Semiparametric Regression Analysis of Interval-Censored Competing Risks Data

• Published in: Biometrics Vol. 73; no. 3; pp. 857 - 865
• Main Authors: Mao, Lu, Lin, Dan-Yu, Zeng, Donglin
• Format: Journal Article
• Language: English
• Published: England Wiley-Blackwell 01.09.2017; Blackwell Publishing Ltd
• Subjects: algorithms; biometry; Computer Simulation; Cumulative incidence; Data processing; DISCUSSION PAPER; Distribution functions; Economic models; Empirical analysis; Failure; Hazards; HIV; HIV infections; Human immunodeficiency virus; Human immunodeficiency virus 1; Interval censoring; Likelihood Functions; Maximum likelihood estimation; Models, Statistical; Nonparametric maximum likelihood estimation; Normality; Parameter estimation; Regression Analysis; Regression models; Risk; Self‐consistency algorithm; Time‐varying covariates; Transformation models; Cumulative incidence; Interval censoring; Time-varying covariates; Nonparametric maximum likelihood estimation; Self-consistency algorithm; Transformation models
• ISSN: 0006-341X; 1541-0420; 1541-0420
• DOI: 10.1111/biom.12664

Interval-censored competing risks data arise when each study subject may experience an event or failure from one of several causes and the failure time is not observed directly but rather is known to lie in an interval between two examinations. We formulate the effects of possibly time-varying (external) covariates on the cumulative incidence or sub-distribution function of competing risks (i.e., the marginal probability of failure from a specific cause) through a broad class of semiparametric regression models that captures both proportional and non-proportional hazards structures for the sub-distribution. We allow each subject to have an arbitrary number of examinations and accommodate missing information on the cause of failure. We consider nonparametric maximum likelihood estimation and devise a fast and stable EM-type algorithm for its computation. We then establish the consistency, asymptotic normality, and semiparametric efficiency of the resulting estimators for the regression parameters by appealing to modern empirical process theory. In addition, we show through extensive simulation studies that the proposed methods perform well in realistic situations. Finally, we provide an application to a study on HIV-1 infection with different viral subtypes.