回归模型中异方差的检验方法

Testing Methods of Heteroscedasticity in Regression Models

异方差的存在并不破坏普通最小二乘法估计量的无偏性,但是估计量的方差变大了,由于估计量方差的变大,就使通常假设检验的值不可靠,因此选取适当的异方差的检验方法是极其重要的.

Athough the existence of heteroscedasticity does not destroy the unbiasedness of the OLS estimators,the variances become larger. Thus,it makes the heteroscedasticity unreliable. Thus, it is of great significance to choose the proper testingmethods of heteroscedasticity. In this article, we summarize and evaluate several methods that are often utilized to test heteroscedasticity in detail, and discuss advantages and defects of these methods.