组内和组间的 Stat_compare_means

问题描述

这是我第一次尝试 R。我想使用 stat_compare_means 来比较子组内的均值以及来自不同子组的均值。我需要用治疗标记的 x 轴。 I am aiming for some thing like this

我的数据如下

    A tibble: 9 x 3
  Treatment Group     Count
  <chr>     <chr>     <dbl>
1   +         a        12
2   +         a        13
3   +         a        11
4   +         b        14
5   +         b        15
6   +         b        15
7   -         c        22
8   -         c        24
9   -         c        21 

我用 ggbarplot 和 geom_bar 尝试了几次，但都没有奏效。 stat_compare_means 甚至可以实现我的计划吗？任何帮助表示赞赏。

我最后一次尝试是这样的：

library(ggpubr)
library(ggplot2)
df <- structure(list(Treatment = c("+","+","-","-"),Group = c("a","a","b","c","c"),Count = c(12,13,11,14,15,22,24,21)),row.names = c(NA,-9),class = "data.frame")


ggbarplot(df,x = "Treatment",y = "Count",add = "mean_se",error.plot = "upper_errorbar",color = "Group",position = position_dodge(0.8))+

  stat_compare_means(df,comparisons = list(c("a","b" ),c("a",c("b","c")),label = "p.signif")  

哪个返回

Computation failed in `stat_signif()`:
Missing value,where TRUE/FALSE is needed

解决方法

尝试这样的事情：

library(ggpubr)
library(ggplot2)
#Comp
my_comparisons = list( c("+.a","+.b"),c("+.a","-.c"),c("+.b","-.c"))
#Plot
ggplot(df,aes(x=interaction(Treatment,Group),y=Count,fill=Group,group=Group))+
  geom_boxplot(position = position_dodge2(width = 0.5,preserve = 'single'))+
  theme_bw()+
  stat_compare_means(comparisons = my_comparisons,method = 't.test')+
  theme(legend.position = 'top',panel.grid = element_blank(),axis.text = element_text(face='bold',color='black'),axis.title = element_text(face='bold',strip.text = element_text(face='bold',legend.text = element_text(face='bold',legend.title = element_text(face='bold',plot.title = element_text(face='bold',color='black',hjust=0.5))+
  ggtitle('My plot')

输出：

使用的一些数据：

#Data
df <- structure(list(Treatment = c("+","+","-","-"),Group = c("a","a","b","c","c"),Count = c(12L,13L,11L,14L,15L,22L,24L,21L)),row.names = c(NA,-9L),class = "data.frame")