Epidemiological study design

Hiwot M.(MPH)

1
 Learning objective
At the end of this session, you will be able to:
1. Describe all types of epidemiological study designs
2. Characterize the difference between descriptive and analytic study
designs
3. Explain the uses of the various descriptive study designs

2
In broad terms the purpose of Epidemiology is to answer questions like:
How big is the problem (magnitude)?
• Prevalence, incidence, mortality
What, who and where of any health problem?
• Person characteristic of affected population
• Place characteristics (locality)
What factors are associated with certain disease
• Specific factors related to causation
To evaluate interventions
• Which drug is best for patients with X disease
• To evaluate any program

 In addressing this issues there are many approaches that are called
Epidemiological study design
3
 Definition

※ Study design is a detailed plan to enroll subjects, collect data, perform

analysis and interpret findings.

※ The purpose of study design is to transform the conceptual hypothesis in

to an operational hypothesis that can be empirically tested.

4
 Categories of Epidemiological studies
According to their focus of investigation:
Descriptive Epidemiology - Defines the amount and distribution of
health problems in relation to person, place and time. It answers the
questions who, where and when.

 Analytic Epidemiology – involves explicit comparison of groups of

individuals to identify determinants of health and diseases. It answers
the questions why and how.

5
6
 Overview of epidemiologic design strategies
• Descriptive
 Populations{Correlational studies}
 Individual
 Case report
 Case series
 Cross sectional studies
• Analytic studies
Observational
 Case control
 Cohort
 Retrospective
 Prospective
Interventional/Experimental
 Randomized controlled trial
 Field trial
 Clinical trial 7
 Descriptive studies
Defines amount and distribution of health problem
Person: describe disease occurrence by personal characteristics
 “Who is getting the disease?” Age, race, sex

Place: provides information on geographic distribution of the disease

“Where are the rates of disease highest/ lowest?”

Time: provides information organized by time.

“When does the disease occur commonly/ rarely?”

8
 Purpose of descriptive study design
⸙ To evaluate trends in health and disease and allow comparisons among
countries or subgroups within countries

⸙To evaluate a basis for planning and provision of services

⸙To identify problems to be studied by analytic methods and generate a

hypothesis related to those problems

⸙Describes the general characteristics of the distribution of a disease in relation

to person, place and time.

⸙To allocate resources efficiently and plan effective prevention or education

programs. 9
 1. Correlational / Ecological study
Uses data from entire population to compare disease frequencies. (i.e.
it doesn’t need data from individuals)
Between different groups during the same period of time or
In the same population at different points in time

Unit of data source and unit of analysis is population.

They use aggregate data and do not measure outcomes and exposure at
individual level.

10
 Correlational…..
Eg. Colon cancer rates are higher in U.S. counties that use mostly surface
water and in countries with high per capita meat consumption.

These relationships suggest that something about surface water, e.g.,

chlorination, and something about meat consumption, e.g., saturated fat
intake, might be factors in the development of colon cancer.

However, since exposure is not known at the individual level, it is possible

that the cases of colon cancer are not themselves people who drink
chlorinated water or eat meat, “Ecological fallacy” (The attempt to infer
individual characteristics or relationship from group-level measures)

11
Cont’d…

Strength Limitations

⸙Can be done quickly ⸙Unable to link an exposure to

⸙Inexpensive occurrence of disease in a
single individual. (prone to
⸙Can be done using available Ecological fallacy )
data (routine records, reports)
⸙Lack of ability to control for
⸙May be best design to study effects for potential
health effects of environmental confounding factors.
exposures
⸙Eg. Does soft drink
increase heart disease?

12
 2. Case report and case series

 These studies are generally used to report

New disease
An unexpected association between disease and symptoms.
An unexpected event in the course of observing or treating a patient.
Unique or rare features of a disease
Unique therapeutic approaches.

“Something unusual”
13
14
 Case report

⸎It is the study of health profile of a single individual using a careful

and detailed report by one or more clinicians.

⸎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
 Case series
⸎Individual case report can be expanded to a case series, which
describes characteristics of a number of patients (usually 5-12) with a
similar disease.

⸎Similar to case report, it is usually made on cases having new and/ or

unusual disease (giving interest to clinicians)

⸎It is often used to detect the emergence of new disease or an

epidemics.
⸎ E.g. The first five AIDS cases in USA.
16
 ...

Example:

⸙ Five young, previously healthy homosexual men were diagnosed as

having Pneumocystis 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.

