|
Activity Number:
|
144
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #310385 |
|
Title:
|
Variable Selection for Optimal Decisionmaking
|
|
Author(s):
|
Lacey Gunter*+ and Susan Murphy and Ji Zhu
|
|
Companies:
|
University of Michigan and University of Michigan and University of Michigan
|
|
Address:
|
439 West Hall, Statistics Department, Ann Arbor, MI, 48109,
|
|
Keywords:
|
variable selection ; decision making ; prediction
|
|
Abstract:
|
This talk will discuss variable selection for decision making. Current variable selection techniques were developed for use in a supervised learning setting where the goal is optimal prediction of the response. These techniques often leave behind small but important interaction variables that are critical when the ultimate goal is optimal decision making rather than optimal prediction. While prediction represents a first step in finding optimal decisions, we will point out some key differences between prediction and decision making applications. We will present a new technique designed specifically to find variables that aid in decision making and demonstrate the utility of this technique on both simulated data and real world data from a randomized controlled trial for the treatment of depression.
|
