Abstract:
|
The use of linear mixed models (LMMs) in genome-wide association studies (GWAS) is now widely accepted because LMMs have been shown to be capable of correcting for several forms of confounding due to genetic relatedness, such as population structure and familial relatedness. On the other hand, gene and environment (GE) interactions play a pivotal role in determining the risk of human diseases. Conventional parametric models such as linear models and generalized linear models may not reflect the true nonlinear GE interaction. In this paper, we propose a semiparametric mixed model to capture possible nonlinear GE interactions in GWAS. We further propose a profile quasi restricted maximum likelihood estimation method for the semiparametric mixed model. For these profile estimators, asymptotic consistency and normality are established. Moreover, we develop Rao-score-type test procedures based on the profile estimation to check significance of genetic factors. Both simulation studies and an empirical example are presented to illustrate the use of our proposed models and methods.
|
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.