Abstract #300311

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); 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.

Back to main JSM 2003 Program page
JSM 2003 Abstract #300311
Activity Number: 355
Type: Topic Contributed
Date/Time: Wednesday, August 6, 2003 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Epidemiology
Abstract - #300311
Title: Using Completely Observed Covariates to Improve Efficiency of Case-Cohort Estimation
Author(s): Michal Kulich*+
Companies: University of Washington
Address: 8818 Interlake Ave. N, Seattle, WA, 98103-4030,
Keywords: proportional hazards model ; two-phase study ; relative risk ; survival analysis
Abstract:

The case-cohort design reduces covariate assessment costs by collecting complete covariate data only on the cases and on a randomly selected subcohort. Sometimes, a large part of the covariate assessment costs is attributed to a few very expensive covariates, while all other covariates can be observed at little cost. The existing estimators for the case-cohort design ignore the covariate data collected outside the case-cohort sample and thus lose efficiency. To address this problem, we develop a class of estimators with general time-varying weights, which are consistent and asymptotically normal. We consider a specific member of this class which incorporates all completely observed covariates and allows to impute estimated values for unobserved covariates. We combine this estimator adaptively with Estimator II with time-varying weights, one of the most efficient existing case-cohort estimators. The combined estimator is consistent and asymptotically normal. Its limiting variance is guaranteed not to exceed that of Estimator II. Simulation studies demonstrate that the combined estimator can achieve substantial efficiency gains.

  • 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 2003 program

JSM 2003 For information, contact meetings@amstat.org or phone (703) 684-1221. If you have questions about the Continuing Education program, please contact the Education Department.
Revised March 2003