|
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 - #301366 |
|
Title:
|
An Experiment Testing Alternative Approaches to Screen For Poverty on a Random Digit Dial Survey
|
|
Author(s):
|
David Cantor*+ and Kevin Wang
|
|
Affiliation(s):
|
Westat, Inc. and Urban Institute
|
|
Address:
|
1650 Research Blvd., Rockville, Maryland, 20850,
|
|
Keywords:
|
switching ; burden reduction
|
|
Abstract:
|
The National Survey of America's Families is a random digit dial survey which has an oversample of families that are below 200% of poverty. In order to find poor families, a screening interview is administered that includes questions on whether or not the family income was above or below the boundary for 200% of poverty. Since households are sampled based on this report of poverty on the screener, error in this measure has important consequences for the eventual precision of the survey (e.g., mistakenly being identified as below poverty when actually above poverty). The purpose of this paper is to describe the results of an experiment that experimented with two additional methods to screen for poverty on the screener. One set of questions first asked about income for the current year and then followed up with a question on income for the reference year. The second set of questions initially asked about the average income in the U.S. and followed up with whether the family was above or below that average. The primary outcome variable of interest was whether or not the report of poverty status on the screener is consistent with the report collected during the extended interview.
|
