Professional Documents
Culture Documents
STUDY DESIGN
Optional:
1. Bonita et al., 2006. Basic
Epidemiology (WHO)
2. Webb and Bain, 2011. Essential
Epidemiology
ILLUSTRATION:
Parikesit, a cardiologist, delivered a community
health education related to coronary heart disease
(CHD).
He explained that from 100 patients with CHD, 80
of them were having high blood pressure. He then
concluded that hypertension is the major risk
factor for CHD.
Disease (+)
Unexpose
d
Disease (-)
Retrospective
Direction of Inquiry
Time
Risk Factor
(+) Onset of
Risk Factor (- Cases study
) Study
Population
Case (-)
Risk Factor
(+)
Control
Risk Factor (-
)
Direction of Inquiry
CASE CONTROL STUDIES:
To study the risk of ‘cause and effect’ or to
estimate the relative risk
Retrospective study
D. Condition
Cases selected should be representative
toward the population where they taken
from
CONTROL
Examples:
1. Normal weight babies
2. People without CHD
Control
Selection
CONDITION :
1. Representative to population
2. Comparable to cases group (except
for disease of interest and risk factors)
METHODS :
1. Matching or no matching
2. Sampling random or non random
Exploring Risk Factors/Exposure
Data
Condition:
Methods used for cases group MUST
exactly the same to control groups
(comparable between cases and
control)
Method(s):
Medical Record
Interview CAUTION of Recall Bias!!
DATA ANALYSIS
THE ESTIMATION OF RELATIVE RISK (RR)
ODD RATIO (OR)
Plasenta previa 12 56 68
Tdk plasenta 9 59 68
previa
Case C D C+D
Unexposed
Total A+C B+D n
OR = B/C
95%CI = (OR) exp[+1.96 1/B+1/C]
OR Interpretation
A study wanting to explore the relationship
between smoking and lung cancer. From a
case control study were found OR was 2,5.
Information Bias
Measurement error
CASE CONTROL STUDIES:
Advantages Limitations
Efficient for the study of rare diseases Risk of disease can not be estimated
directly
Efficient for the study of chronic diseases Not efficient for the study of rare
exposure