Analysis of transformation models with right-truncated data. Issue 2 (4th March 2017)

• Record Type: Journal Article
• Authors: Shen, Pao-sheng; Liu, Yi; Maa, Der-Pyng; Ju, Yeunjyr
• Is Part Of: Statistics. Volume 51:Issue 2(2017)
• Page Start: 404
• Page End: 418
• Publication Date: 2017-03-04
• Subjects: Right-truncation -- semiparametric transformation model -- martingale -- estimating equation -- conditional likelihood; Primary: 62N99 -- Secondary: 62N02; Mathematical statistics -- Periodicals; 519.505
• DOI: 10.1080/02331888.2016.1268617
• Languages: English
• ISSNs: 0233-1888

Abstract

ABSTRACT: In many applications, statistical data are frequently observed subject to a retrospective sampling criterion resulting in right-truncated data. In this article, a general class of semiparametric transformation models that include proportional hazards model and proportional odds model as special cases is studied for the analysis of right-truncated data. We proposed two estimators for regression coefficients. The first estimator is based on martingale estimating equations. The second estimator is based on the conditional likelihood function given the truncation times. The asymptotic properties of both estimators are derived. The finite sample performance is examined through a simulation study.