Improving research communication with data visualisation

LMS Research Talks: CHICAS
8 January 2025

Dr Nicola Rennie

About me

Lecturer in Health Data Science within the Centre for Health Informatics, Computing, and Statistics.

Background in statistics, operational research (transport), and data science consultancy.

Collaborate with local NHS trusts on data science projects.

Co-author of Royal Statistical Society’s Best Practices for Data Visualisation guidance.

CHICAS logo

Why develop a data visualisation guide?

How did the Royal Statistical Society’s Best Practices for Data Visualisation guide start?

A survey in 2021 asked Royal Statistical Society (RSS) members their views on Significance magazine.

Respondents were asked, “What aspects of content could be improved?”

“Better, more consistent charts… I’d like to see a house style like The Economist”
“The figures are often difficult to read…”
“The plots sometimes look amateurish…”

Help wanted

“RSS publications seek data visualisation expert to develop best practice guidance.”

Andreas Krause, Idorsia Pharmaceuticals

Nicola Rennie, Lancaster University

Brian Tarran, Royal Statistical Society

What’s the aim of the guide?

The guide would:

Help contributors develop data visualisations that are appropriate for RSS publications.
Be a source of information to aid people in developing charts that are high quality, readable, effective at conveying information, and fulfill their intended purpose.
Summarise and link to authoritative advice on chart styles and formats for different types of data.
Show how to override software defaults in common data visualisation software and packages.

Skip forward quite a few months…

The rest of this talk…

In this session we will cover…

why you should visualise data;
some guidelines for making better charts;
examples of good and bad charts!

The role of visualisation

Why visualise data?

Data visualisation has two main purposes:

Exploratory data analysis and identifying data issues
Communicating insights and results

Communicating insights with data visualisation

Grab attention

Visualisations stand out. If a reader is short on time or uncertain about whether a document is of interest, an attention-grabbing visualisation may entice them to start reading.

Improve access to information

Textual descriptions can be lengthy and hard to read, and are frequently less precise than a visual depiction showing data points and axes.

Summarise content

Visual displays allow for summarising complex textual content, aiding the reader in memorising key points.

What are you trying to communicate?

Data visualisations must serve a purpose.

Ask yourself:

What is the purpose?
Does the visualisation support the purpose?
Is it quick, accurate, and intuitive?

Why do pie charts have a bad reputation?

“All variations [of pie charts] lead to overestimation of small values and underestimation of large ones.” Kesara and Skau (2016)

Why do 3D charts have a bad reputation?

On the plot on the left, how tall is the bar?

Designing better visualisations

Elements of charts

Layout
Aspect ratio
Lines
Points

Colours
Axes
Symbols
Legends

Orientation
Auxiliary elements
Dimensionality

Layouts, aspect ratios, and axes

Layouts, aspect ratios, and axes

Layouts, aspect ratios, and axes

Layouts, aspect ratios, and axes

Longer labels are best on the y-axis, horizontally.

Box plots are just summary statistics in disguise…

Box plots hide information.

Layouts, aspect ratios, and axes

Should the axes start at 0?

Layouts, aspect ratios, and axes

They don’t always have to start at zero…

Layouts, aspect ratios, and axes

Layouts, aspect ratios, and axes

Source: Georgia Department of Public Health

Layouts, aspect ratios, and axes

Order categories appropriately…

Default:

Magnitude ordered:

Naturally ordered:

Lines

Suggest an order
Suggest continuity

Multiple lines

Avoid spaghetti plots!

Multiple lines

Alternatives to spaghetti:

Show a smaller number of lines (e.g. compare a few countries to average)
Use facets (AKA small multiples)
Use colour only to highlight lines

Colours

Why use colours in data visualisation?

Colours should serve a purpose, e.g. discerning groups of data.
Colours can highlight or emphasise parts of your data.
Not always the most effective for, e.g. communicating differences between variables.