We are often asked to advise on the best way to improve response rates to postal surveys. Below are the evidence-based best ways we have found to increase response rates. Further Information about how to improve response rates through collecting, posting and addressing envelopes can be found here.
Recent review articles have found that the most effective way to increase response rates to questionnaires sent through the post is to provide a monetary incentive. Almost any amount will do, there being not much difference between being given £1 or £10. The most effective method is to provide money directly within the initial questionnaire itself (i.e. to pre-pay the prize) and NOT to put conditions on the money.
Although more effective than no incentive at all, asking respondents to apply for the money or sending the money to a charity greatly reduces the response rates.
Sending monetary rewards through the post does have difficulties, such as (in the UK) sending a pound coin makes the incentive obvious to would-be thieves and makes the questionnaire difficult to post out. We have found that in the UK money-like rewards such as first class stamps provide good response rates. We've even had people using the stamps to write back to us to say thank you!
Generally non-monetary incentives such as including a pencil or sticker with the questionnaire have little positive impact on response rates.
Prizes for respondents can improve response rates and are one of the few effective ways non-postal (i.e. Internet) surveys response rates can be improved. Interestingly one study found that better response rates are generated by providing a single large prize (e.g. one prize of 6 bottles of champagne) rather than a larger number of smaller prizes (e.g. 6 prizes of single bottles of champagne), even though the chances of winning are 6 times lower!
The likelihood of someone sending back the questionnaire more than doubles if the survey is sent by recorded delivery. First class delivery when sending the questionnaire and more importantly a first class stamp on a pre-addressed envelope for sending back the questionnaire also increases responses. Pre-contacting the people to be surveyed before the main questionnaire is sent out increases overall response rates, as does unsurprisingly sending follow-up messages and second questionnaires.
Personalised questionnaires and letters increase response rates, as does a signature - although it doesn't seem to matter whether the signature is real or just a image. Using coloured ink also increases response rates.
Questionnaires originating from universities are more likely to be returned than questionnaires from other sources, such as commercial organisations.
Edwards P.J., Roberts, I., Clarke, M. et al. (2002). Increasing response rates to postal questionnaires: Systematic review. British Medical Journal, 2002;324:118-131.
Edwards. P.J. et al, (2009). Methods to increase response to postal and electronic questionnaires. Cochrane Library. http://onlinelibrary.wiley.com/o/cochrane/clsysrev/articles/MR000008/frame.html
Survey Monkey (2007). Best Practices for Survey Design. http://s3.amazonaws.com/SurveyMonkeyFiles/SmartSurvey.pdf
VanGeest, J. B., Johnson, T.P. & Welch, V. L. (2007). Methodologies for improving response rates in surveys of physicians. Evaluation and Health Professionals, 30 (4) 303-321.