Journal of Official Statistics, Vol.3, No.3, 1987. pp. 267282

Current Issue
Personal Reference Library (PRL)
Personal Page

Attrition in a Panel Study of Attitudes

An extensive literature exists on the problems of nonresponse in panel studies where factual and quasi-factual information is collected. The effects of attrition in a panel study of attitudes are less well documented.

This paper describes a four-wave annual panel study of social attitudes in Britain. The response rate and the factors which affect it are discussed in detail. A profile of continuing panel members is drawn and this profile is compared with findings from other longitudinal surveys. Special attention is given to the likely effects of attrition on the proportions answering “Don't know.” Finally, the effects of a post-stratification weight to compensate for differential nonresponse are assessed and some recommendations are made for its use.

Attitude survey; nonresponse; attrition; response rates; panel surveys; post-stratification.

Copyright Statistics Sweden 1996-2018.  Open Access
ISSN 0282-423X
Created and Maintained by OKS Group