Efficient Estimation of Semiparametric Transformation Models for the Cumulative Incidence of Competing Risks.

TitleEfficient Estimation of Semiparametric Transformation Models for the Cumulative Incidence of Competing Risks.
Publication TypeJournal Article
Year of Publication2017
AuthorsMao, Lu, and D Y. Lin
JournalJ R Stat Soc Series B Stat Methodol
Volume79
Issue2
Pagination573-587
Date Published2017 Mar
ISSN1369-7412
Abstract

The cumulative incidence is the probability of failure from the cause of interest over a certain time period in the presence of other risks. A semiparametric regression model proposed by Fine and Gray (1999) has become the method of choice for formulating the effects of covariates on the cumulative incidence. Its estimation, however, requires modeling of the censoring distribution and is not statistically efficient. In this paper, we present a broad class of semiparametric transformation models which extends the Fine and Gray model, and we allow for unknown causes of failure. We derive the nonparametric maximum likelihood estimators (NPMLEs) and develop simple and fast numerical algorithms using the profile likelihood. We establish the consistency, asymptotic normality, and semiparametric efficiency of the NPMLEs. In addition, we construct graphical and numerical procedures to evaluate and select models. Finally, we demonstrate the advantages of the proposed methods over the existing ones through extensive simulation studies and an application to a major study on bone marrow transplantation.

DOI10.1111/rssb.12177
Alternate JournalJ R Stat Soc Series B Stat Methodol
Original PublicationEfficient estimation of semiparametric transformation models for the cumulative incidence of competing risks.
PubMed ID28239261
PubMed Central IDPMC5319638
Grant ListR37 AI029168 / AI / NIAID NIH HHS / United States
R01 AI029168 / AI / NIAID NIH HHS / United States
R01 GM047845 / GM / NIGMS NIH HHS / United States
R01 CA082659 / CA / NCI NIH HHS / United States
P01 CA142538 / CA / NCI NIH HHS / United States