The Interaction Between Question Order and Delivery Mode (All Mail vs. Mixed Mode, Web+Mail)

• Activity Number: 356 - Contributed Poster Presentations: Survey Research Methods Section
• Type: Contributed
• Date/Time: Tuesday, August 1, 2017 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Laura Gamble* and Katherine McLaughlin and Virginia Lesser
• Companies: and Oregon State University and Oregon State University
• Keywords: Survey ; Sampling ; Mixed-Mode Survey ; Question Order

Abstract

In 2016, a probability sample of Oregon drivers was selected to participate in a satisfaction survey for the Oregon Department of Transportation. This study was conducted by the Survey Research Center at Oregon State University using a stratified sampling design. The survey was delivered using a mixed mode methodology, which randomized the sampled population into a web + mail group and an all mail group. In addition, within each of these groups, the effect of question order was examined. Two versions of the questionnaire were used to study the order of a general and specific question (i.e., examing a contrast effect) to determine whether or not the influence of question order was consistent between Web and paper respondents. Our findings show that responses for overall satisfaction are different between surveys where item order is switched. We now wish to will examine whether or not these results change when considering different survey modes. This poster will use chi-square tests to investigate the interaction between question order and other factors of interest-namely, delivery mode and demographic information-and their influence on overall satisfaction.