Consider the following table of the number of individuals with each genotype at
ID: 174769 • Letter: C
Question
Consider the following table of the number of individuals with each genotype at a locus who do (cases) or do not (controls) have restless leg syndrome in a population of residents of Atlanta. Assume that the p-value associated with the test is <10-10.
AA AG GG
Cases 2823 5041 2110
Controls 4976 9951 5028
State which allele is protective and compute the odds ratio for the effect of the AA genotype relative to the GG genotype. If the sample is representative of the Atlanta population, suggest one reason why the association may be a false positive finding. State what you would do statistically to overcome the potential problem.
Explanation / Answer
A is the risk allele and G is the protective allele.
Odd RatiosAA = odds(disease | AA) / odds(disease | GG) = 2823*5023 / 2110* 4976 = 1.35.
The strongest factor associated with the false positive study outcome was if the study had a specific priori hypothesis. Factors that decreased the odds ratio of a false positive outcome included observing a dose-effect relationship.
To overcome false positive, simple odds ratios were calculated to investigate the crude associations between the study characteristics and the status of the study. Statistically, multiple logistic regression was used to adjust the individual odds ratios for the effect of other variables dependency of false positivity.