Paid work versus accessibility in surveys: Are we running the risk of nonresponse bias? The example of ESS 5 in Poland
Loading...
Date
2014
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Ohio State University Libraries in partnership with IFiS Publishers
Abstract
Research data shows that nonresponse in surveys is increasingly connected with
respondents’ lack of time caused, among others, by respondents’ performance of paid work.
Since paid work is one of the key sociological characteristics, the underrepresentation of
working citizens creates a risk of nonresponse bias in surveys. This paper draws on data
from the fifth round of the European Social Survey in Poland to demonstrate how realistic
this risk is. Apart from paid work, the paper analyses three dimensions of workload: total
work hours, regular/irregular nature of work and place of residence/place of work (the same
or different location) and time spent commuting to/from work. The results of our analysis
show that there is a risk of nonresponse bias associated with the performance of paid work
and time spent commuting to/from work in another location. This risk may be reduced by
increasing the number of contact attempts with hard-to-reach respondents.
Description
Keywords
accessibility in surveys, nonresponse bias, paid work as a variable in surveys, European Social Survey
Citation
Ask: Research and Methods. Volume 23, Issue 1 (2014), pp. 79-102