The Survey of Consumer Attitudes (SCA) is a monthly national RDD landline telephone panel survey conducted by the Survey Research Center at the University of Michigan. Since 2009 SCA has been investigating efficient and effective protocols for mail only, and multi-mode web and mail survey data collection in order to improve coverage and operation costs. These alternative modes are a response to increasing undercoverage, nonresponse, and operation costs in RDD landline telephone surveys (Curtin, Presser, and Singer 2005). Current thinking among some survey methodologists and practitioners is that there is an underlying attitude toward mode preference that subjects use to decide to participate in a survey. When multiple mode options are available, there is an expectation that a subject‘s propensity to respond will increase. Despite this expectation empirical evidence to date is mixed (Couper and Miller 2008). This paper presents findings from the SCA web-mail survey tests. Among the findings, the webmail multiple mode choice had response rates that were less than the mail only mode, which had survey response rates of 68.8% with a $5 prepaid incentive, or 54.5% without incentive. We explore significant predictors of response propensities in the web-mail survey examining data on both respondents and nonrespondents available from a prior wave of interviewing.

References: Couper, Mick, and Peter Miller. 2008. ―Web Survey Methods.‖ Public Opinion Quarterly 72(5) 831–835. Curtin, Richard, Stanley Presser, and Eleanor Singer. 2005. "Changes in Telephone Survey Nonresponse over the Past Quarter Century." Public Opinion Quarterly 69:87-98.