Mutual information is a well-known tool to measure the mutual dependence between variables. In this paper, a Bayesian nonparametric estimation of mutual information is established by means of the Dirichlet process and the $k$-nearest neighbor distance. As a direct outcome of the estimation, an easy-to-implement test of independence is introduced through the relative belief ratio. Several theoretical properties of the approach are presented. The procedure is investigated through various examples where the results are compared to its frequentist counterpart and demonstrate a good performance.
翻译:在本文中,通过Drichlet进程和最近的邻里距离,确定了对相互信息的巴伊西亚非参数估计,作为这一估计的直接结果,通过相对的信仰比率,引入了易于执行的独立测试,介绍了这种方法的一些理论特性,通过各种实例对结果与常客对应方进行比较并显示良好表现的事例对程序进行了调查。