Limitations of Ensemble Bayesian Model Averaging for Forecasting Social Science Problems

Abstract

A reanalysis and extension of Montgomery, Hollenbach, and Ward (2012) shows that the predictive performance of Ensemble Bayesian Model Averaging (EBMA) strongly depends on the conditions of the forecasting problem. EBMA is of limited value in situations with small samples and many component forecasts, a situation that is common for social science prediction problems. These results conform to a large body of research, which has determined that simple approaches to combining (such as equal weights) often perform as well as sophisticated approaches when combining forecasts. Simple averages are easy to describe, easy to understand, and easy to use. They should be favored over more complex methods unless one has strong evidence that differential weights will improve accuracy.

Keywords: combining forecasts, equal weights, election forecasting

JEL Classification: C1