1) Square loss and entropy loss function
平方损失和熵损失
2) quadratic loss
平方损失
1.
Simultaneous estimation of p(p≥3) location parameters is considered under quadratic loss.
在平方损失下，考虑ｐ（ｐ≥３）个位置参数的同时估计。
3) Squared error loss
平方损失
1.
Under squared error loss the Rao-blackwell Theorem about interval estimation is given.
在平方损失下给出了关于线性置信区间的Rao Blackwell定理,并证明了常用的置信区间是最优线性无偏置信区间。
2.
Under squared error loss and Linex loss,it shows that a MU predictor is Pitmanclosest within a given family of predictors.
在平方损失及Linex损失下证明了MU预测量是某一给定的预测量集合中的Pitman closest预测量。
5) entropy loss
熵损失
1.
The present paper discussed the function of entropy loss,the Bayes Estimation of two Ordered Geometrics under any prior distribution,and estimated the loss of function in different priori distribution of two ordered geometric overall Bayes.
在平方损失函数和熵损失函数下,分别讨论了序约束下对任何先验分布的两个几何总体参数的Bayes估计,给出了序约束下不同先验分布的两个几何总体的Bayes估计。
2.
In this paper it is shown for the entropy loss L(sum from to ^,∑ ) = tr(∑~-1 sum from to^) - log|Σ~-1 sum from to ^|-p the best affine equivariant estimator of the covariance matrix ∑ is inadmissible and an improved estimator is explicitly constructed.
本文在熵损失 Ｌ（ｓｕｍ ｆｒｏｍ ｔｏ ～，∑）＝ｔｒ（∑~－１，ｓｕｍ ｆｒｏｍ ｔｏ ～）－ｌｏｇ｜∑~－１ｓｕｍ ｆｒｏｍ ｔｏ～｜－ｐ下证明了协方差矩阵∑的最佳仿射同变估计是不容许的，且给出了其改进估计。
3.
Under the conditions of entropy loss and symmetric entropy loss,Bayes estimation is discussed of any two general parameters with prior Burr distribution under order constraint.
分别在熵损失和对称熵损失函数下,讨论了序约束下对任何先验分布的两个Burr分布总体参数的Bayes估计。
6) entropy loss function
熵损失
1.
In this paper,we discussed the case that the parameter has different prior information of the Burr distribution under entropy loss function,the Bayesian estimations,mltilayer Baysian estimations and the general form of the admissible estimator are given.
讨论了在熵损失函数下Burr分布的参数在不同先验分布下的Bayes估计,并且讨论了其多层Bayes估计,给出了容许性估计的一般形式。
2.
This paper started with the general form of one-parameter exponential family function, and considered the Bayesian Estimation under the entropy loss function by mathematical calculations.
Bayes解在不同的损失函数下一般有不同的表现形式,本文根据平方损失下Bayes估计的计算思想方法,探讨了单参数指数族一般形式下,采用熵损失得到Bayes估计一般形式的过程,给出了有用的推论,并对正态分布、二项分布、泊松分布、瑞利分布、指数分布、伽玛分布、几何分布的参数进行说明验证。
补充资料：极端损失
极端损失指的是极端事件发生时银行所遭受的损失。在极端情况下，银行可能会丧失全部资产。
说明：补充资料仅用于学习参考，请勿用于其它任何用途。
参考词条