Full Citation

Title: Panel Attrition

Citation Type: Book, Section

Publication Year: 2018

ISBN:

ISSN:

DOI:

NSFID:

PMCID:

PMID:

Abstract: Social science data collection leans heavily on longitudinal surveys with some of NSF’s most important surveys being entirely longitudinal or having important longitudinal components. The Current Population Survey re-interviews respondents but does not exploit its longitudinal feature as much as it could. Whenever longitudinal studies come up, one of the first topics is attrition. I argue here that longitudinal surveys, even with attrition, are cost-effective and that the typical metric of attrition, wave non-response, is not the correct metric. Rather, it is the completeness of the data over time which really matters. By continuing to seek interviews with wave non-respondents and collecting retrospective data for the time periods covered in missed waves, the data base for a respondent can be made substantially more complete, greatly attenuating the impact of missed interviews.

Url: https://link.springer.com/chapter/10.1007/978-3-319-54395-6_59

User Submitted?: No

Authors: Olsen, Randall

Editors: Vannette, David, L; Krosnick, Jon, A

Pages: 509-517

Volume Title: The Palgrave Handbook of Survey Research

Publisher: Palgrave Macmillan

Publisher Location: Cham, Switzerland

Volume:

Edition:

Data Collections: IPUMS USA

Topics: Methodology and Data Collection

Countries: