多元正态混合模型下约束最大似然估计的相合性

摘要

提出了用约束最大似然的方法来估计多元正态混合模型的参数.在成分数固定情形下,证明了约束最大似然估计的强相合性.%A constrained maximum likelihood method is proposed for estimating the parameter of the multivariate normal mixture distribution.It is shown that the constrained maximum likelihood estimator is strongly consistent,if the number of components is fixed.