|
Activity Number:
|
162
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 9, 2004 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #300403 |
|
Title:
|
Model-based Estimates of the Finite Population Mean for Two-stage Cluster Samples with Unit Nonresponse
|
|
Author(s):
|
Ying Yuan*+ and Roderick J. Little
|
|
Companies:
|
University of Michigan and University of Michigan
|
|
Address:
|
1420 Washington Heights, M4048D, Ann Arbor, MI, 48109,
|
|
Keywords:
|
|
|
Abstract:
|
We propose new model-based methods for unit nonresponse in two-stage survey samples. A standard design-based weighting adjustment (WT) is potentially inefficient when the estimated response rates within clusters are very variable. In addition, we show that the usual random-effects model based estimator of the population mean (RE) is biased in the setting of unit nonresponse unless nonresponse is missing completely at random, which makes the often unrealistic assumption that the response rates are unrelated to cluster characteristics. This fact motivates modifications of RE that allow the cluster means to depend on the response rates in the clusters. Two approaches are considered to correct the bias of RE, one that includes the observed response rate as a cluster-level covariate (RERR), and one based on a probit model for response (NI1). We also consider another nonginorable model estimate of the mean (NI2) that removes the bias of WT, NI1, and RERR when there is association between response and the survey outcome within the clusters.
|
- 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 2004 program |
