摘要
本文以压缩主成分估计为基础,对广义线性模型的最优预测与经典预测的最优性判别问题进行了讨论,获得了在离差矩阵判别准则和广义风险函数判别准则下判断两类预测量最优性的一个充分条件,为进一步研究基于有偏估计关于两类预测量的最优性判别问题提供了一种方法和思路。
Considering the generalized linear regression model and its prediction problem of biased estimation, this paper discusses its superiority of the optimal and classical predictors based on the shrunken principal estimator by criteria of mean dispersion error matrix and generalized risk function. A sufficient condition of comparison of its superiority is given under the condition of above criteria. An alternative method is proposed for the further research of superiority of two predictors based on the biased estimation .
出处
《武汉科技学院学报》
2007年第12期34-37,共4页
Journal of Wuhan Institute of Science and Technology
关键词
预测
压缩主成分估计
离差矩阵
广义风险函数
predictor
shrunken principal estimator
mean dispersion error matrix
generalized risk function
