Freedman Vicki A, McGonagle Katherine A, Couper Mick P
Institute for Social Research, University of Michigan.
J Surv Stat Methodol. 2018 Mar;6(1):98-121. doi: 10.1093/jssam/smx012. Epub 2017 Jul 6.
Relatively low response rates in mixed mode studies remain a concern. Whether targeting protocols to match respondents' likely mode is an effective strategy remains unclear. For those without a clear likely mode, how the details about sequencing influence response rates, mode, field work effort, and potential response bias remain important questions. This article describes a targeted sequential design implemented in a 2016 mixed mode supplement with individuals ages 30 and older in the Panel Study of Income Dynamics, the longest running national panel study in the US (N=10,784). Respondents predicted to be likely to respond by web were invited to a web study and sent a paper copy after 6 weeks (web-first); those likely to respond by paper were also invited to participate by web but told that a paper copy would be sent shortly (signal-and-send). An embedded experiment measured the impact of the two protocols among a group of respondents with no clear likely mode (N=889). Over 40% of individuals with no likely mode are under the age of 40, and the group falls between the likely web and paper groups in terms of education and internet use and includes more women and single respondents. Compared to the likely web and paper groups, those with no likely mode had lower response rates and required more fieldwork effort. Among those randomly assigned, the signal-and-send protocol increased response over the web-first protocol from weeks 4 through 7. By week 16, both protocols yielded similar response rates (AAPOR 1 RR=71% vs. 68%, p=0.49), field effort (7.9 vs. 8.4 mean weeks, p=0.251), and distributions of respondent characteristics. Among those responding, cases randomized to web-first were more likely than those randomized to signal-and-send to respond by web (62.7% vs. 42.4% p<.001). We discuss implications for targeted protocols in mixed mode panel surveys.
混合模式研究中相对较低的回应率仍然是一个令人担忧的问题。针对调查方案以匹配受访者可能采用的模式是否是一种有效策略仍不明确。对于那些没有明确可能采用模式的受访者，关于调查顺序的细节如何影响回应率、调查模式、实地调查工作量以及潜在的回应偏差，仍然是重要的问题。本文描述了一种有针对性的顺序设计，该设计在2016年一项针对美国收入动态面板研究中30岁及以上个体的混合模式补充调查中实施，该研究是美国持续时间最长的全国性面板研究（N = 10784）。预计可能通过网络回应的受访者被邀请参加网络调查，并在6周后发送纸质问卷（网络优先）；预计可能通过纸质问卷回应的受访者也被邀请参加网络调查，但被告知很快会发送纸质问卷（先发出信号再发送）。一项嵌入式实验测量了这两种方案对一组没有明确可能采用模式的受访者（N = 889）的影响。超过40%没有明确可能采用模式的个体年龄在40岁以下，该组在教育程度和互联网使用方面介于可能采用网络和纸质问卷的群体之间，并且包括更多女性和单身受访者。与可能采用网络和纸质问卷的群体相比，没有明确可能采用模式的受访者回应率较低，并且需要更多的实地调查工作量。在随机分配的受访者中，从第4周到第7周，“先发出信号再发送”方案的回应率高于“网络优先”方案。到第16周时，两种方案的回应率（美国民意调查协会标准1回应率=71%对68%，p = 0.49）、实地调查工作量（平均7.9周对8.4周，p = 0.251）以及受访者特征分布相似。在回应的受访者中，随机分配到“网络优先”的受访者比随机分配到“先发出信号再发送”的受访者更有可能通过网络回应（62.7%对42.4%，p <.001）。我们讨论了混合模式面板调查中有针对性的调查方案的意义。
