|
Activity Number:
|
103
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #309997 |
|
Title:
|
Quantile Regression for Censored Point Processes
|
|
Author(s):
|
Rajeshwari Sundaram*+ and Subhashis Ghoshal
|
|
Companies:
|
National Institute of Child Health and Human Development and North Carolina State University
|
|
Address:
|
6100 Executive Boulevard, NIH, Rockville, MD, 20852,
|
|
Keywords:
|
Recurrent Events ; Censoring ; Survival
|
|
Abstract:
|
Recurrent events data often arise in many longitudinal follow-up studies, for example, repeated occurrences of tumors in cancer patients. In analyzing such data, majority of the work have focused on intensity based models or models for the mean function of the underlying recurrent events process. As an alternative to such models, we propose a semiparametric regression model for the quantile of the recurrent events process. In fact in dealing with recurrent medical costs related to episodic events, it may be more desirable to model the quantiles instead of the mean as the distribution of the medical costs are typically skewed. We propose an estimating equations based approach for estimating underlying parameters of interest. Finite sample properties will be investigated through simulations. We will present their large sample properties and conclude with a real data illustration.
|
- 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 2007 program |
