|
Activity Number:
|
98
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #302081 |
|
Title:
|
Proxy Pattern-Mixture Analysis for Survey Nonresponse
|
|
Author(s):
|
Rebecca Andridge*+ and Roderick J. Little
|
|
Companies:
|
The University of Michigan and The University of Michigan
|
|
Address:
|
Department of Biostatistics, Ann Arbor, MI, 48109,
|
|
Keywords:
|
nonignorable nonresponse ; missing data ; survey data ; Bayesian methods ; nonresponse bias
|
|
Abstract:
|
We consider assessment of nonresponse bias for the mean of a survey variable Y subject to nonresponse. We assume that there are a set of covariates observed for nonrespondents and respondents. To reduce dimensionality and for simplicity we reduce the covariates to a proxy variable X that has the highest correlation with Y, estimated from a regression analysis of respondent data. We consider adjusted estimators of the mean of Y that are maximum likelihood for a pattern-mixture model with different means of Y and X for respondents and nonrespondents, assuming missingness is an arbitrary function of a known linear combination of X and Y. We propose a sensitivity analysis, sketch Bayesian versions of this approach, and propose a taxonomy for the evidence concerning bias based on the strength of the proxy and the deviation of the mean of X for respondents from the overall mean.
|
