Non-Separable Preferences in the Statistical Analysis of Roll Call Votes

Abstract Conventional multidimensional statistical models of roll call votes assume that legislators’ preferences are additively separable over dimensions. In this article, we introduce an item response model allows for non-separability latent Conceptually, matters if outcomes dimensions related rather than independent in decisions. Monte Carlo simulations highlight capture via correlated ideal points and higher salience a primary dimension. We apply our to the U.S. Senate European Parliament. both settings, find two basic non-separable. These results have general implications understanding legislative decision-making, as well empirical descriptions legislatures.