R Studio Australia: Guide to Data Visualisation and Statistical Research

• Variable names
• Data types
• Missing values
• Duplicate observations
• Extreme values
• Inconsistent categories
• Incorrect measurements

Cleaning data carefully helps reduce the possibility of drawing conclusions from inaccurate information.

What Is Data Visualisation?

Data visualisation involves presenting information using charts, graphs, and other visual formats. Good visualisation makes patterns and relationships easier to recognise.

R Studio works particularly well with R's visualisation ecosystem. For example, ggplot2 can be used to create different types of graphs, including scatter plots, bar charts, line graphs, and distribution plots. R Studio also provides dedicated functionality for viewing plots and working with visual outputs.

A good visualisation should have a clear purpose. Students should avoid adding charts simply to make a report appear more detailed.

Choosing the Right Chart

Different research questions require different visualisation techniques.

Bar charts are useful for comparing categories.

Line graphs can demonstrate changes over time.

Scatter plots can help investigate relationships between numerical variables.

Histograms can show the distribution of numerical data.