Alternative approaches to multilevel modelling of survey noncontact and refusal


Steele, Fiona and Durrant, Gabriele B. (2009) Alternative approaches to multilevel modelling of survey noncontact and refusal. Southampton, UK, Southampton Statistical Sciences Research Institute, 37pp. (S3RI Methodology Working Papers, (M09/15) ).

Download

[img] PDF
Download (697Kb)

Description/Abstract

We review three alternative approaches to modelling survey noncontact and refusal: multinomial, sequential and sample selection (bivariate probit) models. We then propose a multilevel extension of the sample selection model to allow for both interviewer effects and dependency between noncontact and refusal rates at the household and interviewer level. All methods are applied and compared in an analysis of household nonresponse in the UK, using a dataset with unusually rich information on both respondents and nonrespondents from six major surveys. After controlling for household characteristics, there is little evidence of residual correlation between the unobserved characteristics affecting noncontact and refusal propensities at either the household or the interviewer level. We also find that the estimated coefficients of the multinomial and sequential models are surprisingly similar, which further investigation via a simulation study suggests is due to there being little overlap between the predictors of noncontact and refusal.

Item Type: Monograph (Working Paper)
Keywords: Clustered categorical response data, discrete choice models, hierarchical models, survey nonresponse, interviewer effects.
Subjects: H Social Sciences > HA Statistics
H Social Sciences > HM Sociology
Divisions: University Structure - Pre August 2011 > Southampton Statistical Sciences Research Institute
ePrint ID: 67249
Date Deposited: 07 Aug 2009
Last Modified: 27 Mar 2014 18:48
URI: http://eprints.soton.ac.uk/id/eprint/67249

Actions (login required)

View Item View Item

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics