Are interviewer administered follow-ups of web non-respondents still needed to maximise respondent dataset quality? Evidence using Understanding Society: the UK Household Longitudinal Study

Abstract

This paper investigates whether follow-ups of web non-respondents with CAPI (Computer Assisted Personal Interviewing) or CATI (Computer Assisted Telephone Interviewing) are still required to maximise dataset quality, and how this pattern may have changed over time. The analysis uses data from Understanding Society: the UK Household Longitudinal Study (UKHLS) and representativeness indicators (R-indicators, and Coefficients of Variation of response propensities, CVs) are used to evaluate the representativeness of respondent samples. The findings discuss the impacts of follow-ups of non-respondents on response rates, representativeness and hard-to-reach population subgroups and non-response bias, including implications of for survey practice.