Epidemiologic Study Design

Case - Control
Dr. Mufuta Tshimanga
Professor – Public Health Medicine
 Learning Objectives
When you have completed this session
you will be able to:
• Describe the differences between and
descriptive and analytic studies
• Describe the differences between and
experimental and observational studies
• Describe two major types of
observational studies, including their
advantages and disadvantages
 Epidemiological studies
Populations Ecologic

Descriptive Case-series
Individuals
Cross-sectional

Case-control

Observational
Prospective
Cohort
Analytical Retrospective

Intervention Clinical trials

3
 Descriptive Studies
• Populations (correlational or ecological
studies)

• Individuals
– Case reports
– Case series
– Cross-sectional surveys
 Analytic Studies
• Experimental (intervention or clinical trial)

• Observational
– Cohort studies (retrospective or prospective)
– Case-control studies
 Analytic Studies – Hallmark

Q. What is the hallmark feature that

distinguishes a descriptive study
from an analytic study?
 Analytic Studies – Hallmark
Q. What is the hallmark feature that
distinguishes a descriptive study from
an analytic study?

A. Comparison Group
Case-Control Studies
 Introduction
• Most frequently undertaken analytical
epidemiological studies
• Practical approach for identifying risk
factors for rare diseases
• Best suited to the study of diseases for
which medical care is sought
 Design
• Selection of cases(disease) and controls(no
disease)
• Exposure status is unknown
• Retrospective design
• Select cases after the diagnostic criteria and
definition of the disease is clearly established
• Study cases should be representative of all
cases
• Study may not include all cases in the population
 Case-Control Study

Exposure
Disease
? (Case)

?
No disease
(Control)

Retrospective Nature
 Source population

Exposed
Unexposed
 Source population

Exposed
Cases
Unexposed
 Source population

Exposed
Cases
Unexposed

Controls
 Source population

Exposed
Cases
Unexposed

Controls =
Sample of the denominator
Controls Representative with
regard to exposure
 Major Steps in case-control study

• Define and select cases

• Select controls
• Ascertain exposures
• Compare exposure in cases and
controls
– proportions/odds ratios ....
• Test any differences for statistical
significance
 Observation

• Start with cases

• Are any observed exposures higher
than expected ?
• To find this out we need a
comparison group
• This group are known as controls
 What is a control ?
• A control is as like a case as possible
except that they do not have the disease
(outcome) in question.
• They must have the same opportunity for
exposure as a case and must be subject to
the same inclusion and exclusion criteria.
• No one control group is optimal for all
situations
• Scientific, economic and practical
considerations
Principles of Control Selection
• From same study base (target population) as
cases
• Selected independently of exposure status!!
• If they had developed illness, they would
have been a case
• Comparable information to cases
• Multiple control groups can be used to
increase statistical power
 General Population Controls

• Advantages
– If all cases in general population known
direct calculation of risk
• Disadvantages
– Costly and time consuming
– Sampling frame
– Non-participation
 Neighborhood Controls
• Advantages:
– Inexpensive,efficient
– Matched for potentially confounding
variables
• Disadvantages
– Exposure related to neighborhood
– Potential bias
 Hospital Controls
• Advantages:
– Convenient
– Come from same catchment area
– Cooperation
• Disadvantages:
– Control disease may be linked to exposure
– Hospitalized controls differ from general
population i.e different from healthy
individuals
 Spouses & Friend Controls
• Advantages
– Convenient
– More like the general population
• Disadvantages
– Bias (selection)
– Friends may share same exposure
 Number of controls
• Availability

• Ratio controls / cases

• Trade-off: cost vs. power

• Decision based on power calculation

• More than one control group?

 Nested case-control study
• Initial data and or serum, urine or other
specimen obtained
• Subgroup selected as “controls” and
“cases”
• Easier to apply stringent diagnostic
criteria
• Incidence( and/or absolute) risk can be
calculated
 Intuitively….
If the frequency of exposure is higher
among the cases than the controls,

then the incidence will probably be

higher among the exposed than the
non-exposed.
Measure of Association

• Think Odds Ratio (OR)

• Odds ratio
• Cross-product ratio
• Good estimator of risk or rate
ratio, when disease is rare

27
 Probability that an event will happen
Odds=
Probability that the even will not happen

Probability that an event will happen

Odds=
1 - (Probability that the event will happen)

Foot ball game Wins Loose Total

Team A 2884 97116 100000

Probability of winning = 2884 / 100000 = 0.029

Probability of not wining = 97116 / 100000 = 1 - 0.029 = 0.971

Odds of wining = 2887 / 97116 = 0.029/0.971 = 0.030

28
Case-Control – 2-by-2 Table
Case Control
Exposed a b

Unexposed c d
V1 V2

Odds Ratio = ad / bc

29
 Interpreting the Odds Ratio
• Those with CHD…..are 62% more likely
to be smokers than those without HD
• Those with CHD are 1.62 times more
likely to be smokers than those without
CHD
Advantages of Case-control Studies

• Rare diseases
• Several exposures
• Rapidity
• Low cost
• Small sample size
• Available data
• No ethical problem
Disadvantages of Case-control Studies

• No direct calculation of rates and risks

• Temporal relationship exposure-disease
difficult to establish
• Not suitable for rare exposures
• Problems with bias
– Selection of controls
– Recall
 Case-control Study: Issues
 Consistent case definition: mixing
disease conditions can blur the measure
of exposure and disease association

 Should cases represent all persons

developing the disease?

 Generalizability versus Validity?

33
 Case-control Study: Issues
 Clarify temporal sequence between
exposure and disease

 Prevalent cases?

 Incident cases?

 Prevalence = Incidence x Duration 34

 Case-control Study: Issues

 Possible sources of cases

 Hospital-based?

 Population-based registry?

35
 Case-control Study: Issues
 Controls should represent the frequency
of exposure among healthy persons.

 Controls should represent the same

population from which the cases
originated.

 If the controls had developed the disease,

…would this study have detected them?
36
 Case-control Study: Issues
 Possible sources of controls
 Hospital (which diagnoses?)
 Relatives (genetic factors?)
 Friends (social or behavior factors?)
 Neighbors (economic or environmental
factors?)
 General population (difficult logistically)

37
Case-Control Studies –
Summary
 Test hypotheses about disease risk factors /
causes
 Case-control studies
Disease  exposure (cause  effect)
Measure of association = OR
Quick, less expensive
Have potential for selection and information
bias

38