not suitable for studying rare or highly
fatal diseases or a disease with short
duration of expression
7/10/2015
20

21. ADVANTAGES
 Gives general description or scope of
problem
 Useful in health service evaluation and
planning
 Baseline for prospective study
 Low-cost
7/10/2015
21

22. DISADVANTAGES
7/10/2015
22
 No calculation of risk
 Temporal sequence is unclear
 Not good for rare diseases
 Selective recall can lead to bias

23. CASE CONTROL STUDY
 An “observational” design comparing
exposures in disease cases vs. healthy
controls from same population.
 Exposure data collected retrospectively.
 Most feasible design where disease
outcomes are rare.
7/10/2015
23

24. Study
population
Cases
(disease)
Controls
(no disease)
factor present
factor absent
factor present
factor absent
present
past
time
Study begins here
7/10/2015
24

25. ODDS RATIO
 Odds ratio= ad/bc
7/10/2015
25
Suspected
Risk Factor
Cases Controls
Present a b
Absent c d
a+c b+d

26. ADVANTAGES
 Cheap, easy and quick studies
 Require comparatively few subjects
 Multiple exposures can be examined
 Rare diseases and diseases with long
latency can be studied
 Suitable when randomization is unethical
7/10/2015
26

27. DISADVANTAGES
 Case and control selection troublesome
 Subject to bias
 Direct estimation of incidence is not
possible
 If the incidence of exposure is high, it is
difficult to show the difference between
cases and controls
7/10/2015
27

28. COHORT STUDY
 An “observational” design comparing
individuals with a known risk factor or
exposure with others without the risk
factor or exposure.
 Looking for a difference in the risk
(incidence) of a disease over time.
 One of best observational design.
 Data usually collected prospectively
(some retrospective)
7/10/2015
28

29. time
Study begins here
Study
population
free of
disease
Factor
present
Factor
absent
disease
no disease
disease
no disease
present
future
7/10/2015
29

30. 7/10/2015
30
Disease
TotalPresen
t
Absen
t
Exposur
e
present
a b a+b
Exposur
e
absent
c d c+d
CONTD.

31. ADVANTAGES
 Can establish population-based incidence
 Accurate relative risk (risk ratio)
estimation
 Can be used where randomization is not
possible
 Selection and information biases are
decreased
 Multiple outcomes can be studied
7/10/2015
31

32. DISADVANTAGES
 Lengthy and expensive
 May require large samples
 Not suitable for rare diseases
 Not suitable for diseases with long-
latency
 Unexpected environmental changes may
influence the association
 Nonresponse, migration and loss-to-
follow-up biases
7/10/2015
32

33. EXPERIMENTAL STUDY
7/10/2015
33

34. EXPERIMENTAL STUDY
 Treatment and exposures occur in a
“controlled” environment
 Planned research designs
 Clinical trials are the most well known
experimental design.
7/10/2015
34

35. CONTD.
 Investigator can “control” the exposure
akin to laboratory experiments except
living populations are the subjects
 Generally involves random assignment
to groups
 The ultimate step in testing causal
hypotheses
7/10/2015
35

36. RANDOMIZED CONTROLLED TRIAL
 A design with subjects randomly
assigned to “treatment” and
“comparison” groups.
 Provides most convincing evidence of
relationship between exposure and
effect.
 Not possible to use RCTs to test effects
of exposures that are expected to be
harmful for ethical reasons.
7/10/2015
36

37. time
Study begins here (baseline point)
Study
population
Intervention
Control
outcome
no outcome
outcome
no outcome
baseline
future
RANDOMIZATION
7/10/2015
37

38.  The “gold standard” of research
designs
 Provides most convincing evidence of
relationship between exposure and
effect
Trials of hormone replacement
therapy in menopausal women
found no protection for heart
disease, contradicting findings of
7/10/2015
38
CONTD.

39.  Ability to randomize subjects
 Temporal sequence of cause and effect
 Can control extraneous variables
 Best evidence of causality
ADVANTAGES
7/10/2015
39

40. DISADVANTAGES
7/10/2015
40
 Expensive
 It may be unethical to assign persons to
certain treatment or comparison groups

41.  Other Types of Experimental Study
 Field trials
 Community trials
 Animal studies
7/10/2015
41

42. META ANALYSIS
 Meta-analysis is a statistical analysis of a
collection of studies.
 Meta-analysis methods focus on
contrasting and comparing results from
different studies in anticipation of
identifying consistent patterns and
sources of disagreements among these
results.
7/10/2015
42

43. 7/10/2015
43