Ridge Regression: Biased Estimation for Nonorthogonal Problems
Ridge Regression: Biased Estimation for Nonorthogonal Problems
复制标题
DOI：
10.1080/00401706.2000.10485983
复制
发表时间：
2000-02
期刊：
影响因子：
2.5
通讯作者：
A. E. Hoerl;R. Kennard
中科院分区：
文献类型：
--
作者：
A. E. Hoerl;R. Kennard
在多元回归中，它示出了基于最小残差平方和的参数估计具有不令人满意的高概率，如果不是不正确的，如果预测向量不是正交的。提出了一种基于在X′X的对角线上增加小的正量的估计方法。介绍了脊迹法，这是一种在二维空间中显示非正交效应的方法。然后说明如何增广X′X以获得具有较小均方误差的有偏估计。
In multiple regression it is shown that parameter estimates based on minimum residual sum of squares have a high probability of being unsatisfactory, if not incorrect, if the prediction vectors are not orthogonal. Proposed is an estimation procedure based on adding small positive quantities to the diagonal of X′X. Introduced is the ridge trace, a method for showing in two dimensions the effects of nonorthogonality. It is then shown how to augment X′X to obtain biased estimates with smaller mean square error.