自动使用 LRT 评估整个因子变量的显着性 [英] Automatically use LRT to assess significance of entire factor variable

问题描述

包含一个或多个因子变量的多变量回归模型的 R 输出不会自动包含模型中整个因子变量显着性的似然比检验 (LRT).例如:

R's output for a multivariable regression model including one or more factor variable does not automatically include a likelihood ratio test (LRT) of the significance of the entire factor variable in the model. For example:

fake = data.frame( x1=rnorm(100), x2=sample(LETTERS[1:4], 
       size=100, replace=TRUE), y=rnorm(100) )

head(fake)
          x1 x2          y
1  0.6152511  A  0.7682467
2 -0.8215727  A -0.5389245
3 -1.3287208  A -0.1797851
4  0.5837217  D  0.9509888
5 -0.2828024  C -0.9829126
6  0.3971358  B -0.4895091

m = lm(fake$y ~ fake$x1 + fake$x2)
summary(m)

如果我们想测试模型中整个变量x2的显着性，我们可以拟合一个简化的模型m.red并使用LRT:

If we want to test the significance of the entire variable x2 in the model, we can fit a reduced model m.red and use the LRT:

m.red = lm(fake$y ~ fake$x1)
anova(m, m.red, test="LRT")

但是如果模型中有很多因子变量，那么一遍又一遍地这样做会变得很荒谬.我必须相信有一些内置的方法?

But if you have many factor variables in a model, doing this over and over becomes ridiculous. I have to believe there is some built-in approach?

推荐答案

我认为您正在寻找 drop1:

drop1(m,test="Chisq")
## Single term deletions

## Model:
## fake$y ~ fake$x1 + fake$x2
##         Df Sum of Sq    RSS     AIC Pr(>Chi)
## <none>               79.814 -12.547         
## fake$x1  1   0.33741 80.152 -14.125   0.5160
## fake$x2  3   2.88510 82.699 -14.996   0.3142

这篇关于自动使用 LRT 评估整个因子变量的显着性的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！