R interaction.plot

Question

我想为我的数据绘制interaction.plot。

with(data, interaction.plot(biofeedback, diet, as.numeric(drug),
xlab="Biofeedback", ylab="Drug", ylim = c(0, 4), col = 2:3))

结果：

但显然这不正确，因为我的数据是：

##    biofeedback    diet drug pressure
## 1      present  absent    1      170
## 2      present  absent    1      175
## 3      present  absent    1      165
...
## 7      present present    1      161
## 8      present present    1      173
## 9      present present    1      157
...
## 19     present present    2      164
## 20     present present    2      166
## 21     present present    2      159
...

此数据对于当前drugs的缺席和当前Biofeedback有不同的diet。对于缺席drugs，它有一些diet。这些都没有显示在情节上。为什么呢？

dput(data) 



## structure(list(biofeedback = structure(c(2L, 2L, 2L, 2L, 2L, 
## 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
## 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 
## 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
## 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
## 1L, 1L, 1L), .Label = c("absent", "present"), class = "factor"), 
##     diet = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 
##     2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 
##     1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 
##     1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 
##     2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 
##     2L, 2L), .Label = c("absent", "present"), class = "factor"), 
##     drug = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 
##     1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 
##     3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 
##     1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
##     2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
##     3L, 3L), .Label = c("1", "2", "3"), class = "factor"), pressure = c(170L, 
##     175L, 165L, 180L, 160L, 158L, 161L, 173L, 157L, 152L, 181L, 
##     190L, 186L, 194L, 201L, 215L, 219L, 209L, 164L, 166L, 159L, 
##     182L, 187L, 174L, 180L, 187L, 199L, 170L, 204L, 194L, 162L, 
##     184L, 183L, 156L, 180L, 173L, 173L, 194L, 197L, 190L, 176L, 
##     198L, 164L, 190L, 169L, 164L, 176L, 175L, 189L, 194L, 217L, 
##     206L, 199L, 195L, 171L, 173L, 196L, 199L, 180L, 203L, 202L, 
##     228L, 190L, 206L, 224L, 204L, 205L, 199L, 170L, 160L, 179L, 
##     179L)), .Names = c("biofeedback", "diet", "drug", "pressure"
## ), row.names = c(NA, -72L), class = "data.frame")

Answer 1

看起来没有错误。每组的平均值为2.0，这是情节显示的。

> df$drug <- as.numeric(levels(df$drug))[df$drug]
> library(plyr)
> ddply(df, .(biofeedback, diet), summarise, val = mean(drug))
  biofeedback    diet val
1      absent  absent   2
2      absent present   2
3     present  absent   2
4     present present   2