摘要
在使用回归模型进行多元回归分析时,容易忽视"自变量不存在近似线性关系"这一应用条件,造成分析结果不准确甚至严重偏离变量间本来的依存关系。论文对多重共线性的产生原因、对线性回归模型的影响以及诊断方法进行了论述,并从理论和实例两个方面探讨了如何运用岭回归模型来克服和解决多重共线性问题。
With the popularity of computer application,multiple regression analysis has been extensively applied in production, as well as scientific research in practice. But in the application of multiple regression analysis, the application condition that there is no linear relationship between independent varia- bles is apt to be overlooked; therefore , the obtained result may become incorrect and even be far from the original relationship among the variables. Therefore, it is necessary to analyze the causes and the impact of multicollinearity in the linear regression model,and introduces some of the diagnosis methods of multicollinearity. Then this paper introduces the theory of the ridge regression model, and the scope of its application, as well as advantages and disadvantages. Then with the example of pork prices factors analysis and the aid of SAS program,this paper objectively evaluates the characteristics of the method and its strength and weakness.
出处
《华中农业大学学报（社会科学版）》
2008年第2期78-81,85,共5页
Journal of Huazhong Agricultural University(Social Sciences Edition)
关键词
多重回归分析
线性回归方程
多重共线性
multiple regression analysis
linear regression model
multicollinearity
