Recent Developments and Future Directions in Bayesian Model Averaging

Abstract

From a Bayesian point of view, the selection of a particular model from a universe of possible models can be characterized as a problem of uncertainty. The method of Bayesian model averaging quantifies model uncertainty by recognizing that not all models are equally good from a predictive point of view. Rather than choosing one model and assuming that the chosen model is the one that generated the data Bayesian model averaging obtains a weighted combination of the parameters of a subset of possible models, weighted by each models’ posterior model probability. This workshop provides an overview of Bayesian model averaging with a focus on recent developments and applications to propensity score analysis, missing data, and probabilistic forecasting of relevance to social science research.