Case Control and OR Flashcards
Case-Control Study
Retrospective study where an investigator compares proportion of cases exposed to a risk factor with proportion of controls exposed to a risk factor.
Case-Control Design
- Cases: subjects with the disease
- Controls: subjects without the disease
- Investigators look backward in time to identify the presence or absence of exposure/risk factors among cases and controls
Case-Control Advantages
- Good for disease with long latency
- Cost and time efficient
- Good for rare diseases
- Allows evaluation of multiple risk factors
Case-Control Disadvantage
BIAS
- Selection bias
- Information Bias: recall, misclassification, interviewer
- Do not allow calculation of incidence and RR
Hospital-based Cases
- Subjects with the disease identified through a medical treatment facility
- Relatively easy, inexpensive
Population-based Cases
- Select all persons with the disease or select a random sample from the general population
- Avoid biases arising from use of a particular medical facility
- More difficult logistically and more expensive
Hospital Controls
Patients in same hospital being treated for diseases other than cases
General Population Controls
Random-digit telephone dialing, voting lists, population registers
Special Controls
Friend, neighbors, relatives of cases
Hospital Control Advantages
- Easily identified and readily available
- Comparable to cases in their accuracy in reporting past exposure
- Subject to the same intangible selection factors that influence admission to a particular facility
- More willing to cooperate
Hospital Controls Disadvantages
- Differ from healthy individuals
- Might not accurately represent the exposure distribution in the general population
General Controls Advantages
-Assures the greatest level of comparability to cases
General Controls Disadvantages
- Costly and time consuming
- Harder to contact
- Harder to recruit
- People who can be contacts during the day may be systemically different
- Potential recall bias
Special Controls Advantages
- Healthy individuals
- More likely to cooperate
- Share similar risk factors as cases - control for confounding
Special Controls Disadvantages
-Share similar risk factors: underestimation of association
Measures of Association
- Can ONLY calculate odds ratio
- Odds ratio: ratio between the odds of exposure in the cases and the odds of exposure controls
- OR: odds of exposure among cases/odds of exposure among controls
- OR: AD/BC
- OR < 1 = protective effect
- OR = 1: no association
- OR > 1 = positive association
Matching
- Process of selecting controls so that they are similar to the cases in certain characteristics
- Group matching: matching certain characteristics (age, gender, etc.)
- Individual: should a control for each case on a matching basis
Matching Advantages
– Straightforward
– Effective
– Necessary for factors for which there would otherwise be insufficient overlap between the study groups in a random sample
Matching Disadvantages
– Difficult, expensive, and time-consuming to find a comparison subject
– Limits sample size
– Require a special type of statistical analysis (McNemar’s, conditional logistic regression)
– Cannot evaluate the effect of the matched factors
Evaluating Case-Control Studies
- Were the cases and control from a common population
- What standard was used to defined cases
- Are the controls truly free of the outcome
- How was exposure determined, was same applied for case and control
- Were potential confounders taken into consideration
