Abstract:

What is the impact of using 4-, 5-, 7-, 10- and 100-point scales on the internal consistency and reliability of survey data? What is the impact of using rich media and plain scales on the consistency and reliability of mobile survey data? Does the inclusion or exclusion of a neutral point have an impact on respondents’ evaluation of products or constructs? We’ll extend earlier research by comparing differences in response styles and scale reliabilities using multiple measurement scales. We’ll also examine the impact of dropping or retaining the neutral point in Likert-type scales, and address guidelines for designing global (online and mobile) surveys that yield more reliable results—all while adjusting for the impact of response styles across various countries and cultural regions.