|
Activity Number:
|
428
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #305567 |
|
Title:
|
Design-Based Calibration Estimators for Measurement Error in the Cox Model
|
|
Author(s):
|
Thomas Lumley*+ and Pam Shaw
|
|
Companies:
|
University of Washington and University of Washington
|
|
Address:
|
, Seattle, WA, 98195,
|
|
Keywords:
|
raking ; measurement error
|
|
Abstract:
|
Many techniques exist for using a small validation subsample to correct for measurement error in predictors when error-free data are available in the subsample. We present a technique that is valid when the validation subsample has classical measurement error and no assumptions are made about error model in the full cohort. The estimation is based on survey calibration for the cohort total of the estimating function, using biased estimating function in the cohort as calibration variables.
|
- 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 2006 program |
