|
Activity Number:
|
186
- Contributed Poster Presentations: International Chinese Statistical Association
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 29, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
International Chinese Statistical Association
|
|
Abstract #305235
|
|
|
Title:
|
A Rank-Based Regression Tree for Subgroup Identification
|
|
Author(s):
|
Xiang Peng* and Huixia Judy Wang
|
|
Companies:
|
The George Washington University and The George Washington University
|
|
Keywords:
|
quantile treatment effect;
rank score;
recursive partitioning;
regression tree;
subgroup analysis
|
|
Abstract:
|
One primary goal of subgroup analysis is to identify subgroups of subjects with differential treatment effects. Existing methods have focused on the mean treatment effect, and thus are ineffective when the two distributions differ in scales or only in the upper or lower tail. We develop a new rank-based regression tree method for subgroup identification. The new method uses rank score tests to partition the regression tree and is free of selection bias. In each node, the population difference is summarized by a generalized quantile treatment effect. We show that the proposed method gives more accurate or comparative subgroup identification than existing methods under various models.
|
Authors who are presenting talks have a * after their name.
