Regularized quantile regression under heterogeneous sparsity with application to quantitative genetic traits

摘要: Genetic studies often involve quantitative traits. Identifying genetic features that influence traits can help to uncover the etiology of diseases. Quantile regression method considers conditional quantiles response variable, and is able characterize underlying structure in a more comprehensive manner. On other hand, high-dimensional genomic features, may be heterogeneous terms both effect sizes sparsity. To account for potential heterogeneity, including sparsity, regularized quantile introduced. The theoretical property proposed investigated, its performance examined through series simulation studies. A real dataset analyzed demonstrate application method.