Second-Order Exchangeability Analysis for Multimodel Ensembles
Second-Order Exchangeability Analysis for Multimodel Ensembles
复制标题
多模型系综的二阶可交换性分析
DOI：
10.1080/01621459.2013.802963
复制
发表时间：
2013
影响因子：
3.7
通讯作者：
L. House
中科院分区：
文献类型：
--
作者：
J. Rougier;M. Goldstein;L. House
理解复杂系统的挑战往往会导致模型的多样性。考虑这些模型的输出是否可以组合起来产生比任何一个单独模型的输出更有信息量的系统预测是很自然的。并且，特别地，考虑模型输出的散布和系统不确定性之间的关系。我们描述了这样一个组合的统计框架，基于交换的模型，和他们的coexchangeries与系统。我们在气候预测的背景下展示了我们框架的最简单实现。在整个过程中，我们完全在均值和方差中工作，以避免指定高阶量的必要性，因为我们经常缺乏有根据的判断。
The challenge of understanding complex systems often gives rise to a multiplicity of models. It is natural to consider whether the outputs of these models can be combined to produce a system prediction that is more informative than the output of any one of the models taken in isolation. And, in particular, to consider the relationship between the spread of model outputs and system uncertainty. We describe a statistical framework for such a combination, based on the exchangeability of the models, and their coexchangeability with the system. We demonstrate the simplest implementation of our framework in the context of climate prediction. Throughout we work entirely in means and variances to avoid the necessity of specifying higher-order quantities for which we often lack well-founded judgments.
影响因子：
0.9
作者：
Goldstein, Michael;Rougier, Jonathan
通讯作者：
Rougier, Jonathan