Publication type
Survey Futures Working Paper Series
Series Number
20
Series
Survey Futures Working Paper Series
Authors
Publication date
June 22, 2026
Summary:
Many social surveys have adopted web first sequential mixed mode designs in which web mode is offered, then non-respondents followed up in interviewer administered face-to-face (Computer Assisted Personal Interviewing (CAPI) or telephone (Computer Assisted Telephone Interviewing (CATI) modes. These designs cost less than CAPI or CATI only designs, and can produce higher quality datasets than web only designs, though research suggests that benefits have declined over time. However, the impacts of such follow-ups on dataset quality for important population subgroups are unknown. We address this question by using Understanding Society: the UK Household Longitudinal Study data to investigate the impact of CATI follow ups of web non-respondents on overall and Young adult, Older adult, Ethnic minority and Low income subgroup dataset quality. We find that follow-ups: 1) increase dataset sizes by more than for the overall dataset for some subgroups but not others; 2) improve both overall and subgroup dataset representativeness; 3) improve the representation of some under-represented subgroups but not others in both overall and subgroup datasets; and 4) reduce non-response biases remaining after non-response weighting for some subgroups but not for others or for the overall dataset. We then discuss the implications of our findings for survey practice.
Subjects
Link
https://surveyfutures.net/working-papers/
#589091