A0204
Title: Regression analysis of semiparametric Cox-Aalen transformation models with partly interval-censored data
Authors: Xi Ning - Colby College (United States)
Yanqing Sun - University of North Carolina at Charlotte (United States)
Yinghao Pan - University of North Carolina at Charlotte (United States) [presenting]
Peter Gilbert - University of Washington and Fred Hutchinson Cancer Research Center (United States)
Abstract: Partly interval-censored data, comprising exact and interval-censored observations, are prevalent in biomedical, clinical, and epidemiological studies. A flexible class of so-called Cox-Aalen transformation models is introduced for regression analysis of such data. These models offer a versatile framework by accommodating multiplicative and additive covariate effects within a transformation while allowing for potentially time-dependent covariates. Moreover, this class of models includes many popular models, such as the Cox-Aalen and transformation models, as special cases. To facilitate efficient computation, a set of estimating equations is formulated, and an expectation-solving (ES) algorithm that guarantees stability and rapid convergence is proposed. Under mild regularity assumptions, the resulting estimator is shown to be consistent and asymptotically normal, with its variance consistently estimated by weighted bootstrap. Finally, the proposed method is evaluated through comprehensive simulations and applied to analyze data from a randomized HIV/AIDS trial.
