ggplot2: Adding mean on individual data with standard error from 2 variables

Question

This is my first time using this platform. I hope I am doing this right. I am trying to add a group mean on top of individual data in a standard geom_point() graph from two groups. I got that part covered quite fast (see code below). The data I want to show are from two continuous variables.

The problem is that I would like the group mean to represent not only the mean, but also the standard error of the means (from each of the two variables). I thought a "+" sign with different height and width according to each variable would be a good idea, but I don't find anywhere how to change the Height and the Width (separately) of a single point.

So far, the code resemble this:

DataMean <- Data %>% 
        group_by(Group) %>% 
        summarise(x = mean(x),
                  y= mean(y))

ggplot(Data, aes(x = x, y = y, shape = as.factor(Group))) +
  geom_point() +
  geom_point(data = DataMean, size = 4, shape = 3)

Shape 3 being the "+" sign in R. However, I do not know how to change the height/width of the vertical/horizontal bar of that "+" sign in order to make it correspond to each groups' standard error of the mean. So far, I obtain the graph below.

Thanks and have a great day. Graph

It's easier to help you if you include a simple [reproducible example](https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example) with sample input and desired output that can be used to test and verify possible solutions. — MrFlick, Jun 18 '21 at 18:13

score 1 · Answer 1 · answered Jun 18 '21 at 18:36

In order to plot a cross with ranges proportional to the data's variability (the standard error of the means), use two geom_linerange layers with the ranges computed based on the standard errors.

library(dplyr)
library(ggplot2)

DataMean <- Data %>%
  group_by(Group) %>%
  summarise(across(everything(), list(mean = mean, sd = sd), .names = "{.col}_{.fn}"))

DataMean
## A tibble: 3 x 5
#  Group      x_mean  x_sd y_mean  y_sd
#  <fct>       <dbl> <dbl>  <dbl> <dbl>
#1 setosa       1.46 0.174  0.246 0.105
#2 versicolor   4.26 0.470  1.33  0.198
#3 virginica    5.55 0.552  2.03  0.275

ggplot() +
  geom_point(data = Data, aes(x, y, group = Group)) +
  # vertical bars
  geom_linerange(
    data = DataMean,
    mapping = aes(
      x = x_mean,
      ymin = y_mean - y_sd, ymax = y_mean + y_sd)) +
  # horizontal bars
  geom_linerange(
    data = DataMean,
    mapping = aes(
      x = x_mean, xmin = x_mean - x_sd, xmax = x_mean + x_sd,
      y = y_mean)
  ) +
  theme_bw()

Test data

Data <- iris[3:5]
names(Data) <- c("x", "y", "Group")

ggplot2: Adding mean on individual data with standard error from 2 variables

1 Answers1

Test data