Biostats 6 Flashcards
Case-Control Studies. How are subjects selected?
Subjects are selected on the basis of whether they do (cases) or do not (controls) have a particular disease under study
T or F. Case-Control Studies evaluate an association between exposure and disease (not a cause)
T.
What are the strengths of a case-control study?
Quick, inexpensive
Appropriate for diseases with long latent periods
Optimal for study of rare diseases
Evaluate multiple etiologic factors of one disease
What are the weaknesses/limitations of a case-control study?
Inefficient for study of rare exposures
Inability to calculate incident rates directly
Questionable temporal relationship between exposure and disease
Prone to bias (selection, recall, interviewer)
What is Odds Ratio (OR) in relation to case-control studies?
Odds of exposure for cases divided by odds of exposure for control OR is estimate of Relative Risk (RR) when disease is rare
Odds ratio = ad/bc (Cross-product, shortcut, all you need
to know)
Deriving OR for a cross-plot.
Odds of case exposure=Exposed cases/all cases divided by Non-exposed cases/all cases
= a/a+b divided by b/b+a
= a/b
Odds of control exposure= c/d
Odds ratio=odds of case exposure/odds of control exposure = a/b divided by c/d
Odds ratio = ad/bc (Cross-product, shortcut, all you need
to know)*
Interpretation of OR and RR
- Reference is 1
- If OR or RR >1 increased risk
- If OR or RR less than 1, decreased risk
What is a Type I error?
occurs when the null hypothesis is true, but it is incorrectly rejected—(concluding there is a difference when there is actually no difference).
Often a significance level of 0.05 is chosen; then 5% of the time the null will be rejected when it should not be.
What is the level of significance (alpha level)?
Is pre-determined by the investigator; it is the probability of making a Type I error that the investigator is willing to accept.
What is a P-value?
Calculated from the data
Probability that the results are due to chance
If calculated P-value is less than the pre-determined level of significance, then the results are statistically significant, not due to chance, and the null is rejected.
What is Validity?
Degree to which a measurement or study reaches a correct conclusion
What is the difference between internal and external validity?
Internal validity- extent to which the results of the study the truth
External validity- reflect extent to which the results of a study are applicable to other populations, generalizability
What are some types of bias in case-control studies?
selection bias
recall bias
interviewer bias
What is a cohort study?
An observational study in which subjects are sampled based on presence of of a risk factor of interest.
• These subjects are followed over time for the development of a disease or outcome of interest
What are the strengths of cohort studies?
Useful for study of rare exposures
Able to study multiple effects of single exposure
Definite temporal relationship between Exp and Dis
Able to minimize bias in ascertainment of Exposure
Direct calculation of incidence in Exp and non Exp
