A1753
Title: Generalized method of moments for semiparametric transformation models of recurrent events with informative censoring
Authors: Chang-Yu Tsai - National University of Kaohsiung (Taiwan) [presenting]
Yu-Jen Cheng - National Tsing Hua University (Taiwan)
Abstract: Semiparametric transformation models for recurrent events with a shared frailty variable are considered, allowing for dependence between the event process and censoring. Unlike standard shared frailty proportional rate models, this framework relaxes the proportionality assumption and allows the rate functions to vary flexibly across covariates over time. Motivated by the decomposition of the rate function into shape and size components, an inverse-rate weighting approach and a generalized method of moments framework are developed that combine information from different components of the rate function to improve efficiency. Large-sample properties are established, finite-sample performance is evaluated through simulations, and practical utility is demonstrated using a real dataset.
