Taking two-step Stein estimate and Pitman criterion for instance,the purpose of this text is to explain two-step estimates rationality under other criteria from the angle of protecting.

Then we discuss the superiority of the Stein estimator over LS estimator under Pitman closeness (PC) criterion.

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.

Research of improvement of Stein estimators of coefficients in linear regression models;

It is proved that the Stein estimators can be improved by minimizing the mean square error of the generalized c-K estimators or by specializing matrix K respectively,and the optimal values of the parameters are also obtained.

The necessary and sufficient condition that James-Stein estimator were better than least square (LS) estimator based on the balanced loss function.

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.