Attitudes, Uncertainty and Survey Responses

Abstract

Theory: We assume that survey respondents are uncertain about their attitudes, and that their attitudes about political issues can be understood as probability distributions. From this perspective, we derive the "expected value" survey response model. We also derive a dynamic model of attitude change, based on the notion that attitudes are uncertain. Hypotheses: This perspective on political attitudes leads to two predictions. The first is that uncertain respondents will show less variance in responses than certain respondents, and that the less certain will tend to give responses towards the midpoint of issue placement scales. The second is that uncertain respondents will have less stable opinions about political issues over time. Methods: These hypotheses are tested using new survey questions we have developed to measure respondent uncertainty. These survey questions have been included in three recent national surveys, two conducted by the Letters and Sciences Survey Center at the University of Wisconsin, Madison and the other by the National Election Studies. Results: We demonstrate that uncertain respondents are more likely that certain respondents to provide issue placements at the midpoint of the scale, controlling for many factors. Also, we show that uncertain respondents have less stable political attitudes than certain respondents.