JSM 2005 - Toronto

Abstract #302519

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: 498
Type: Invited
Date/Time: Thursday, August 11, 2005 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Epidemiology
Abstract - #302519
Title: Extreme Regression Models for Prognosis
Author(s): Michael LeBlanc*+
Companies: Fred Hutchinson Cancer Research Center
Address: 1100 Fairview Ave N, Seattle, WA, 98109,
Keywords: Prognostic ; Regression ; Survival
Abstract:

Extreme regression is a new statistical technique for finding patient subsets with either very good or very poor prognoses. The regression method specifies a model class composed of extrema (maximum and minimum) functions of the predictor variables. This class of models allows for simple function inversion and results in level sets of the regression function that can be expressed as interpretable decisions based on individual predictors. In contrast to Cox regression, which results in predictions based on linear combinations of variables, extreme regression results in groups based on intersections or unions of simple statements involving single covariates (e.g., (x1 > 3.5 AND x2 < = 7) OR (x3 > 5 AND x4 > 2.3)). This is similar in spirit to tree-based regression methods, but allows for calibration of the outcome groups. In this paper, we develop an estimation algorithm and show how the method leads to a graphical representation of a sequence of nested decision rules as the target outcome is varied. We present clinical applications for describing patient characteristics associated with a good or poor outcome.

  • 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