|
Activity Number:
|
167
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #305394 |
|
Title:
|
A Simulation Study of Alternative Weighting Class Adjustments for Nonresponse When Estimating a Population Mean from Complex Sample Survey Data
|
|
Author(s):
|
Brady T. West*+
|
|
Companies:
|
University of Michigan
|
|
Address:
|
Survey Methodology Program, Ann Arbor, MI, 48106-1248,
|
|
Keywords:
|
Complex Sample Survey Data ; Unit Nonresponse ; Nonresponse Weighting Adjustments ; Missing Data
|
|
Abstract:
|
Results are presented from a simulation study of alternative weighting class adjustments for nonresponse when estimating a population mean from complex sample survey data, in an effort to extend the previous work of Little and Vartivarian (2003, 2005) to a complex sample survey setting involving stratified cluster sampling from a finite target population. Results from 30 different simulations suggest that the use of weighted response rates within weighting classes that are defined by values on an auxiliary variable and the sampling strata can be beneficial (in terms of reduced RMSE) when working with survey data collected from "complex" stratified cluster samples, particularly when response rates are low and the auxiliary and stratum variables are correlated with both the survey variable of interest and response propensity. Suggestions for survey practice and future research follow.
|
