CFE 2019: Start Registration
View Submission - CMStatistics
Title: Simultaneous estimation and inference for high dimensional censored quantile regression Authors:  Hyokyoung Grace Hong - Michigan State University (United States) [presenting]
Abstract: Censored quantile regression has emerged as a powerful tool for detecting heterogeneous effects of covariates on outcomes in survival analysis. With the availability of high dimensional data such as molecular biomarkers, it is often of interest to identify heterogeneous effects of these predictors on patients survival. However, to our knowledge, no work has been conducted to estimate and draw inferences on effects of high dimensional predictors within the framework of censored quantile regression. A novel fused estimator is proposed for modeling survival outcomes with high dimensional predictors and a consistent model-free variance estimator via functional delta method and data re-sampling, which lead to simultaneous statistical inferences for all predictors.