|
Activity Number:
|
293
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #308803 |
|
Title:
|
A Dynamic Approach to Response Propensity
|
|
Author(s):
|
Kristen Olson*+
|
|
Companies:
|
University of Michigan
|
|
Address:
|
Institute for Social Research, Ann Arbor, MI, 48104-2321,
|
|
Keywords:
|
nonresponse ; response propensity ; nonresponse bias ; data collection
|
|
Abstract:
|
Traditional views of survey participation view a person's likelihood of participating in a survey as deterministic or stochastic. Both views assert that a sample unit has one response propensity, given an evolved survey protocol. In a field survey, sample units vary in their receipt of individual recruitment protocol components and in the timing of these components. These components are specifically applied to alter response propensities. This paper argues that sample units have more than one response propensity, changing with the introduction of new protocol components. We call this a dynamic view of response propensity. Dynamic response propensities are estimated using two surveys with records for respondents and nonrespondents. The records are used to illustrate how a dynamic response propensity approach changes the understanding of nonresponse bias and of recruitment procedures.
|
- 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 2007 program |
