|
Activity Number:
|
401
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
IMS
|
| Abstract - #303077 |
|
Title:
|
Robust Model-Free Probability Estimation
|
|
Author(s):
|
Yichao Wu*+ and Hao (Helen) Zhang and Yufeng Liu
|
|
Companies:
|
North Carolina State University and North Carolina State University and The University of North Carolina at Chapel Hill
|
|
Address:
|
Department of Statistics, Raleigh, NC, 27695,
|
|
Keywords:
|
model-free ; multi-category response ; probability ; robust
|
|
Abstract:
|
Logistic regression was invented to handle problems with a binary response and provides an estimator of the conditional probability. For the extension to the case with a multi-category response, parametric methods include baseline logit and cumulative logit models. However, there is a limited literature on nonparametric methods. In this work, we propose a robust model-free probability estimation scheme. Our method is justified by providing asymptotic consistency and favorable comparison to existing methods.
|
