|
Activity Number:
|
275
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 5, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #301532 |
|
Title:
|
Statistical Inferences for Outcome-Dependent Sampling Design with Multivariate Outcomes
|
|
Author(s):
|
Tsui-Shan (Eva) Lu*+ and Haibo Zhou
|
|
Companies:
|
The University of North Carolina at Chapel Hill and The University of North Carolina at Chapel Hill
|
|
Address:
|
CB#7420, School of Public Health, , Chapel Hill, NC, 27599,
|
|
Keywords:
|
Outcome-dependent sampling ; Multivariate ; Empirical ; Semiparametric
|
|
Abstract:
|
An outcome-dependent sampling (ODS) (Zhou et al. 2002) scheme is a useful sampling scheme where one observes the exposure with a probability, maybe unknown, depending on the outcome. However, the ODS design and statistical inference procedures with multivariate situations still remain undeveloped. We discuss a general sampling design and inference methods using ODS under multivariate settings. The proposed estimators are consistent and more efficient than those obtained using a simple random sample of the same size. The estimators are semiparametric in nature that all the underlying distributions of covariates are modeled nonparametrically using the empirical likelihood methods. The multivariate-ODS design provides a cost-effective approach to further improve study efficiency.
|
