Do postage stamps versus pre-paid envelopes increase responses to patient mail surveys? A randomised controlled trial

Abstract

Background: Studies largely from the market research field suggest that the inclusion of a stamped addressed envelope, rather than a pre-paid business reply, increases the response rate to mail surveys. The evidence that this is also the case regarding patient mail surveys is limited.

Methods: The aim of this study is to investigate whether stamped addressed envelopes increase response rates to patient mail surveys compared to pre-paid business reply envelopes and compare the relative costs. A sample of 477 initial non-responders to a mail survey of patients attending breast clinics in Greater Manchester between 1/10/2002 - 31/7/2003 were entered into the trial: 239 were randomly allocated to receive a stamped envelope and 238 to receive a pre-paid envelope in with their reminder surveys. Overall cost and per item returned were calculated.

Results: The response to the stamped envelope group was 31.8% (95% CI: 25.9% - 37.7%) compared to 26.9% (21.3% - 32.5%) for the pre-paid group. The difference (4.9% 95% CI: -3.3% - 13.1%) is not significant at alpha = 0.05 (chi2 = 1.39; 2 tailed test, d.f. = 1; P = 0.239). The stamped envelopes were cheaper in terms of cost per returned item (1.20 pounds) than the pre-paid envelopes (1.67 pounds). However if the set up cost for the licence to use the pre-paid service is excluded, the cost of the stamped envelopes is more expensive than pre-paid returns (1.20 pounds versus 0.73 pounds).

Conclusion: Compared with pre-paid business replies, stamped envelopes did not produce a statistically significant increase in response rate to this patient survey. However, the response gain of the stamped strategy (4.9%) is similar to that demonstrated in a Cochrane review (5.3%) of strategies to increase response to general mail surveys. Further studies and meta analyses of patient responses to mail surveys via stamped versus pre-paid envelopes are needed with sufficient power to detect response gains of this magnitude in a patient population.

Figure 1

Response rates by allocation group.