Reduction of Effect Estimate Bias in Genomewide Studies by Resampling

• Activity Number: 170
• Type: Invited
• Date/Time: Monday, August 8, 2005 : 2:00 PM to 3:50 PM
• Sponsor: SSC
• Author(s): Shelley B. Bull*+ and Lei Sun and Longyang Wu
• Companies: University of Toronto and University of Toronto and Samuel Lunenfeld Research Institute
• Keywords: linkage analysis ; genetic effect estimates ; selection bias ; statistical genetics ; bootstrap ; cross-validation

Abstract

The reliability of gene detection, the accuracy of locus-specific effect estimates, and failure to replicate initial claims of linkage or association have emerged as major concerns in genome-wide studies. While multiple testing methods are useful to control genome-wide type I error, they do not address the bias introduced into genetic-effect-parameter estimates by use of strict significance criteria. Some authors have argued that valid gene (locus)-specific parameter estimates can only be obtained in an independent sample---or they have suggested the strategy of sample splitting. Statistical resampling techniques such as crossvalidation and the bootstrap have been successfully employed to address overfitting and variable selection bias in prognostic prediction models in clinical settings and to obtain accurate estimates of classification error in microarray gene expression studies. We show how to tailor these techniques to effect estimation in genomewide studies. Under a simple model, we derive analytically the upward bias of the naive estimator and the loss of efficiency due to sample splitting and propose simple resampling-based estimators that can be applied to the original sample.