Over the past few decades, the survey industry has experienced a steady decline in response rates, which has posed numerous challenges for researchers, most notably concerns about nonresponse bias. We present results from three studies conducted in an attempt to increase response rates and reduce nonresponse bias for a U.S. national household survey. We examined design features related to mode (i.e., mail-only vs. web-push), incentive, reminder type, nonresponse follow-up, and messaging. Results showed that a combination of a mail-only approach and the use of US$2 prepaid incentives increased response rates. However, using incentives did not bring into the respondent pool sample members who were less likely to respond. Additionally, we found that the use of a seventh follow-up contact only slightly increased response rates. Finally, we found that the use of a friendly message not only suppressed response rates but also increased potential nonresponse bias for sample members aged 35–48.

中文翻译：

---

什么有效，什么无效？三项旨在改善调查反应的研究

在过去的几十年里，调查行业的回复率一直在稳步下降，这给研究人员带来了许多挑战，最显着的是对无回复偏见的担忧。我们展示了三项研究的结果，这些研究旨在提高美国全国家庭调查的响应率并减少不响应偏差。我们检查了与模式（即，仅邮件与网络推送）、激励、提醒类型、无响应跟进和消息传递相关的设计特征。结果表明，将仅邮寄方式与使用 2 美元预付奖励相结合提高了响应率。然而，使用激励措施并没有将不太可能做出回应的样本成员带入受访者池。此外，我们发现使用第七个后续联系人只会略微提高响应率。最后，