摘要
考虑线性回归模型Y=Xβ+e,e～(o,σ~2I)。其中观测数据y用TY代替,T是对称幂等矩阵,本文引进了基于变换数据的岭型估计。当岭参数非随机时,给出了其优于OLS—估计的充要条件。当岭参数随机时,给出了两种自适应岭型估计,并在误差正态假设下得到了其优良性质。
In this paper we introduce some ridge type estimators considering the standard linear regression model y=xβ+e, Where y is substituted by Ty, T being a symmetric idempotent matrix with non-randam ridge parameter a necessary and sufficient condition, superiori to the OLSE is obtained. Assuming normalitg of the distribution of disturbance in the model, Superiorty of two adaptive ridge type estimators over the OLSE is also obtained.
出处
《华北水利水电学院学报》
1992年第2期28-33,共6页
North China Institute of Water Conservancy and Hydroelectric Power
关键词
线性回归模型
对称幂等矩阵
岭型估计
Linear Regression Model
Symmitrical Idempotent Matrix
Ridge Type Estimators
