Fit for purpose? The impact of between-wave engagement strategies on response to a longitudinal survey
Andrew Cleary
Ipsos MORI
Nigel Balmer
UCL
Introduction
It is widely accepted that, in sample surveys, non-response bias is the major component of total survey error (Groves 1989). Although recent debate has focused on demonstrating the lack of a clear link between response rates and non-response bias (Groves 2006; Groves & Peytcheva 2008), the options for detecting and ameliorating its effects are limited, hence there remain strong grounds to maximise response rates to mitigate the risk of bias. Longitudinal surveys present a special case where,...