1) Stein-typed estimations
Stein型估计
1.
The purpose of this paper is to modify three calsses of biased estimations (Stein-typed estimations, double-h ridged estimations, double-l ridged estimations) so that these improved estimations could always be better than the least squared estimation in the sense of MSE.
对线性模型中回归系数的Stein型估计,双h类估计和双l类估计作了改进,使得它们在设计阵的任何情形下都能一致优于最小二乘估计。
2) Jame-Stein type estimator
James-Stein型估计
3) Stein-type OLS Estimate
stein型OLS估计
4) stein-type principal-componenets Estimate
stein型主成分估计
5) Stein estimator
Stein估计
1.
Then we discuss the superiority of the Stein estimator over LS estimator under Pitman closeness (PC) criterion.
本文在广义均方误差(GMSE)准则下给出了回归系数β的Stein估计优于最小二乘(LS)估计的充分必要条件,然后在Pitman Closeness(PC)准则下比较了Stein估计相对于LS估计的优良性。
6) Stein estimation
Stein估计
1.
Whittemore(1989) proposed Stein estimation of the unobserved true covariates,provided that the measurement error is Gaussian with known variance,when the variances of the measurement errors are equal in different observed points.
Whittemore(1989)针对在各观测点等误差的情形提出了一种参数估计的方法,其基本思想是:当观测误差来自方差已知的高斯分布时,用带有观测误差的观测样本的Stein估计代替不可观测的协变量的真实值。
补充资料:Behnke-Stein定理
Behnke-Stein定理
Behnke Stein theorem
Behnke一Stein定理{】khnke一Stein theore「n;1翻汉,耽U】Te俪a TeO碑M。] 设全纯域G、C=C”k=1,2,…,其中对所有的k有G;CG*刊,则它们的并仍然是全纯域·Behnke一stein定理不仅对复Eudid空间C”成立,而且对任何Stein流形(stein manifold)也成立.如果序列G*在嵌入意义下不是单调增加的,则定理不成立.例如CZ中两全纯域 G,={(z!:2):{:l】·(l,}z:阵艺}和 G:二{(:::2川:、{<2,}::1<玛的并不是全纯域.
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