17
 Case report and case series

Strength Limitation
⸙Very useful in hypothesis ⸙Are prone to Atomistic fallacy
generation ⸙ reports are biased on single
⸙Useful for studying sign and individual or few patients,
symptoms(new syndromes) which could happen by
and creating case definition for coincidence
epidemiological studies.
⸙Lack of appropriate
comparison group/unable to
test for statistical association.

18
 3. Cross sectional

⁜It is called study of prevalence/survey study.

⁜Measure disease and exposure status simultaneously among

individuals at the same point in time.

⁜Could provide information about the frequency of a disease by

furnishing a ‘snapshot’ at a specified time.

19
 Characteristics of cross sectional

⸙Assess both exposure and outcome simultaneously.

⸙Sample with out knowledge of exposure or disease- then

classify after result obtained.

⸙Calculate prevalence, but not incidence.

⸙Measure of association is made using odds ratio(OR)

20
21
 Odds ratio = cross product ratio

⸙In case control studies, RR can not be calculated directly to determine the
association between exposure and disease.

⸙Difficult to know the risk of disease among exposed and non exposed
since we start recruiting cases and controls.

⸙We use odds ratio to measure association between exposure and disease .

⸙The odds of an event is the ratio of the number of ways the event can
occur to the number of ways the event can not occur.

22
11/26/2025
 Strength
⸎Less expensive

⸎As it involves large sample size it is more likely to provide generalizable

findings

⸎Provides much information useful for planning health service and medical
programs

⸎Useful to compare prevalence of disease on different population

⸎Examine trends in disease prevalence or severity over time

⸎Yields prevalence 23
 Limitation

Since exposure and disease status is assessed at a single point in time,

temporal relationship between exposure and disease can not be clearly
determined.
Egg and chicken dilemma (it is difficult to know which occurred
first, the exposure or outcome?)
Potential bias in measuring exposure
Not feasible for rare diseases
Doesn’t yield incidences or true relative risk

24
 Analytic Epidemiological study designs
 Goal: to determine the relationship between exposure and disease:
– Assess determinants of disease
– Focus on risk factors, causes
 Used for

– Testing hypotheses
– Looking for / quantifying associations

The hallmark feature that distinguishes an analytic study from a

descriptive study is the presence of Comparison Group.

25
 Types of analytical study

1. Observational studies
– Case-control studies
– Cohort studies

2. Experimental studies
– Clinical trials
– Community trials

26
 1. 1. Case control
Subjects are selected with respect to presence or absence of the
outcome of interest and then inquiries are made about past exposure
to the factors of interest.

Case: those who have the outcome of interest

Controls: those who do not have the outcome of interest

The exposure histories of cases and controls are then obtained and
compared.

27
cont’d…

28
 Features of case control

⸎Identify group of cases and group of controls

⸎Question both groups for possible exposure

⸎Measure the frequency of exposure occurrence in both groups

⸎Compare the frequency of exposure between cases and controls

⸎Calculate the odds ratio and interpret the result

29
cont…

• Generates many insights in to the aetiology of chronic diseases such as

lung, cervical, cancers, congenital defects, etc.
Important for study of rare disease
For diseases with latent period or duration
Use convenient sampling
Short study period
Less expensive than cohort studies

30
 Selection of cases
 Ideally, cases are a random sample of all cases of interest in the source
population
 Sources for cases can be:
 hospital or clinic patient rosters
 death certificates
 special surveys
 reporting systems
 Care is needed that bias does not arise from the way in which cases are
selected (i.e. selection bias)

31
 Cont…

Selections of controls

⸙Controls should have the same exposure distribution as the source

population from which cases are drawn

⸙The controls should be similar to the cases in all respects other

than having the disease in question or

⸙Should be representative of all persons without the disease in the

population from which the cases are selected
32
 Sources of cases and controls
CASES CONTROLS

All cases diagnosed in the population Sample of general population

All cases diagnosed in a sample of the Non-cases in a sample of the population

population

All cases diagnosed in all hospitals Sample of patients in all hospitals who do
not have the disease

All cases diagnosed in a single hospital Sample of patients in the same hospital who
do not have the disease

Any of the above methods Spouses, siblings or associates of cases

33
Cont’d…

 Epidemiologists use several sources for identifying controls

like:
 Individuals from the general population
 Individuals attending a hospital or clinic
 Friends or relatives identified by the cases
 Dead controls

34
Analysis in case control

35
 Advantage of case control

Optimal for the evaluation of rare disease

Suitable for diseases with long induction period
Can examine multiple etiologic/risk factors for a single disease
Quick and inexpensive as compared with cohort study
Need small sample size
No ethical problems

