Métodos Bayesianos para caracterizar el comportamiento legislativo del Senado colombiano en el periodo 2010 - 2014

Abstract

This work applies Bayesian methodologies to characterize the legislative behavior of the Colombian Senate during the 2010–2014 period. The analysis is done through the plenary roll-call votes of this legislative chamber. Furthermore, parliamentary electoral behavior is operationalized by implementing the one-dimensional standard Bayesian ideal point estimator by means of Markov chain Monte Carlo algorithms. The results mainly provide contributions in two directions: Political space dimensionality and pivotal legislators identification. Patterns revealed by the estimated ideal points suggest non–ideological latent trait (opposition–no opposition) underlying the vote of the Senate deputies. Thus, in addition to providing empirical evidence for a better understanding of legislative policy in Colombia during the period under analysis, this work also offers methodological, theoretical, and practical tools to guide the pre-processing and analysis of roll-call data in contexts of unbalanced parliaments (as opposed to the North American parliament), taking as a reference the particular case of the Colombian’s Senate.