We consider equivariant estimation of location/scale parameters of a general bivariate distribution, under quite general conditions on underlying distributions and the loss function, when it is known apriori that these parameters satisfy a order restriction. This problem is broadly studied in the literature for specific probability models having independent marginals and specific loss functions. In most of these studies, sufficient conditions for inadmissibility of best location/scale equivariant estimators are provided. This paper generalizes these results by considering a quite general bivariate model and a quite general loss function. We provide sufficient conditions for inadmissibility of any location/scale equivariant estimator under general probability model (statistical dependent) and general loss function. We also provide some applications of the results obtained in this paper to specific probability models and loss functions that are not studied in the literature.
翻译:我们认为,在基本分布和损失功能的相当一般的条件下,在已知这些参数符合命令限制的情况下,对一般两变分布的地点/尺度参数进行等值估计,因为已知这些参数首先满足了命令限制;文献对具有独立的边际和具体损失功能的具体概率模型进行了广泛的研究;在大多数这些研究中,为不允许最佳位置/尺度等差估计机提供了充分的条件;本文件通过考虑相当一般的双变模式和相当一般的损失功能,概括了这些结果;我们为不允许采用一般概率模型(统计依赖)和一般损失功能的任何位置/尺度等差估计机提供了充分的条件;我们还对文献中未研究的具体概率模型和损失功能提供了本文中所获结果的一些应用。