R in Action 学习笔记 － 第九章－Analysis of Variance

One-way ANOVA

> install.packages("multcomp")

> library(multcomp)

> attach(cholesterol)

条件：因为 one-way ANOVA 的因变量需要满足正态分布，并且各组等方差

In a one-way ANOVA, the dependent variable is assumed to be normally distributed, and have equal variance in each group 

Step-1：用QQPlot检查是否符合正态分布条件

use a Q-Q plot to assess the normality assumption 

> install.packages("car")

> library(car)

> qqPlot(lm(response~trt,data=cholesterol),simulate=TRUE,main="Q-Q Plot",labels=FALSE)

#data fall within the 95 percent confidence envelope, 

#suggesting that the normality assumption has been met fairly well 

Step-2: 用 ANOVA

> fit <- aov(response~trt)

> summary(fit)
            Df Sum Sq Mean Sq F value   Pr(>F)    
trt          4 1351.4   337.8   32.43 9.82e-13 ***
Residuals   45  468.8    10.4                     
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

结论：

The ANOVA F test for treatment (trt) is significant (p < .0001), providing evidence that the