Activity Number:
|
96
|
Type:
|
Topic Contributed
|
Date/Time:
|
Monday, August 12, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Survey Research Methods*
|
Abstract - #300899 |
Title:
|
Evaluation of a Proceedure Based on Interruptions in Telephone Service for Reducing Coverage Bias in RDD Surveys
|
Author(s):
|
K. Srinath*+ and Michael Battaglia and Martin Frankel and Meena Khare and Wenxing Zha
|
Affiliation(s):
|
Abt Associates, Inc. and Abt Associates, Inc. and Abt Associates, Inc. and National Center for Health Statistics and National Center for Health Statistics
|
Address:
|
1110 Vermont Avenue, Washington, D.C., District of Columbia, 20005,
|
Keywords:
|
Poststratification ; Mean Squared Error
|
Abstract:
|
The estimates from an RDD survey may be biased due to exclusion of nontelephone households. A common method to reduce this bias is to adjust the weights through poststratification. Recent studies have shown that weight adjustment methods based on interruptions in telephone service among telephone households in the sample further reduce the coverage bias at the national and state levels. However, it is of interest to examine whether mean-squared errors of interruption-based estimates increase at the state level as compared to poststratification. In this paper, we evaluate the method based on interruptions in telephone service using the data from the Current Population Survey (CPS) and the National Health Interview Survey (NHIS). The data from the CPS (1996-1998) is used exclusively to compare the reduction in bias in the estimates at the state level to the reduction achieved through only poststratification. The data from the three years of NHIS (1997-1999) are used to compare both bias and the variance of the interruption estimates at the state level for nine large states with the usual poststratification estimates.
|