This document provides an overview of epidemiological study designs, outlining their definitions, types, and classifications. It distinguishes between descriptive and analytic studies, observational and experimental studies, and further categorizes them based on timing and data type. Moreover, it discusses the advantages and limitations of various study designs, such as case reports, cohort studies, and case-control studies, providing examples and considerations for each.

1. EPIDEMIOLOGY
Epidemiological study designs
Sewnet Getaye (BSC,MPH)
Email: sgetaye@gmail.com
1

2. Session Objectives
After completing this session learners will be able to
 Understand epidemiological study designs
 Differentiate the type of study design used by
investigators
 Identify the merits and demerits of each study
designs
 Apply epidemiological study designs to conduct a
study.

3. Study design
Definition
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.

4. Types of Epidemiologic study designs
I. Based on objective/focus/research
question
1. Descriptive studies
– Describe: who, when, where & how many
2. Analytic studies
– Analyse: How and why

5. Types of Epidemiologic study designs
II. Based on the role of the investigator
1. Observational studies
– The investigator observes nature
– No intervention
2. Intervention/Experimental studies
– Investigator intervenes
– He has a control over the situation

6. Types of Epidemiologic study designs
III. Based on timing
1. One-time (one-spot) studies
– Conducted at a point in time
– An individual is observed at once
2. Longitudinal (Follow-up) studies
– Conducted in a period of time
– Individuals are followed over a period of time

7. Types of Epidemiologic study designs
IV. Based on direction of follow-up/data
collection
1. Prospective
– Conducted forward in time
2. Retrospective
– Conducted backward in time

8. Types of Epidemiologic study designs
V. Based on type of data they generate
1. Qualitative studies
– Generate contextual data
– Also called exploratory studies
2. Quantitative studies
– Generate numerical data
– Also called explanatory studies

9. Types of Epidemiologic study designs
VI. Based on study setting
1. Community-based studies
– Conducted in communities
2. Institution-based studies
– Conducted in institutions
3. Laboratory-based studies
– Conducted in major laboratories

10. Types of Epidemiologic study designs
VII. Standard classification
1. Cross-sectional studies
2. Case-control studies
3. Cohort studies
4. Experimental studies

11. Classification of Study designs
Epidemiological Study Designs
Descriptive
Ecological
/Correlational
Case Report/
Case Series
Cross-Sectional
Analytic
Observational
Case-control
Cohort
Experimental/
Interventional
Therapeutic/
clinical
Preventive
Filed trial
Community
Trial

12. Descriptive studies
Relatively cheap in terms of time cost, because it
can use information already collected.
It usually describes:
1. Who gets a disease and who doesn’t ( person)
2. Where rates are highest and lowest ( place)
3. Temporal patterns of disease (time)

13. Descriptive studies
 It is the most common form of study in
medical literatures
 There are three forms of descriptive study
designs
1. Correlational /ecological design ( use population as
study subject)
2. Case report and/or case series studies
3. Cross-sectional survey

14. Case report and case series
• Case reports describe the experience of a single
patient
• Case series describe the experience of a group
of patients with similar diagnosis
• Both document unusual occurrences
14

15. Case report
• It is the study of health profile of a single individual using
a careful and detailed report by one or more clinicians
• It is made using a history, physical examination and lab
investigation
• Report is usually documented if there is unusual medical
occurrence, thus it may be first clue for identification of a
new disease
• It is useful in constructing a natural history of individual
disease. 15

16. Case report
Eg. The first one AIDS cases in USA.
 One young, previously healthy homosexual man was
diagnosed as having Pneumocysti carinii pneumonia at
Los Angeles hospital in 1980. This form of pneumonia
had been seen almost exclusively among older men and
women whose immune systems were suppressed. This
unusual circumstance suggested that this individual was
actually suffering with a previously unknown disease,
subsequently it was called AIDS
16

17. Case series
• First case report may stimulate compilation of
additional case reports….a case series
e.g. occurrence of Pneumocystis carinii on young,
homosexual man with no history of immune
deficiency stimulated the collection of additional
similar cases
• Collection of case reports in a short period of
time 17

