This article presents a formal explanation of the forecast combination puzzle, that simple combinations of point forecasts are repeatedly found to outperform sophisticated weighted combinations in empirical applications. The explanation lies in the effect of finite-sample error in estimating the...

The finite mixture distribution is proposed as an appropriate statistical model for a combined density forecast. Its implications for measures of uncertainty and disagreement, and for combining interval forecasts, are described. Related proposals in the literature and applications to the U.S....