将它们分解为两项之积,指出强影响点、异常点、高杠杆点间的内在联系;
The decompositions clarify the relationship of influential observations, outliers, and high leverage cases.
城市空气质量回归预报模型的残差分布存在着不对称现象,它是由高杠杆点引起。
There exists asymmetry characteristic of residual distribution in the regression model of city air quality forecast. It is caused by some high leverage cases.
使用高杠杆值对模型进行分析诊断,探测出数据中的强影响点后,再建立一个改良模型。
Using the leverage value to detect this model and finding the mainly influential observation, an improvable model is built.
应用推荐