|
Activity Number:
|
470
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 9, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #307038 |
|
Title:
|
Statistical Inference for Multivariate Outcome-Dependent Sampling Design
|
|
Author(s):
|
Tsui-Shan Lu*+ and Haibo Zhou
|
|
Companies:
|
The University of North Carolina at Chapel Hill and The University of North Carolina at Chapel Hill
|
|
Address:
|
Department of Biostatistics, CB #7420, School of Public Health, Chapel Hill, NC, 27599,
|
|
Keywords:
|
outcome-dependent sampling ; empirical likelihood ; semiparametric
|
|
Abstract:
|
An outcome-dependent sampling (ODS) (Zhou et al. 2000) scheme is a retrospective sampling scheme like the case-control study where one observes the exposure with a probability, maybe unknown, that depends on the outcome variable. Allowing the selection probability of each individual in the ODS sample to depend on the outcome can be a cost effective way to enhance study efficiency. We consider a design of ODS, where the sampling of a family depends on the aggregate of the outcomes with the family. We propose a semiparametric empirical likelihood method for such family-based ODS design. The proposed methods are semiparametric in the sense that the marginal distribution of covariates is treated as a nuisance parameter and is left unspecified. Our simulation results show that the proposed estimator provides a more efficient parameter estimate than it obtained using a simple random sample.
|