18. Case series
• Describes characteristics of a number of
patients with a given disease
• Similar to case report, it is usually made on
cases having new and/ or unusual disease
• It is often used to detect the emergence of new
disease or an epidemics
18

19. Case series
Eg. The first five AIDS cases in USA.
• Five young, previously healthy homosexual men were diagnosed
as having Pneumocysti carinii pneumonia at Los Angeles hospital
during a six month period from 1980 to 1981. This form of
pneumonia had been seen almost exclusively among older men and
women whose immune systems were suppressed. This unusual
circumstance suggested that these individuals were actually
suffering with a previously unknown disease, subsequently it was
called AIDS.
19

20. Case report / series
Advantages:
• Use available clinical data
• Detailed individual data
• Useful for the recognition of new diseases
• Suggest need for investigation (hypothesis generation)
Disadvantages:
• May reflect experience of one person or one clinician
• No explicit comparison group
• Difficult to compute rate as the denominator is not 20

21. Ecological study
• Based on aggregate measures of exposure and outcome
from several populations
• The units of analysis are populations or groups of
people rather than individuals
• Correlations are obtained between exposure rates and
disease rates among different groups or populations
• Compare populations in different countries at the same
time or the same population on one country at different
times 21

22. Ecological study
Example
• Suppose air pollution is higher in Baltimore than in Tampa, but
mortality from lung disease is lower in Baltimore than in Tampa.
It would be fallacious to conclude that air pollution protects
against lung disease deaths.
• It is possible that persons dying of lung disease in Tampa may
have moved from cities with high air pollution or that another risk
factor for lung disease – such as smoking – is more prevalent in
Tampa than Baltimore. We do not know the cumulative exposures
of cases and non-cases in either city.
22

23. Ecological study
Ecologic Fallacy:
• Observations made at the group level may not
represent the exposure-disease relationship at
the individual level
• The ecologic fallacy occurs when incorrect
inferences about the individual are made from
group level data
23

24. Ecological study
Ecological study Strength
• Easy to do
• Quick and inexpensive
• Often use already available information
• Generate hypotheses for additional study
24

25. Ecological study
Limitation
• Unable to examine data for individuals; data on exposure
and data on outcome are collected independently
• No assurance that persons with exposure (risk factor) of
interest are the same ones with the outcome (disease) of
interest
• Association at the aggregate level may not reflect
association at the individual level - The ecologic fallacy
25

26. Cross-sectional studies
 In this study design information about the status of
an individual with respect to presence/absence of
exposure and diseased is assessed at a point in time.
Cross-sectional studies are useful to generate a
hypothesis rather that to test
For factors that remain unaltered overtime (e.g. sex,
race, blood group) it can produce a valid association

27. Cross-sectional studies
Comparison groups are formed after data collection
The object of comparison are prevalence of exposure or
disease
Groups are compared either by exposure or disease status
Cross-sectional studies are also called prevalence studies
(point)
Cross-sectional studies are characterized by concurrent
classification of groups

28. Cross-sectional studies

29. Cross-sectional studies

30. Design and analysis of cross-sectional studies

31. Design and analysis of cross-sectional studies

32. Design and analysis of cross-sectional studies

33. Design and analysis of cross-sectional studies
Measure of association in cross-sectional studies: -Odds
ratio

34. Cross-sectional studies
Uses of Cross-Sectional Studies
Hypothesis generation
Estimation of the magnitude and distribution of a
health problem
Intervention planning

35. Cross-sectional studies
Advantages of cross-sectional studies
• Less time consuming
• Less expensive
• Provides more information
• Describes well
• Generates hypothesis

36. Cross-sectional studies
Limitations of cross-sectional studies
• Antecedent-consequence uncertainty
“Chicken or egg dilemma”
• Data dredge leading to inappropriate
comparison
• More vulnerable to bias

37. Example of Cross-sectional study
A study was conducted among 240 people to
determine the relationship between coffee drinking
and stomachache. The people were asked if they
had stomachache and if they were coffee drinkers.
Out of 80 people who reported that they were
coffee drinkers, 20 reported having stomachache.
Of those who reported that they do not drink coffee
4 reported having stomachache

38. Example …
a) Summarize the result by 2-by-2 table ?
b) Calculate the prevalence of stomachache?
c) Calculate the prevalence of coffee drinking ?
d) Calculate OR?