36
 Disadvantage of case control

It is restricted to single outcome

Usually cannot measure disease risk
Prone to Information bias: e.g. recall bias, non-response bias
Prone to Selection bias: e.g. survivor bias
using different criteria to select cases and controls
the probability of selecting a real case and control
 Misclassification of exposures and outcomes
 Selection of controls is difficult
 Inefficient for rare exposures
37
 1.2. Cohort study
Cohort:
 The term cohort has military, not medical, roots.
 The term “cohort” derived from the Latin word “cohors”.
 A cohort was a 300–600-man unit in an ancient Roman army
 A group of individuals who have the same ideas or beliefs or who are pursuing
the same activity together

Figure : An early cohort in search of favorable outcomes

38
 Cohort study

⸙Involves following up for a specific period of time for the out come
occurrence in two or more groups
⸙Measure and compare the incidence of outcome between exposed and
unexposed groups
⸙Who will develop an outcome, when and why?
⸙Looking for an uncertain outcome
⸙Identifying group of
• Exposed subjects to
• Unexposed subjects

39
 Cohort study cont…

Incidence among exposed

(7/15)
Exposed

Incidence among
unexposed
unexposed
(3/15)

Follow up period

40
 Purpose of cohort study

Have two primary purpose

• Descriptive(measure of frequency)
• To describe the incidence rates of an outcome over time, or simply
describe the natural history of disease

• Analytic (measure of association)

• To analyze associations between the rates of the outcomes and risk
factors
41
 Types of cohort study
Depending on the temporal relationship between the initiation of the
study and the occurrence of the disease, there are two cohort studies
types

1. Prospective (classical) cohort study: at the beginning of the study

the outcome has not yet occurred

2. Retrospective (historical) cohort study: Both exposure and

outcome status have occurred at the beginning of the study

42
Prospective cohort study…

43
Retrospective cohort study…

44
 Closed and open cohort
There are two types of cohorts that epidemiologists follow:

1. Closed cohorts
 A closed cohort is one with a fixed membership
 Once it is defined and follow-up begins, no one can be added to a closed
cohort

[Link] cohorts
 An open cohort, which is also referred to as a dynamic cohort, can take on
new members as time passes.
45
 Incidence cohort Vs. Prognostic (clinical)
Incidence Cohort Study
• To assess incidence of disease
• To identify risk factors for disease onset
• Incidence greater in exposed than non-exposed?
Prognostic Cohort Study
• Follow diseased cohort to assess factors associated with outcome
(recovery or death)
• Goal is to identify explanatory/prognostic factors of those factors
helped to the dev’t of the disease.

46
 Analysis of cohort studies

Compare groups to check similarity at baseline

Calculate incidence of the outcome for exposed and non-exposed

group
Incidence rates are usually calculated by dividing the number of
new events in the follow up period by the appropriate denominator,
based on the size of the population at risk.
Estimate risk (relative risk)
47
Incidence rate in cohort study

48
49
 Advantage of cohort study

⸙Helps to understand the natural history of a disease

⸙Provide clear temporal relationship b/n exposure and outcome
⸙Since information is collected longitudinally it is less prone to bias
⸙Optimal for the study of rare exposures
⸙Can examine multiple effects of a single exposure
⸙Minimizes bias in ascertainment of exposure and outcome

50
 Disadvantage of cohort study
⸙Inefficient in the evaluation of rare disease
⸙Can’t study the effect of multiple exposures at a time
⸙Inefficient in the evaluation of disease with long latent period (for the
prospective type)
⸙Expensive and time consuming (for the prospective type)
⸙Loss to follow-up (for the prospective type)
⸙The exposure might not be ‘fixed exposure’
51
Comparison of case control and cohort

Case control Cohort

52
 2. Experimental/interventional study
⸎ An experimental study (trial) investigates the role of some
agent/intervention in the prevention or treatment of a disease.

⸎ The investigator assigns individuals to two or more groups that either

receive or don’t receive the agent/intervention.

⸎ The group that is allocated the agent under study is called the
treatment/intervention group, and the group that is not allocated the
agent under study is called the comparison group.

53
 Cont’d…

The quality of "gold standard" in intervention studies can be achieved

through :
• Randomization
• Use of placebo
• Double Blinding

 Randomization: random allocation of both intervention and control groups

by lottery or random number table.
54
 Cont’d…

Blinding - is when the observers and/or subjects are kept ignorant as

to the group to which the subjects are assigned
⸙Open/Unblind = all know which intervention a patient is receiving.
⸙Single blind = subjects are ignorant
⸙Double blind = health care giver and subject are ignorant
⸙Triple blind = health care giver, subject and analyst are ignorant

55
 Cont’d…
Placebo - an inert agent indistinguishable from the active treatment.

※ Use of placebo minimizes bias in the ascertainment of both subjective

disease outcomes and side effects.

