An Empirical Analysis of the Association between Neighbourhood Income and Unit Nonresponse in the Survey of Health, Ageing and Retirement in Europe

28 Pages Posted: 28 Sep 2009 Last revised: 4 Oct 2009

Date Written: September 1, 2009

Abstract

This paper estimates associations between individual and neighbourhood characteristics and unit nonresponse in a survey of the population aged 50 and over in the Netherlands in 2004. The statistical model includes interviewer fixed effects to control for the non-random distribution of addresses over interviewers. The empirical analysis shows that, relatively to individuals living in apartments, there is a lower unit nonresponse among individuals living in houses and a higher unit nonresponse among individuals living in old age institutions. Unit nonresponse is positively associated with the size of a city. No age and gender effects are found. Unit nonresponse is about 25% lower among individuals in the top than among individuals in the bottom of the distribution of neighbourhood average income. This latter result implies that the response sample is biased towards individuals living in the more wealthy neighbourhoods.

Keywords: household survey, unit nonresponse, discrete choice model, income

JEL Classification: C8, C35, C42

Suggested Citation

Kalwij, Adriaan, An Empirical Analysis of the Association between Neighbourhood Income and Unit Nonresponse in the Survey of Health, Ageing and Retirement in Europe (September 1, 2009). Netspar Discussion Paper No. 09/2009-028, Available at SSRN: https://ssrn.com/abstract=1479397 or http://dx.doi.org/10.2139/ssrn.1479397

Adriaan Kalwij (Contact Author)

Utrecht University ( email )

Janskerkhof 12
Utrecht, 3512 BL
Netherlands

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
68
Abstract Views
515
Rank
603,475
PlumX Metrics