There are many types of variables. Understanding the different variable types is half of the battle when it comes to data visualisation.

Go to RStudio Cloud and open your session. Load in the Iris dataset:

iris <- datasets::iris

You can see a newly created Data object in your environment called iris with 150 obs of 5 variables.

There are two common methods to visualise the distribution of a single variable: using boxplots or histograms – both portray the same information.

boxplot(iris$Sepal.Width, horizontal = TRUE)
plot(density(iris$Sepal.Width))
hist(iris$Sepal.Width)

Boxplots

This section will focus on boxplots. Whilst they broadly convey the same information as histograms (the distribution of the data), boxplots are a more informative plot providing the user with a five-number summary of a set of data: 1) the minimum score 2) first (lower) quartile 3) median 4) third (upper) quartile and  5) maximum score.

• Minimum Score: The lowest score, excluding outliers (shown at the end of the left whisker).
• Lower Quartile: Twenty-five percent of scores fall below the lower quartile value (also known as the first quartile).
• Median: The median marks the mid-point of the data and is shown by the yellow line that divides the box into two parts (sometimes known as the second quartile). Half the scores are greater than or equal to this value and half are less.
• Upper Quartile: Seventy-five percent of the scores fall below the upper quartile value (also known as the third quartile). Thus, 25% of data are above this value.
• Maximum Score: The highest score, excluding outliers (shown at the end of the right whisker).

An outlier is an observation that is numerically distant from the rest of the data, and are represented as dots that fall outside of the range of the boxplot whiskers.

Visualising Relationships

To assess the relationship between two continuous variables, use a scatterplot. Simple pass the two variables to the plot() function which accepts as inputs vectors to plot x and y coordinates.

plot(iris$Petal.Length, iris$Petal.Width)

We can see that there is a positive relationship between the two variables – that is to say, as Petal.Width increases, so does Petal.Length. They have a positive correlation.

Visualising Nested Groups

In the previous example using boxplots, we viewed the distribution of one variable Sepal.Width for every sample in the Iris dataset. What if we wanted to compare Sepal.Width amongst the 3 flower species?

We will use the library ggpubr to do this – the code is relatively intuitive. Bypassing the column Species to the x-axis, the plot will automatically divide our data according to the three flower species:

library(ggpubr)
ggboxplot(iris, x = "Species", y = "Sepal.Width", bxp.errorbar = TRUE)

For histograms and scatter plots, use the parameter facet.by to create faceted plots – one plot for each grouping variable in a panel.

gghistogram(iris, x = "Sepal.Width", y = "..density..", facet.by = "Species")

ggscatter(iris, x = "Petal.Length", y = "Petal.Width", facet.by = "Species")

Enhancing Plots

Adding colours to plots make groups instantly stand out. To do this in ggpubr, you will need to specify the fill parameter with the grouping variable. This will fill in your histogram bars/boxplots with a unique colour according to the number of unique groups in the variable (for the iris dataset this is ‘Setosa’, ‘Versicolor’ and ‘Virginica’).

gghistogram(iris, x = "Sepal.Width", y = "..density..", add_density = T, fill = "Species", add = "median")

ggboxplot(iris, x = "Species", y = "Sepal.Width", fill = "Species", bxp.errorbar = T)

ggscatter(iris, x = "Petal.Length", y = "Petal.Width", color = "Species")