Regression Diagnostics for Current Status Data Using the Odds-Rate Model

• Activity Number: 411
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 2:00 PM to 3:50 PM
• Sponsor: International Chinese Statistical Association
• Author(s): Chi-Chung Wen*+
• Keywords: Goodness of fit ; Case I interval-censored ; Odds-rate model

Abstract

Regression diagnostics that assess the adequacy of a regression model for observed data should be conducted before the regression analysis. Several regression diagnostic methods have been established for complete or right censored failure time data, but there are not many approaches available for current status failure time data. In this study, we develop a diagnostic method for assessing the proportional hazards (PH) and proportional odds (PO) assumptions with current status data under the odds-rate (OR) model (Scharfstein, Tsiatis, and Gilbelt 1998). The OR model includes the PH and PO models as special cases and hence offers a semiparametric likelihood ratio test to evaluate the PH and PO assumptions for current status data. We provide a stable and efficient computation method for proposed estimation, verify the asymptotic theories of the likelihood ratio tests via simulations, and illustrate the proposed method with three real data analyses. This is a joint work with Hsiao-Han Hung.