摘要
在多元回归模型建立的过程中,由于各个变量的测量单位不相同,多元回归模型无法正确地评估出各个分量对预测值直接的和间接的影响.为此,引入路径系数,将多元回归模型转化为多元标准回归模型,通过变量间的相关系数和多元标准回归模型,分析预测变量对响应变量的直接和间接影响.
The model of multi-regression cannot correctly distinguish the direct and indirect effects from different components in the process of building because the measuring units have differences. In order to solve the problem, we introduce the routing coefficient model, transform the model into standard. We can anaUyze the direct and indirect effects to the prediction value by use of the correlate coefficient and the standard multi-regression model.
出处
《湛江师范学院学报》
2006年第6期122-124,共3页
Journal of Zhanjiang Normal College
关键词
多元回归
预测
标准回归模型
路径系数
multi-regression
model prediction
standard multi-regression
routing coefficient