Quality & Quantity (2006) 40:1013–1036 © Springer 2006
Explaining Income Nonresponse – A Case Study
by means of the British Household Panel Study
Ruhr-University Bochum and DIW Berlin, Germany. E-mail: firstname.lastname@example.org
Abstract. Many validation studies deal with item nonresponse and measurement error
in earning data. In this paper, we explore motives of respondents for the failure to
reveal earnings using the British Household Panel Study (BHPS). The BHPS collects
socio-economic information of private households in Great Britain. We explain the evolution
of income-nonresponse in the BHPS and demonstrate the importance of a discrimination
between refusing the income-statement or don’t know.
JEL Classiﬁcation: C81.
Key words: interviewer effects, item-nonresponse, multilevel modeling, panel analysis,
This paper deals with income nonresponse and unit nonresponse in the
British Household Panel Study (BHPS). We describe the trend in the data
and try to explain why respondents refuse to state their income question on
the basis of a cognitive and rational choice theory. The BHPS is conducted
by the ESRC Centre on Micro-social Change at the University of Essex,
UK, with ﬁeldwork implemented by NOP Research, London. Interviewing
on the BHPS began in 1991. The BHPS was designed as an annual survey
of each adult member of a nationally representative sample of approx-
imately 5000 housholds. Children will be interviewed as they reach the
age of 16. The BHPS provides some features for methodological analy-
sis like information about the survey methods and there is for a quarter
of the full sample in wave 2 an interpenetrating sample design experiment
This study is done during my fellowship at the University Essex and is part of
the ECASS Project “Respondent Behaviour in Panel Studies”. In particular I would like
to thank Heather Laurie, Cheti Nicoletti and Peter Lynn (ISER, Essex) as well as Gert
G. Wagner (DIW Berlin and Berlin University of Technology, TUB) for helpful comments.
The usual disclaimer applies.