New Frontiers in Bayesian Econometrics and Forecasting

The rich histories of Bayesian time series and econometrics are deeply intertwined, with each field advancing the other. Bayesian models (including state space models) have been remarkably successful for probabilistic forecasting and inference with economic data, including for macroeconomic indicators, monetary policy, and causal assessments of crises, recessions, and interventions, etc. At the same time, these and other urgent economic problems have motivated new Bayesian methods for modeling volatility, large cross-sectional data, mixed frequency data, and complex dynamic or seasonal behaviors, among many other examples. This session strives to continue the dialog between and mutual advancement of Bayesian time series and econometrics. This session features multiple layers of diversity within the ASA community, including diversity in gender and ethnicity; diversity in geography (domestically and internationally); diversity in rank (assistant, associate, and full professors); and diversity in research focus (including both statisticians and economists).