Notice: the WebSM website has not been updated since the beginning of 2018.

Web Survey Bibliography

Title Why Do Respondents Break Off Web Surveys and Does It Matter? Results From Four Follow-up Surveys
Year 2014
Access date 17.11.2014

With the rise of Web survey research high breakoff rates are increasingly considered a major shortcoming. Based on the framework for the explanation of Web survey participation, three categories of predictors have been identified as major causes for breakoff: Respondent-related factors, survey design, and page and question characteristics (Peytchev, 2009, pp. 76–82). While there are many findings on the impact of questionnaire, question, and survey characteristics on breakoff (e.g., El-Menouar & Blasius, 2005; Galesic, 2006; Heerwegh, 2005; Peytchev, 2009), there is only limited evidence on the effects of respondent characteristics. We know little about sociodemographic and attitudinal correlates of breakoff because information on respondents who break off is normally highly limited. This article analyzes data from follow-up surveys to initial surveys in which respondents broke off. By revealing comprehensive information on both complete responders and breakoffs, these data allow for a detailed analysis of breakoff.

We regard survey breakoff as a specific form of nonresponse. Survey nonresponse is problematic if nonrespondents differ systematically from respondents in their personal characteristics or their norms, values, attitudes, and their (political) behavior (Weisberg, 2005). Researchers accordingly could obtain biased estimates and draw wrong conclusions. Thus, the first goal of our article is to study how complete responders and breakoffs differ with respect to sociodemographics, perceptions of the survey, political attitudes, and political behavior. This aspect is important …

Access/Direct link

Homepage (Abstract)/ (Full text)

Year of publication2014
Bibliographic typeJournal article
Full text availabilityAvailable on request