39. Example …
a.
b. P=
𝑎+𝑐
𝑎+𝑏+𝑐+𝑑
=
24
240
=10%
c. P=
𝑎+𝑏
𝑎+𝑏+𝑐+𝑑
=
80
240
= 33.3%
d. OR=
𝑎𝑑
𝑏𝑐
=
20 𝑥 156
60 𝑥 4
= 13
Drank
coffee
Stomach ache
Yes No Total
Yes 20 60 80
No 4 156 160
Total 24 216 240

40. Analytical study designs
Purpose / aim of analytic epidemiologic study designs
To test hypothesis about causal relationship
To search for cause & effect
To compare treatment regimens/prevention programs
To asses diagnostic tests
To quantify the association b/n exposure & outcome
(measure of association)
It focus on determinants of the diseases by testing
hypothesis

41. Case-control studies
• Subjects are selected with respect to the presence
(cases) or absence (controls) of disease, and then
inquiries are made about past exposure
• We compare diseased (cases) and non-diseased
(controls) to find out the level of exposure
• Exposure status is traced backward in time

42. Case-control studies

43. Case-control studies
In case-control study design the disease status is
fixed by the investigator prior to the data collection
while exposure status to the expected risk factor is
random

44. Case-control studies

45. Case-control studies
Features to look for in a Case-control study
Is selection bias present?
• Are cases and controls similar in all important respects except
the disease in question?
Is information bias present?
• Is information about exposures gathered in the same way for
cases and controls?
Is confounding factors present?
• Could the results be accounted for by the presence of a factors
associated with both the exposure and outcome but not directly
involved in the causal pathway?

46. Case-control studies
Steps in a case control study
• Define the study’s objectives
• Identify and select “cases”:
• Select “controls”
• Collect data: measure level of “exposure” in both cases
and controls
• Analyze data: compare the exposure frequencies in those
with and without disease

47. Case-control studies
Choosing cases and controls in case-control study
• Ideally, cases are selected from a clearly defined
population, often called the source population, and
controls are selected from the same population that
yielded the cases
• Control group should be representative of the
population from which the cases are derived,
typically called the source population

48. Case-control studies
Choosing controls
• Two common types of controls are population based and
hospital-based controls
Population-based controls
• In population-based case-control study, controls are
selected from the community
• An advantage is that cases and controls come from the
same source population, so they are similar in some way
• A disadvantage is that it is difficult to obtain population
lists and to identify and enroll subjects

49. Case-control studies
Hospital-based controls
• In a hospital-based case-control study, controls are
selected from hospital patients with illnesses other than
the disease of interest
• An advantage is that hospital controls are easily
accessible, tend to be cooperative, and are inexpensive
• A disadvantage is that hospital-based controls are not
likely to be representative of the source population that
produced the cases

50. Case-control studies

51. Case-control studies
Recall information in Case-control study
• Information on some past exposures depends on
memory of events from both cases and controls
• Recall bias occurs when the recall is better among
cases than controls because of the presence of the
disease
• Consequently, a false association may be found
between exposure and disease

52. Case-control studies
Case-control study Strengths
• Good for studying rare outcomes
• Can examine many exposures at the same time
• Quick & Cheap
• Provides Odds Ratio

53. Case-control studies
Limitation
• Cannot measure Incidence, Prevalence and Relative Risk
• Can only study one outcome
• Not suitable for rare exposures
• Highly liable to selection bias and recall bias
• Difficult to establish temporal relationship of exposure-
disease relationship i.e. Does not establish sequence of
events

54. Example of Case-control study
In a study examining the relationship between the chili
pepper consumption and gastric cancer, the researchers
sampled 910 study subjects, 213 with gastric cancer and
697 controls, and asked their prior history of chili pepper
consumption. The researchers found that,204 and 552 of
the total cases and controls had the history of chili pepper
consumption respectively.
a) Draw 2-by-2 crosstab?
b) Calculate OR?

