Activity Number:
|
315
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 14, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Survey Research Methods*
|
Abstract - #301976 |
Title:
|
Weighting for Nontelephone Households in the 2001 California Health Interview Survey
|
Author(s):
|
Ismael Flores-Cervantes*+ and Michael Brick and Michael Jones and Charles DiSogra and Wei Yen
|
Affiliation(s):
|
Westat, Inc. and Westat, Inc. and Westat, Inc. and University of California, Los Angeles and University of California, Los Angeles
|
Address:
|
1650 Research Blvd., Rockvill, MD, 20850, USA
|
Keywords:
|
Nontelephone adjustment ; Keeter adjustment ; modified poststatification method ; health survey
|
Abstract:
|
The decision to use a telephone survey introduces a coverage error due to the exclusion of persons in households without telephones. For estimates correlated with socioeconomic measures the bias associated may be important. In the last couple of years, several methods have been proposed to address this problem. The main idea of these methods is to adjust the weights based on auxiliary data to account for the population without telephones. This paper describes our experience of implementing one of these methods in the California Health Interview Survey (CHIS 2001). We present the reasons for using a modified poststratification method instead of a Keeter-type adjustment. We also discuss problems found and the approaches used to solve them. The strengths and weakness of this approach when applied to CHIS 2001 are discussed. Estimates created using weights with and without the adjustments are also presented.
|