To Allow or Disallow Smartphone Participation in Web Surveys: Choosing Between the Potential for Coverage and Measurement Error

• Activity Number: 63
• Type: Topic Contributed
• Date/Time: Sunday, August 9, 2015 : 4:00 PM to 5:50 PM
• Sponsor: Survey Research Methods Section
• Author(s): Gregg Peterson* and Jamie Griffin and John LaFrance and JiaoJiao Li
• Companies: Institute for Social Research and Institute for Social Research and Market Strategies International and Market Strategies International

Abstract

In this paper, we attempt to demonstrate the coverage impact of disallowing smartphones, the futility of relying on warnings and recommendations about device usage, and we demonstrate how a well-chosen "mobile friendly" interface design can minimize the impact of non-response and measurement errors in web surveys that allow smartphone participation. We propose that in order to minimize Total Survey Error, researchers should allow smartphone participation on most surveys but simultaneously work hard to minimize measurement and non-response error by focusing on survey content, question types and interface designs. The paper draws on a review of literature, recent data from studies conducted at the University of Michigan's Survey Research Center demonstrating the growing trend of smartphone response to web surveys, and the results of experiments conducted by Market Strategies International -- the first tests approaches to discouraging smartphone survey taking on a customer service feedback survey; the second compares response distributions for smartphone and non-smartphone survey participants. The experiment compares multiple "mobile friendly" design alternatives to learn which des