|
Activity Number:
|
160
- SPEED: Biometrics
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 31, 2017 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
|
Abstract #323791
|
View Presentation
|
|
Title:
|
Comparison of Treatment Regime Estimation Methods Incorporating Variable Selection: Lessons from a Large Simulation Study
|
|
Author(s):
|
Adam Ciarleglio* and Eva Petkova and Thaddeus Tarpey and Zhe Su and R. Todd Ogden
|
|
Companies:
|
Columbia and New York University School of Medicine and Wright State University and New York University School of Medicine and Department of Biostatistics, Columbia University
|
|
Keywords:
|
Treatment regime ;
variable selection ;
precision medicine ;
effect modification ;
high-dimensional data
|
|
Abstract:
|
Increased emphasis on precision medicine has prompted the development of myriad statistical methods for both identifying moderators of treatment effect and estimating optimal rules for selecting treatment. Though many of these methods are promising, they do not perform equally well in all settings. Currently there is little guidance as to which method one should choose to use in practice. In this talk, we present results from a large simulation study in which we compare different recently-developed methods that simultaneously select important moderators and estimate treatment decision rules in a wide variety of realistic settings. The methods are compared with respect various performance metrics and guidelines for selecting methods to use in practice are proposed.
|
Authors who are presenting talks have a * after their name.
