How to add a line in boxplot?

Question

I would like to add lines between \"mean\" in my boxplot.

My code:

library(ggplot2)
library(ggthemes)

Gp=factor(c(rep(\"G1\",80),rep(\"G2\",80)))
Fc=fac         


        

Answer 1

You can try a tidyverse solution as well:

library(tidyverse)
DATA %>% 
   ggplot() + 
   geom_boxplot(aes(X, Y, fill=Z)) +
   stat_summary(aes(X, Y,fill=Z),fun.y = mean, geom = "point",
                position=position_nudge(x=c(-0.185,0.185))) +
   geom_segment(data=. %>%
                  group_by(X, Z, Gp , Fc) %>% 
                  summarise(M=mean(Y)) %>% 
                  ungroup() %>% 
                  mutate(Z=paste0("C",Z)) %>% 
                  spread(Z, M), aes(x = as.numeric(X)-0.185, y = C100, 
                    xend = as.numeric(X)+0.185, yend = C50)) +
   facet_grid(Gp ~ Fc)

The idea is the same as in the answer of d.b.. Create a data.frame for the geom_segment call. the advantage is the dplyr workflow. So everything is done in one run.

DATA %>% 
  group_by(X, Z, Gp , Fc) %>% 
  summarise(M=mean(Y)) %>% 
  ungroup() %>% 
  mutate(Z=paste0("C",Z)) %>% 
  spread(Z, M) 
# A tibble: 8 x 5
       X     Gp     Fc  C100   C50
*     
1     B1     G1    FC1 0.169 0.281
2     B1     G1    FC2 0.170 0.294
3     B1     G2    FC1 0.193 0.270
4     B1     G2    FC2 0.168 0.269
5     B2     G1    FC1 0.171 0.276
6     B2     G1    FC2 0.161 0.292
7     B2     G2    FC1 0.188 0.269
8     B2     G2    FC2 0.163 0.264

Or you can try a slighlty different approach compared to Julius' answer. Add breaks and labels to get the expected output and play around with some offset on a numeric X2 and the width parameter within the boxplot function to get the boxes plotted together.

DATA %>% 
  mutate(X2=as.numeric(interaction(Z, X))) %>% 
  mutate(X2=ifelse(Z==100, X2 + 0.2, X2 - 0.2)) %>% 
  ggplot(aes(X2, Y, fill=Z, group=X2)) + 
   geom_boxplot(width=0.6) +
   stat_summary(fun.y = mean, geom = "point") +
   stat_summary(aes(group = X),fun.y = mean, geom = "line") +
   facet_grid(Gp ~ Fc) +
   scale_x_continuous(breaks = c(1.5,3.5), labels = c("B1","B2"),
                        minor_breaks = NULL, limits=c(0.5,4.5))