Author
Summary
In the longitudinal survey literature, there is little discussion of how call record data (and particularly, specific call sequences) are able to account for household-level response propensities in subsequent waves. This paper uses call records as well as observed data from Understanding Society’s Wave 1 to model Wave 2 and Wave 3 household contact and cooperation propensities. Single- and multi-level logistic models are used to account for the nested structure of the data (households within interviewers) and to explore effects of the interviewer, household traits, and aggregates of individual and call record data from the preceding wave. Model specification considers the conditionally independent processes of contact and cooperation and is informed by established theories of survey nonresponse. Additional controls include interviewer identifiers, geographical markers and stable household flags to account for possible effects of intra-wave splits and reallocation of interviewers. Understanding Society data indicates that specific events and contact sequences predict future contact and cooperation propensities. More specifically, these findings suggest that households which repeated unproductive contacts, broke appointments, registered above median proportion of ‘no replies’, or began the call sequence with an unproductive contact in Wave 1 are at risk of future nonresponse. The effects are consistent for Waves 2 and 3. This is not trivial if one considers the frequency of occurrence of these types of call sequences. Obviously, the risk is magnified when one considers the multiplicative effect of these events. The analysis of the models is followed by a discussion of possible implications for field effort optimization and nonresponse prevention in subsequent waves.
Subject
Link
https://www.understandingsociety.ac.uk/scientific-conference-2015/papers/64