B1397
Title: Pseudo-observation regression for sequentially truncated data
Authors: Jing Qian - University of Massachusetts, Amherst (United States) [presenting]
Erik Parner - Aarhus University (Denmark)
Morten Overgaard - Aarhus University (Denmark)
Rebecca Betensky - New York University (United States)
Abstract: In observational cohort studies with complex sampling schemes, truncation arises when the time to event of interest is observed only when it falls below or exceeds another random time, i.e., the truncation time. In more complex settings, observation may require a particular ordering of event times; this extension of the traditional paradigm is referred to as sequential truncation. A previous study proposed nonparametric and semiparametric maximum likelihood estimators for the distribution of the event time of interest in the presence of sequential truncation under two truncation models. Methods for regression modelling are presented in this complex setting using the tool of pseudo-observations (PO). POs are jackknife-like constructs that estimate an individual's contribution to an estimand. They are attractive in this setting because they obviate the need to directly account for the sequential truncation in the regression model of interest. Importantly, they may not be used when the truncation depends on the covariates that explain the time to the event of interest; in this case, a modified PO approach is available. Both the Cox and accelerated failure time (AFT) models are considered. The approach is evaluated in simulation studies and application to an Alzheimer's cohort study.