Efficient Estimation for Linear Transformation Models with Current Status Data

Abstract

Linear transformation models provide a class of flexible models for regression analysis of failure time data and several methods have been proposed for fitting them to right-censored failure time data (Chen, 2002; Cheng et al., 1995; Yin and Zeng, 2006). This article considers the fitting of these models to current status data, a special type of interval-censored failure time data. We derive the maximum likelihood estimates and their information bound and establish the efficiency of the estimates. Simulation studies show that the approach is appropriate for practical use and an application is given to illustrate the approach.

Keywords:

• Current status data
• Efficient score function
• Information bound
• Linear transformation models

Acknowledgment

The authors would like to thank the editors and the referees for their helpful and constructive comments that greatly improved this article. This work was partly supported by an NSF China Zhongdian Project 11131002, NSFC (No. 10971015), Key Project of Chinese Ministry of Education (No. 309007), and the Fundamental Research Funds for the Central Universities.