Activity Number:
|
307
- Advanced Survival Analysis Tools for Statistical Learning from Complex Scientific Studies
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 5, 2020 : 10:00 AM to 11:50 AM
|
Sponsor:
|
Lifetime Data Science Section
|
Abstract #309706
|
|
Title:
|
Flexible Semiparametric Latent Class Analysis of Recurrent Events Outcomes
|
Author(s):
|
Limin Peng* and Wei Zhao and John Hanfelt
|
Companies:
|
Emory University and Emory University and Emory University
|
Keywords:
|
Recurrent events;
latent class;
frailty;
estimating equation
|
Abstract:
|
Recurrent events data collected from clinical follow-up studies contain rich information on the evolvement of survival phenotype over time. Latent class analysis is a useful venue to parsimoniously characterize the heterogeneity in survival phenotype trajectories across the study population of interest. In this work, we propose a new semi-parametric model that sensibly accounts for potential latent subgroups with different recurrent event risk profiles. We develop a robust estimation procedure from adapting the idea of artificial estimating equation technique. We provide rigorous theoretical justifications for the proposed estimators. Our simulation studies suggest good finite-sample performance of the proposed method as well as dramatic gains over benchmarks without accommodating latent classes. We also apply our method to an Alzheimer dataset.
|
Authors who are presenting talks have a * after their name.