Propensity to consent to data linkage: experimental evidence on the role of three survey design features in a UK longitudinal panel

Abstract

When performing data linkage, survey respondents need to provide their informed consent. Since not all respondents agree to this request, the linked data-set will have fewer observations than the survey data-set alone and bias may be introduced. By focusing on the role that survey design features play in gaining respondents' consent, this paper provides an innovative contribution to the studies in this field. Analysing experimental data collected in a nationally representative household panel survey of the British population, we find that interview features such as question format (dependent/independent questions) and placement of the consent question within the questionnaire have an impact on consent rates.

Obtaining Record Linkage Consent from Establishments: The Impact of Question Placement on Consent Rates and Bias

“…The study results are in line with social survey studies showing that placing the consent question at the end of the questionnaire is a suboptimal strategy for optimizing the linkage consent rate (Sakshaug et al, 2013;Sala et al, 2014). The fact that this result holds in an establishment survey context is interesting considering that the establishment survey response process differs in a number of ways compared to response processes in social surveys.…”

“…The available evidence suggests that establishment surveys typically place the consent question at or near the end of the questionnaire, as is the case for the majority of surveys in Table 1. This trend is in line with social surveys despite the experimental evidence demonstrating its suboptimality (Sakshaug et al 2013;Sala et al 2014 …”

“…Sakshaug et al (2013) show that asking for consent at the beginning of the interview produces a higher consent rate than asking at the end of the interview, a finding which has since been replicated (Kreuter et al 2015). Sala et al (2014) also find that administering the linkage consent question earlier in the questionnaire yields a higher consent rate than administering it at the p. 8…”

“…To minimize the risk of consent bias in surveys, researchers have tested different strategies for maximizing the consent rate (Sakshaug, Tutz, and Kreuter 2013;Sakshaug and Kreuter 2014;Sala, Knies, and Burton 2014;Kreuter, Sakshaug, and Tourangeau 2016). One particular strategy is to modify the placement of the consent question in the questionnaire.…”

Optimizing Opt-Out Consent for Record Linkage

“…For example, Singer (1978Singer ( , 2003 reported that some respondents who may have been willing to participate in a survey were not willing to sign a consent form. Sala et al (2013) provide an estimate of the negative effect of having to sign a consent form: 3.9% of the sample who consented to record linkage verbally refused to sign a consent form. Hunt et al (2013) found that requiring explicit opt-in consent (in the form of a reply card) prior to a mail survey significantly reduced participation.…”