Quality & Quantity 36: 427–437, 2002.
© 2002 Kluwer Academic Publishers. Printed in the Netherlands.
A Multilevel Multinomial Analysis of Interviewer
Effects on Various Components of Unit
JAN PICKERY and GEERT LOOSVELDT
Department of Sociology, KU Leuven, E. Van Evenstraat 2B, 3000 Leuven, Belgium. E-mail:
Abstract. This note demonstrates an application of a multilevel multinomial model. We use that
model to analyse interviewer effects on various components of unit nonresponse to a face-to-face
survey: refusals and noncontacts. The model allows for an analysis of these two interviewer effects
and a possible connection between both at the same time. Our results show that both the chances
for refusals as for noncontacts are subject to interviewer effects. We also ﬁnd some evidence for a
relation between both interviewer effects: interviewers who obtain more refusals are also more likely
to report noncontacts. That result is however at least partly dependent on an outlier, an interviewer
with a high number of refusals and noncontacts.
In this note we analyse interviewer effects on two different components of unit non-
response in a face-to-face survey: refusals and noncontacts. Moreover we examine
a possible connection between both interviewer effects.
Groves (1989: 140–144) distinguishes six possible outcomes of an attempt to
interview a respondent (completed interview, partial interview, noncontacted but
known eligible unit, refused eligible unit, noneligible unit, other noninterviewed
unit). Refusals and noncontacted respondents generally make up the two most
important components of unit nonresponse. Although it is important to separ-
ate noncontacts from refusals when examining survey participation (Groves and
Couper, 1998), a simultaneous analysis of both components seems relevant when
assessing interviewer effects. Such an analysis can answer the question whether
interviewers who are successful in contacting the respondents are also successful
in obtaining participation.
A refusal is an active act of the respondent and a crucial aspect of respond-
ent behaviour. Several authors try to explain this respondent behaviour (see e.g.,