Uncertainty in Issue Placements and Spatial Voting

Abstract

Empirical applications of spatial voting approaches frequently rely on ordinal policy scales to measure the policy preferences of voters and their perceptions about party or candidate platforms. Even though it is well known that these placements are affected by uncertainty, only a few empirical voter choice models incorporate uncertainty into the choice rule. In this manuscript, we develop a two-stage approach to further the understanding of how uncertainty impacts on spatial issue voting. First, we model survey responses to ordinal policy scales where specific response styles capture the uncertainty structure in issue placements. At the second stage, we model voter choice and use the placements adjusted for the detected uncertainty as predictors in calculating spatial proximity. We apply the approach to the 2016 US presidential election and study voter preferences and perceptions of the two major candidate platforms on the traditional liberal-conservative scale and three specific issues. Our approach gives insights into how voters attribute issue positions and spatial voting behavior, and performs better than a voter choice model without accounting for uncertainty measured by AIC.