|
Activity Number:
|
414
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #309137 |
|
Title:
|
Use of Interviewer Judgments About Attributes of Selected Respondents in Post-Survey Adjustment for Unit Nonresponse: An Illustration with the National Survey of Family Growth
|
|
Author(s):
|
Robert M. Groves and James Wagner and Emilia Peytcheva*+
|
|
Companies:
|
University of Michigan and University of Michigan and University of Michigan
|
|
Address:
|
2722 Packard Street, Ann Arbor, MI, 48108,
|
|
Keywords:
|
nonresponse ; postsurvey adjustment ; propensity models ; paradata
|
|
Abstract:
|
With computer-assisted data collection methods, the survey designer has the ability to seek interviewer observations about sample persons. When such observations can be made on both respondents and nonrespondents, the resulting paradata are candidates for use in adjustment. This paper evaluates the measurement error properties of an interviewer observation about attributes related to key measures in the National Survey of Family Growth (NSFG), sponsored by the US National Center for Health Statistics. Immediately after the household roster is taken, one age-eligible respondent is selected using fixed probabilities based on age and gender. Prior to any initiation of the main interview request, the interviewer is asked to judge attributes of the sample person. These are evaluated using a variety of post-survey adjustment approaches and a variety of key statistics computed on the NSFG.
|
