We analyze the combination of multiple predictive distributions for time series data when all forecasts are misspecified. We show that a specific dynamic form of Bayesian predictive synthesis -- a general and coherent Bayesian framework for ensemble methods -- produces exact minimax predictive densities with regard to Kullback-Leibler loss, providing theoretical support for finite sample predictive performance over existing ensemble methods. A simulation study that highlights this theoretical result is presented, showing that dynamic Bayesian predictive synthesis is superior to other ensemble methods using multiple metrics.

翻译：当所有的预测都被错误地描述时,我们分析对时间序列数据的多重预测分布组合。我们显示,一种具体动态的贝叶西亚预测合成形式 -- -- 一个通用的、连贯的贝叶西亚共同方法框架 -- -- 产生与Kullback-Leebler损失有关的精确微小预测密度,为相对于现有共同方法的有限抽样预测性能提供理论支持。我们介绍了一项模拟研究,其中强调了这一理论结果,表明动态贝叶西亚预测性合成优于使用多种指标的其他共同方法。