|
Activity Number:
|
170
- Nonparametric Methods for Longitudinal and Survival Data
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 31, 2017 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #324066
|
View Presentation
|
|
Title:
|
Nonparametric Group Sequential Methods for Combined Endpoints of Recurrent and Terminal Events from Multiple Follow-up Windows
|
|
Author(s):
|
Meng Xia* and Susan Murray and Nabihah Tayob
|
|
Companies:
|
University of Michigan and University of Michigan and The University of Texas MD Anderson Cancer Center
|
|
Keywords:
|
Recurrent events ;
Survival analysis ;
Restricted means ;
Group sequential monitoring ;
Stopping rules ;
Nonparametric
|
|
Abstract:
|
In this research, we take a fresh look at group sequential methods applied to two-sample tests of survival data with combined endpoints of recurrent and terminal events and propose an alternative method of defining and evaluating treatment benefit in this context. As in Tayob and Murray (2014) we re-purpose traditional survival time data collected over long follow-up periods into a sequence of (potentially overlapping) short-term follow-up windows, each holding information on short-term outcomes of interest. This corresponding test statistic gives an alternative understanding of treatment benefit with increased power to detect treatment effects as an added bonus. As part of developing group sequential methods for this type of analyses, we make recommendations for asymmetric error spending approaches that differentially limit the chances of stopping incorrectly for perceived efficacy versus perceived harm attributed to the investigational arm of the trial. Recommendations for how to choose proper group sequential stopping boundaries in different research settings is given, with supporting simulations and an example.
|
Authors who are presenting talks have a * after their name.
