Dynamic Ideal Point Estimation via Markov Chain Monte Carlo for the U.S. Supreme Court, 1953-1999

At the heart of attitudinal and strategic explanations of judicialbehavior is the assumption that justices have policy preferences.In this paper we employ Markov chain Monte Carlo methods tofit a Bayesian measurement model of ideal points for all justicesserving on the U.S. Supreme Court from 1953 through 1999. Weare particularly interested in determining to what extent idealpoints of justices change throughout their tenure on the Court.This is important because judicial politics scholars oftentimesinvoke preference measures that are time invariant. To investigatepreference change, we posit a dynamic item response model thatallows ideal points to change systematically over time. Additionally,we introduce Bayesian methods for fitting multivariate dynamiclinear models to political scientists. Our results suggest thatmany justices do not have temporally constant ideal points.Moreover, our ideal point estimates outperform existing measuresand explain judicial behavior quite well across civil rights,civil liberties, economics, and federalism cases.