Forecasting Using Bayesian and Information-Theoretic Model Averaging
比较了贝叶斯模型平均与基于信息论的模型平均在预测英国通胀中的表现，发现后者是前者的有力替代方案，尤其适用于数据丰富的环境。
Model averaging often improves forecast accuracy over individual forecasts. It may also be seen as a means of forecasting in data-rich environments. Bayesian model averaging methods have been widely advocated, but a neglected frequentist approach is to use information-theoretic-based weights. We consider the use of information-theoretic model averaging in forecasting U.K. inflation, with a large dataset, and find that it can be a powerful alternative to Bayesian averaging schemes.