※ Have psychologic benefit of receiving a treatment (can have a powerful

effect)

※ When to use placebo as comparison:

※ If there is no standard treatment for the condition being studied

56
 Classification of experimental study

Based on population
Clinical trial - usually performed in clinical setting and the subjects
are patients.

Field trial- used in testing medicine for preventive purpose and the
subjects are healthy people.

Community trial - unit of the study is group of people/community.

E.g. fluoridation of water to prevent dental caries.

57
Based on design:

[Link] trial: no control group and control will be past experience

(history)

[Link]-randomized controlled trial: There is control group but allocation into

either group is not random

3. Randomized controlled trial: There is control group and allocation into

either group is randomized
• Individual randomized controlled trial: Randomization is at individual
level
• Cluster randomized controlled trial: The randomization is at cluster level
58
Cont’d…
Based on level (phase I-IV) for new drug trials only:
Phase I:
• Trial on few subjects (20-80)
• 1st experiment in human for new drug, schedule, or combination
• Primary concern: Safety
• Goal: define the maximum tolerated dose (MTD) in a dose-escalation
study
Phase II:
• Small randomized, controlled, blinded (100-300)
• Tests tolerability and different doses
• E.g., optimal dosage without side effects
• Applied to patients with relevant illness
• Goal - Identify suitable formulation of drug 59
Cont’d…
Phase III
• Referred to as clinical trial
• Trial on large number of subjects (1000+) with therapeutic dose to
evaluate efficacy of drug and side effects
• Usually randomized, blinded, controlled trial
• If successful, licensed and marketed
Phase IV
• Post marketing surveillance for long term effects.
• Large studies after approval of drug
• Often observational, study long-term effects

60
Fig. Schematic display of experimental study 61
Cont…

Uncontrolled trials

• The new intervention is studied without any direct comparison with a

similar group of patients on more standard therapy

• Problems of uncontrolled studies are:

-biased selection of participants

-biased assessment of outcomes

Cont…
Non randomized concurrent controls
• Non randomized methods are used to allocate participants to
intervention or control group
• Systematic allocation - e.g. date of birth, date of
presentation
• Judgement allocation – investigator or participant is allowed
to exercise judgement in allocation
• Major problem is predictability of allocation group,
especially by investigator
Cont…
Randomized concurrent controls

• An experimental design used to evaluate drugs and

health interventions

• Subjects should be allocated to treatment group

according to some chance mechanism

• RCT is a research activity that involves the

administration of a test regimen to humans to evaluate
its safety, efficacy, effectiveness
Main steps in RCT
1. Identify new drug/intervention/prevention

2. Identify comparison –

Example, standard treatment versus placebo (Control v

intervention group)

3. Define eligible patient population/ exclusions (i.e the

sampling frame)

4. Define the outcomes and how to assess them

5. Write the protocol 65

cont…

6. Obtain research ethics committee approval

7. Recruit and consent required sample of patients

8. Randomize to treatment, then treat

9. Follow-up and compare/analyze outcome data

10. Publish/disseminate findings

66
 Challenges of experimental study

⸙Ethical issues: Ethical considerations prevent evaluation of many

treatments or procedures using an interventional strategy.

⸙Feasibility/practicability: Getting adequate subjects to be enrolled into

the study is not easy.

⸙Cost: In most of the cases experimental studies are vey expensive.

⸙Non-compliance: When study subjects are expected to take medication

for long period of time non-compliance can be a challenge to the study.
67
 Analysis in Interventional studies

⸎Similar to cohort studies

⸎Compare the rates of the outcome of interest in the treated group(s) and
the corresponding rates in the comparison group(s)

⸎The roles of chance, bias, and confounding must be evaluated

⸎Compare the relevant characteristics of the randomized treatment and

comparison groups to assess balance is achieved

⸎This comparison should always be presented as one of the first tables in

the report of the study findings 68
cont…

⸎The exclusion of any randomized patients from the analysis can lead to
biased results

⸎Noncompliance may be related to factors that also affect the risk of the
outcome under study

⸎Thus, analyze by intention to treat-in other words, “once randomized,

always analyzed”

⸎Those who are no longer complying with the study regimen should
continue to provide all follow-up information whenever possible, or at the
very least, their vital status should be ascertained 69
70
Thank you !!!

71