Bar plot with error bars in R

Here’s a simple way to make a bar plot with error bars three ways: standard deviation, standard error of the mean, and a 95% confidence interval. The key step is to precalculate the statistics for ggplot2.

n.per.group<-10
alpha<-0.05 # for a (1.00-alpha)=95% confidence interval

# Simulate raw data for an experiment or observational study.
data.raw <- data.frame(
	treatment=rep(c('A','B'), each=n.per.group),
	value=c(rnorm(n.per.group, 2), rnorm(n.per.group, 3))	
	)

# This data frame calculates statistics for each treatment.
data.summary <- data.frame(
	treatment=levels(data.raw$treatment),
	mean=tapply(data.raw$value, data.raw$treatment, mean),
	n=tapply(data.raw$value, data.raw$treatment, length),
	sd=tapply(data.raw$value, data.raw$treatment, sd)
	)

# Precalculate standard error of the mean (SEM)
data.summary$sem <- data.summary$sd/sqrt(data.summary$n)

# Precalculate margin of error for confidence interval
data.summary$me <- qt(1-alpha/2, df=data.summary$n)*data.summary$sem

# Load ggplot2 library
require(ggplot2)

# Use ggplot to draw the bar plot using the precalculated 95% CI.
png('barplot-ci.png') # Write to PNG
ggplot(data.summary, aes(x = treatment, y = mean)) +  
  geom_bar(position = position_dodge(), stat="identity", fill="blue") + 
  geom_errorbar(aes(ymin=mean-me, ymax=mean+me)) +
  ggtitle("Bar plot with 95% confidence intervals") + # plot title
  theme_bw() + # remove grey background (because Tufte said so)
  theme(panel.grid.major = element_blank()) # remove x and y major grid lines (because Tufte said so)
dev.off() # Close PNG

# Plot one standard error (standard error of the mean/SEM)
png('barplot-sem.png')
ggplot(data.summary, aes(x = treatment, y = mean)) +  
  geom_bar(position = position_dodge(), stat="identity", fill="blue") + 
  geom_errorbar(aes(ymin=mean-sem, ymax=mean+sem)) +
  ggtitle("Bar plot with standard error as error bars") + 
  theme_bw() +
  theme(panel.grid.major = element_blank())
dev.off()


# Plot one standard deviation
png('barplot-sd.png')
ggplot(data.summary, aes(x = treatment, y = mean)) +  
  geom_bar(position = position_dodge(), stat="identity", fill="blue") + 
  geom_errorbar(aes(ymin=mean-sd, ymax=mean+sd)) +
  ggtitle("Bar plot with standard deviation as error bars") + 
  theme_bw() + 
  theme(panel.grid.major = element_blank())
dev.off()

The plots:

Tested with R 2.15.2, R 3.0.2, and ggplot2 0.9.3.1. Recently ggplot2 has gone under some changes, and this code won’t work in earlier versions of ggplot2.

Advertisements