回归系数的联合回归估计

United Regression Estimate for Regression Coefficients

本文提出了一种新的关于回归系数的有偏估计—联合回归估计.证明了在一定条件下,它优于最小二乘估计、主成分估计和组合主成分估计,且在均方误差意义下是可容许估计.

In this paper, a new biased estimate, which is called the united regression estimate, is proposed for the regression coeffients. Under the given conditions, the proposed estimate, which is found to be superior to the least squares estimate, the principal components estimate and the combinative principal components estimate, is an admissible estimate in the mean square error.