Variable Selection for Failure Time Data from Stratified Case-Cohort Studies: An Application to a Retrospective Dental Study

• Activity Number: 92
• Type: Invited
• Date/Time: Sunday, August 4, 2013 : 8:30 PM to 10:30 PM
• Sponsor: Korean International Statistical Society
• Author(s): Sangwook Kang*+
• Companies: University of Connecticut

Abstract

Root canal therapy (RCT) is an option to extend the life of a damaged tooth. But even after RCT, teeth still can be lost due to many reasons. In a retrospective dental study, it was of interest to identify factors associated to survival of root canal filled (RCF) teeth. To accomplish this goal, we propose a variable selection procedure for Cox models via a penalization of estimating functions. The proposed method is developed under a stratified case-cohort design, which includes the case-control design considered in the dental study as a special case. An adaptive bridge method along with other penalized regression methods are adapted to appropriately accommodate this study design. Both asymptotic properties and finite sample properties of the proposed methods are investigated. We illustrate our methods to the retrospective dental study data.