JSM 2005 - Toronto

Abstract #304371

This is the preliminary program for the 2005 Joint Statistical Meetings in Minneapolis, Minnesota. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 7-10, 2005); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.



The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

The Program has labeled the meeting rooms with "letters" preceding the name of the room, designating in which facility the room is located:

Minneapolis Convention Center = “MCC” Hilton Minneapolis Hotel = “H” Hyatt Regency Minneapolis = “HY”

Back to main JSM 2005 Program page
Legend: = Applied Session, = Theme Session, = Presenter
Activity Number: 325
Type: Contributed
Date/Time: Tuesday, August 9, 2005 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistical Computing
Abstract - #304371
Title: Finding Important Covariates with Survival Forests
Author(s): Van Parsons*+ and Thu Hoang
Companies: National Center for Health Statistics and Université René Descartes
Address: 3311 Toledo Rd Rm 3219, Hyattsville MD 20782, 20782, United States
Keywords: tree ensembles ; survival analysis ; bootstrap
Abstract:

Tree-based survival models are an alternative to the commonly used Cox proportional hazard models. Survival forests (SF) are ensembles of survival trees. Each tree is grown on a bootstrap sample and an estimator of the survival function is obtained using both the tree and the complementary sample. Individual trees produce unbiased, but highly variable, survival predictors; averaging such predictors improves their performance. The SF method appears to work well when the sample size is larger than the number of covariates (i.e., the "n >p" case). However, applications of SF on genomic data typically fall into the "p>>n" case. We have experienced several challenges when using SF on microarray data. For example, heavy censoring or large numbers of unimportant covariates may affect the SF predictor's performance. We discuss some SF tuning parameters and general strategies to help overcome these problems.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2005 program

JSM 2005 For information, contact jsm@amstat.org or phone (888) 231-3473. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2005