Bayesian Data Analysis

Abstract: For a Markov decision problem in which unknown transition probabilities serve as hidden state variables, we study the quality of two approximations to the decision rule of a Bayesian who each period updates his subjective distribution over the transition probabilities by Bayes’ law. The first is the usual rational expectations approximation that assumes that the decision maker knows the transition probabilities. The second approximation is a version of Kreps’ (1998) anticipated utility model in which decision makers update using Bayes’ law but optimize in a way that is myopic with respect to their updating of probabili- ties. For a range of consumption smoothing examples, the anticipated utility approximation outperforms the rational expectations approximation. The an- ticipated utility and Bayesian models augment market prices of risk relative to the rational expectations approximation.

TL;DR: In this article, the authors generalize the well-known mixtures of Gaussians approach to density estimation and the accompanying Expectation-Maximization technique for finding the maximum likelihood parameters of the mixture to the case where each data point carries an individual d-dimensional uncertainty covariance and has unique missing data properties.

TL;DR: This article attempts to comprehensively characterize the risks, synthesize the existing data available for modeling them, and present quantitative risk estimates that can provide a starting point for informing policy decisions.

TL;DR: A joint EEG/fMRI generative model and devoted VBEM learning scheme are built that explicitly accounts for local coupling/uncoupling of bioelectric and hemodynamic activities, which are supposed to share a common substrate.

TL;DR: This work adapts an algorithm and uses it to implement a general-purpose, multiple imputation model for missing data that is considerably faster and easier to use than the leading method recommended in the statistics literature.

TL;DR: This article used a multilevel Bayesian model to compare partisan bias and majoritarian bias across the Argentine provinces and showed large seat premiums for incumbent parties initiating electoral reforms, which can be applied to comparative analyses of electoral reforms within and across countries.

TL;DR: In this article, the authors examined the qualitative features of an anelasticity model associated with the bowing of dislocations in the presence of phase transition and proposed a simple physically plausible mechanism to describe the interaction of an elasticity and the transformation.

TL;DR: In this paper, a nonhomogeneous Markov hazard model with competing hazard rates was presented for the Japanese pavement system, where the dynamic selection of cracking condition states were undergone by a competing process of cracking types and damage levels.