线性回归模型系数岭估计的改进研究

Research on improvement of ridge estimationof coefficients in linear regression models

对作者提出的c-k型估计,进行了进一步的研究.证明利用Stein式压缩技术可以改进岭估计(在均方误差意义下);同时给出了参数的最优值满足的条件.证明了c-k型估计的可容许性.文中的方法为病态线性回归模型系数的有偏估计提供了改进的技术途径.

Further research on the c-k class of estimators of the coefficientsis done. The ridge estimation isimproved by applyingthe idea of James-Stein regressionon this class of biased estimation, and thecondition the optimal value of the parameter satisfies is given. This class of biased estimationis proved to be admissible. The method proposed in this paper provides a technical way to the improvement of the biased estimation.