Meta-analysis of randomised trials of monetary incentives and response to mailed questionnaires
- Department of Epidemiology and Population Health, London School of Hygiene and Tropical Medicine, London, UK
- Correspondence to: Dr P Edwards Department of Epidemiology and Population Health, London School of Hygiene and Tropical Medicine, Keppel Street, London WC1E 7HT, UK; phil.edwardslshtm.ac.uk
- Accepted 15 May 2005
Abstract
Study objective: To quantify the increase in mailed questionnaire response attributable to a monetary incentive.
Design: A systematic search for randomised controlled trials of monetary incentives and mailed questionnaire response was conducted. For each trial identified, logistic regression was used to estimate the odds ratio for response per $0.01 incentive increase. Odds ratios were pooled in a series of random effect meta-analyses stratified by the minimum and maximum amounts offered. Piecewise logistic regression was used to estimate the odds ratio for response per $0.01 increase given in each of five incentive ranges.
Setting: Populations in several developed countries, predominantly the USA.
Participants: 85 671 randomised participants from 88 trials.
Main results: The pooled odds ratios for response per $0.01 incentive decreased monotonically as the maximum amount of incentive offered increased. The piecewise logistic regression model estimated that for incentive amounts up to $0.50, each additional $0.01 increased the odds of response by about 1% (pooled OR = 1.012, 95%CI 1.007 to 1.016). The effects on response above $0.50 were smaller and decreased monotonically in the ranges: $0.50–0.99, $1–1.99, $2–4.99, $5.00 and over, but remained statistically significant up to $5.
Conclusions: This meta-analysis of the best available evidence shows that monetary incentives increase mailed questionnaire response. Researchers should include small amounts of money with mailed questionnaires rather than give no incentive at all.
Footnotes
-
Funding: none.
-
Conflicts of interest: none declared.
