A novel analysis of the state space model is presented. It is shown that by modifying the standard recursive update it is possible to apply a copula model to eliminate a particular integral, which is typically performed using importance sampling. With Bayesian models, copulas have recently been shown to provide predictive densities directly, avoiding integrals altogether. As in every particle filter algorithm particles are generated; hence the proposed algorithm is named the Copula Particle Filter (CPF). As a by-product, the likelihood function of the model is obtained and used for parameter inference. Several illustrations and comparisons made with the standard updating schemes are provided. Supplementary material for this article, containing code, are available online.

提出了一种对状态空间模型的新颖分析。结果表明，通过修改标准递归更新，可以应用关联模型来消除特定的积分，这通常是使用重要性抽样来执行的。使用贝叶斯模型，最近已显示了copulas直接提供预测密度，完全避免了积分。像在每个粒子过滤器算法中一样，都会生成粒子。因此，所提出的算法被称为Copula粒子滤波器（CPF）。作为副产品，获得了模型的似然函数并将其用于参数推断。提供了一些与标准更新方案进行比较的说明和比较。可在线获取本文的补充材料，其中包含代码。