The Dynamics of “Neither Agree Nor Disagree” Answers in Attitudinal Questions

Abstract

Abstract Attitudinal questions are an integral part of surveys in the social sciences. Previous research based on cross-sectional data has shown that both respondents’ characteristics and questionnaire design can lead to higher use of midpoint responses when questions are operationalized on uneven rating scales. To further current understanding of this phenomenon, in this article we apply hybrid regression models to analyze differences between respondents but also developmental changes within respondents, allowing for a more profound interpretation of the dynamics behind midpoint responses, theoretically explained by satisficing behavior. For our midpoint analyses, we use a set of attitudinal item blocks asked in the British Household Panel Survey (BHPS) from 1991 to 2008. Respondents’ reports and interviewers’ judgments offer satisficing-related indicators regarding ability and motivation, enabling particularly accurate analyses of midpoint response behavior in terms of the “neither agree nor disagree” option. Results show that depending on respondents’ specific characteristics, higher use of the midpoint cannot automatically be equated with nonsubstantive response behavior. Furthermore, we demonstrate that specific indicators related to low ability and motivation do not uniformly increase midpoint responses. Application of the hybrid model reveals that changes in respondents’ characteristics do not affect midpoint response. We speculate that there are unobserved personality attributes that affect the propensity to midpoint response and conclude by reflecting on reasons for the increase in midpoint responses over the years.