戈德菲尔德匡特检验的推广

The generalization of Goldfeld-Quandt Test

在大多数经济现象中,回归模型的随机扰动项并不具有同方差性,它可能随观察值的不同而变化。对这种异方差模型进行最小二乘估计,会产生严重的后果,因此研究异方差的检验方法具有重要意义。由于戈德菲尔德 匡特检验方法只适用于一个自变量,因此,本文对G Q检验进行了推广,说明在多变量的情况下,可以利用主成分对样本数据进行排序,从而解决了对多变量数据的排序问题,使戈德菲尔德 匡特异方差检验得到了推广,并举实例说明。

In most economic phenomena,the random disturbances of linear regression model have unequal variance. Sometimes the disturbances vary with the observations. If such Kind of heteroscedastic regression model is estimated by the method of OLS, it will bring about serious effect. So it is of great significance to study the hypothesis testing of heteroscedasticity. As Goldfeld-Quandt test can only be applied to one independent variable,it is generalized that, in Multivariate situation, the data can be arranged according to their principle components. Furthermore, one example is cited to support the theory.