PLS回归应用实例

Application of PLS regression

在研究因变量y与p个自变量的线性回归关系时 ,常遇到自变量间存在多重共线性的问题。文献 [3]介绍了用PLS回归来消除多重共线性的方法。本文通过两个例子的计算建立PLS回归 ,并发现了PLS回归实施过程中的若干问题 。

While building up the linear regression between response variable y and explanatory variables x 1,...,x p,there is often affection of multi-correlation. The literature has introduced the new method of PLS(Partial Least Squares) regression of eliminating multi-correlation. This paper sets up PLS regression with two examples, and has discovered several problems during the execution procedure, puts forward some views about them.