55. Example …
a.
b. OR=
𝑎𝑑
𝑏𝑐
=
204 𝑥 145
552 𝑥 9
= 5.95
Ate chili pepper Gastric cancer
Yes No Total
Yes 204 552 756
No 9 145 154
Total 213 697 910

56. Cohort study
What is a cohort?
• A well-defined group of people who share a common
characteristic/ experience followed-up for specified
period of time
• Examples
– Exposure cohort: individuals assembled as a group
based on some common exposure e.g. asbestos exposure
in ship yards
56

57. Cohort study
• Select group of disease-free people who are
classified according to a specific exposure
• Follow them over time for a specified period of
time to see the occurrence of outcomes of
interest in groups
• Measure and compare the incidence of outcome
between exposed and unexposed groups
• Subjects are sampled by their exposure status57

58. Cohort study
58

59. Cohort study
• Directionality : Exposure to Outcome
• Temporal relationship between observations of
exposure(E) and outcome(O)
• Cohort studies can be either
– Prospective
– Retrospective
59

60. Prospective cohort study
60

61. Prospective cohort study
• Investigator starts the study (from the beginning)
with the identification of the population and the
exposure status (exposed/not exposed groups)
• Follow them (over time) for the development of
disease(future follow-up)
• Time frame of prospective cohort study: From
present to future
• Takes relatively long time to complete the study
61

62. Prospective cohort study: Example
62

63. Prospective cohort study: Example
Framingham Study
Objectives: To study the impact of several factors on
incidence of cardiovascular diseases
Exposures: Blood pressure, blood cholesterol level,
electrocardiogram abnormalities, smoking, body weight,
diabetes, physical exercise, etc.
Multiple Outcomes: Coronary heart disease, stroke,
congestive heart failure, peripheral arterial disease
63

64. Prospective cohort study: Example
 The study started with a defined population
 There were several hypotheses to be tested
-Different exposures and different outcomes
 For each exposure, investigators identified the “exposed
"and “not exposed "groups
 For each exposure, the participants were followed for the
development of disease
 Different exposures were studied, as well as different
diseases 64

65. Timeline Milestones from the Framingham Study
 1948:start of the Framingham Heart Study
 1960:cigarette smoking found to increase risk of heart
disease
 1961:cholesterol level, blood pressure, and ECG
abnormalities found to increase risk of heart disease
 1967:physical activity found to reduce risk of heart
disease; obesity to increase the risk
 1970:high blood pressure found to increase the risk of
stroke
 1971:Framingham Offspring Study initiated to assess
familial and genetic factors as determinants of coronary
heart disease 65

66. Retrospective cohort study
66

67. Retrospective cohort study
Investigator uses existing data collected in the past
to identify the population and the exposure status
(exposed/not exposed groups)
Determine disease status at the present time (no
future follow-up)
Time frame of retrospective cohort study: From
past to present
67

68. Is Prospective or Retrospective cohort
study????????????
In an "outcomes" analysis of coronary bypass
surgery, health services researchers identified charts
of all patients diagnosed with three vessel disease at
three major clinical centers during the past ten years.
These patients are separated into those who initially
were treated surgically and those who were initially
treated medically. Aggregate results for mortality
and a variety of other outcome variables were
compiled for each group, to produce prognostic
profiles for those initially treated medically vs. those
who received immediate surgery. 68

69. Is Prospective or Retrospective cohort
study????????????
The pediatricians wanted to determine if there is a
difference in the incidence of croup between the
babies who are breastfed and those who are not
breastfed. They followed a group of babies who are
breastfed for six months following birth compared
to another group of babies who are not breastfed for
six months following birth. All the babies were free
of croup when the pediatricians started the study. Of
100 breastfed babies, 2 babies developed the croup
while of 50 babies who are not breastfed, 5
developed the croup. 69

70. Cohort study
Features to look for in a cohort study
• Is selection bias present?
• Are the exposed and unexposed groups similar in
all important respects except the exposure status?
• What steps were taken to minimize information
bias?
• Is the outcome identified in the same way for
both groups?
70

