Multilevel modelling of refusal and noncontact nonresponse in household surveys: evidence from six UK government surveys

This paper analyses household unit nonresponse and interviewer effects in six major UK government surveys using a multilevel multinomial modelling approach. The models are guided by current conceptual frameworks and theories of survey participation. One key feature of the analysis is the investigation of survey dependent and independent effects of household and interviewer characteristics, providing an empirical exploration of the leverage-salience theory. The analysis is based on the 2001 UK Census Link Study, a unique data source containing an unusually rich set of auxiliary variables, linking the response outcome of six surveys to census data, interviewer observation data and interviewer information, available for respondents and nonrespondents