简体   繁体   English

我可以对分类数据应用方差膨胀因子 (VIF) 吗?

[英]Can I apply the variance inflation factor (VIF) for classified data?

All columns' values are class labels.所有列的值都是 class 标签。 For example: value "1" for feature1 is <50.例如:feature1 的值“1”小于 50。 Namely, all features were classified.也就是说,所有特征都被分类了。 In this case, can I apply the variance inflation factor (VIF) directly?在这种情况下,我可以直接应用方差膨胀因子(VIF)吗?

Dataset:
    feature1 feature2 feature3 target
        5       1         4      1
        1       1         3      0
        9       3         2      1

You have to be careful with VIFs, as they are not always calculated in the way that you understand.您必须小心使用 VIF,因为它们并不总是按照您理解的方式计算。 My suggestion is to calculate the VIF with numerical variables, in any case, you can make those variables dummies This article could give more explanation about: High VIFs are indicator (dummy) variables that represent a categorical variable with three or more categories我的建议是用数值变量计算 VIF,在任何情况下,您都可以使这些变量虚拟 这篇文章可以给出更多解释:高 VIF 是指示(虚拟)变量,表示具有三个或更多类别的分类变量

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM