Plots and Tables
2025-10-01
Mistakes in displaying data:
How to represent magnitudes dishonestly: π
How to represent magnitudes honestly: π
Why? The height of a bar plot makes us think in magnitudes.
Mistakes in displaying data:
Consider your audience
Labels directly on plots may also help with clarifying patterns
How to draw graphical elements unclearly: π
Unthinkingly accept default options from plotting programs
Do not consider how a diverse audience will consume your figure
How to draw graphical elements clearly: π
Reflect on plot design
Consider the diverse audience you are reaching and how they may interact with your plot
There is more than one way to define the whiskers in a boxplot
R (both base and ggplot) use the following. If there are no outliers, whiskers go up to max and min value
But how are outliers defined?
R uses the popular method of \(\text{lower fence}=Q1β1.5(IQR)\) and \(\text{upper fence}=Q3+1.5(IQR)\). If there are no values beyond these limits, it considers the dataset to not have outliers for the purposes of a boxplot:
If there are outliers, whiskers go up to \(Q3+1.5IQR\) and down to \(Q1-1.5IQR\) and outliers are shown as circles
A thread on plots that could use some TLC:
From: makeameme.org
B21: Biostatistics with R