71. Cohort study
• How complete was the follow-up of both groups?
• What effort were made to limit loss to follow-up?
• Was loss to follow-up similar in both groups?
• Were potential cofounding factor present and controlled
in the analysis?
• Did the investigators anticipated and gather information
on potential confounding factors?
• What method(s) were used to assess and control
confounding? 71

72. Cohort study
Steps in a cohort study
• Define the study’s objectives
• Identify the study cohort
• Measure level of exposure and categorize cohort into
“exposed” and “unexposed” groups
• Follow groups
• Measure outcome or “disease” (dependent) variable
• Analyze data: compare incidence rates in the different
exposure groups
72

73. Cohort study
73

74. Example of Cohort study
Researchers conducted a 20 year prospective cohort
study to assess a possible association between
eating fish and heart disease. They found that, of
the 200 subjects who ate fish, 10 developed heart
disease while of the 400 subjects who did not eat
fish, 10 developed heart disease.
a) Draw 2-by-2 table?
b) Calculate RR? 74

75. Example …
a.
b. RR=
𝑎
𝑎+𝑏
𝑐
𝑐+𝑑
=
10
10+190
10
10+390
= 2
Ate fish Heart disease
Yes No Total
Yes 10 190 200
No 10 390 400
Total 20 580 600

76. Cohort study
Strengths
• Can directly measure incidence rates
• Establishes time sequence for causality
• Eliminates recall bias
• Allows for accurate measurement of exposure variables
• Best for studying rare exposures
• Can measure multiple outcomes at the same time
• Can adjust for confounding variables
• Can calculate relative risk
76

77. Cohort study
Limitation
• Expensive
• Time consuming
• Relatively poor for studying rare diseases or outcomes
• Selection bias
• Exposure may change over time
• Disease may have a long pre-clinical phase
• Potential for loss of study subjects to follow-up
• May require large study groups
77

78. Experimental study design
• A study in which a population is selected for a planned
trial of a regimen, whose effects are measured by
comparing the outcome of the regimen in the
experimental group versus the outcome of another
regimen in the control group
• Such designs are differentiated from observational
designs by the fact that there is manipulation of the study
factor (exposure), and randomization (random
allocation) of subjects to treatment (exposure) groups78

79. Experimental study design
79

80. Experimental study design
80

81. Experimental study design
• The investigator assigns the exposure variable ß
Prospective in nature
• Randomized Clinical Trial(RCT): individual
study subject
• Community Intervention Trial(CIT): study
subject is the “community”
81

82. Experimental study design
Why performed?
1. Provide stronger evidence of the effect (outcome)
compared to observational designs, with maximum
confidence and assurance
2. Yield more valid results, as variation is minimized and
bias controlled
3. Determine whether experimental treatments are safe and
effective under “controlled environments” (as opposed to
“natural settings” in observational designs) 82

83. Experimental study design
Steps in an Experimental study
• Define the study’s objectives
• Identify the target population
• Recruit volunteers from the target population
• Random allocation of volunteers into two groups
(assign study subjects to exposure and non-
exposure group)
83

84. Experimental study design
• Assign exposure (independent) variable. Consider
blinding
• Follow groups prospectively
• Measure outcome (dependent) variable
• Analyze data: compare incidence rates in
exposed (treated) and unexposed (untreated)
84

85. Experimental study design
• Time frame of Experimental study: From
present to future
• Random allocation
• Blinding
• The most serious objections to Experimental
studies are ethical issues
85

86. Experimental study design
86

87. Experimental study design
Strengths:
• Best measure of causal relationship
• Best design for controlling bias and confounding
• Can measure multiple outcomes
Limitation :
• High cost and time-consuming
• Ethical issues may be a problem
87

88. Example of Experimental study
• Researchers are interested in determining whether
the advice given during routine physical
examination is effective in encouraging patients to
stop smoking. In a study of current smokers, one
group of patients was given a brief talk about
hazards of smoking and was encouraged to quit. A
second group received no advice pertaining to
smoking. All the patients were given a follow up
examination/assessing. In a sample of 114 patients
who received advice, 11 reported, they had quit
smoking and in a sample of 96 patients who had
not received advice, 7 quit smoking. 88

89. 89