在 R 中为 ANOVA 设置对比度的问题

Question

For testing a specific hypothesis, I am trying to contrast a factor in R.

set.seed(24)
data <- data.frame(var = sample(1:100, 70, replace = TRUE),
              version = rep(c("v3", "v4", "v1", "v3", "v4","v2","v2"),times=10)) 

c1 <- c(1/3, -1, 1/3, 1/3) 
c2 <- c(0, -1, 1, 0) 
c3 <- c(0, -1, 0, 1)
c4 <- c(1, -1, 0, 0) 

mat <- cbind(c1, c2, c3, c4)

contrasts(data$version, how.many = 4) <- mat

model <- aov(var ~ version, data = data)

summary.aov(model, split=list(version=list("comparison1"=1,"comparison2"= 2,
                                       "comparison3"=3,"comparison4"= 4))) 

Why is there no result for comparison 4? How can I fix that? Thanks.

Answer 1

We specify the how.many parameter and it should work. According to ?contrasts

how.many -How many contrasts should be made. Defaults to one less than the number of levels of x. This need not be the same as the number of columns of value.

So, it is the default behavior we observe while doing the assignment without any how.many parameter

contrasts(data$var, how.many = 4) <- mat
contrasts(data$var)
#             c1 c2 c3 c4
#var1  0.3333333  0  0  1
#var2 -1.0000000 -1 -1 -1
#var3  0.3333333  1  0  0
#var4  0.3333333  0  1  0

data

set.seed(24)
data <- data.frame(var = sample(paste0("var", 1:4), 20, replace = TRUE))