Premium
Marginal screening of 2 × 2 tables in large‐scale case‐control studies
Author(s) -
McKeague Ian W.,
Qian Min
Publication year - 2019
Publication title -
biometrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.298
H-Index - 130
eISSN - 1541-0420
pISSN - 0006-341X
DOI - 10.1111/biom.12957
Subject(s) - bonferroni correction , permutation (music) , multiple comparisons problem , computer science , false discovery rate , statistical hypothesis testing , resampling , null hypothesis , statistical power , monte carlo method , type i and type ii errors , scale (ratio) , statistics , mathematics , data mining , artificial intelligence , biology , genetics , acoustics , gene , physics , quantum mechanics
Summary Assessing the statistical significance of risk factors when screening large numbers of 2 × 2 tables that cross‐classify disease status with each type of exposure poses a challenging multiple testing problem. The problem is especially acute in large‐scale genomic case‐control studies. We develop a potentially more powerful and computationally efficient approach (compared with existing methods, including Bonferroni and permutation testing) by taking into account the presence of complex dependencies between the 2 × 2 tables. Our approach gains its power by exploiting Monte Carlo simulation from the estimated null distribution of a maximally selected log‐odds ratio. We apply the method to case‐control data from a study of a large collection of genetic variants related to the risk of early onset stroke.