The Effective Statistician - in association with PSI

The Effective Statistician - in association with PSI

The Effective Statistician - in association with PSI

Why and how to declutter and simplify your data visualization

Download it: MP3 | AAC | OGG | OPUS

Click this link to go to the homepage of this episode!

In episode 3 of this mini-series, I discuss the impact of simplified data visualization and how to achieve it. Specifically, I address these factors that affect your visualization:

  • Clutter

  • Mis-alignment
    • Too many visual lines
      • Example misalinged header, legends,
    • Long categories below vertical bar charts not fitting well under the bars (avoid diagonal)
    • How many horizontal and vertical lines (start and stop of visual elements) do you have?
    • Can you avoid a legend?
    • Do you need these gridlines?
    • Do you need tickmarks?
  • Too many elements like
    • Colour
    • Fonts
    • Bold, italic
    • Annotations
    • Header, subheader, sub-subheader
  • “Unnecessary” annotations
    • File names
    • Source data
    • Program name
    • Validation status
  • Understand gestalt principles
    • Proximity - put the description for treatment next to the lines - not in a legend
    • Similarity - re-use color for the lines and the font color of the treatment
    • Enclosure- box around the most important area (e.g. randomized period vs open-label follow up)
    • Continuity - bars being organized below each other have a same starting point - take out the line showing baseline
    • Connection - connect what belongs together - line charts over time
    • Closure - take away the box around your overall vis

Learn more on how to create simple but effective data visualization by listening to this podcast and share this with others who might learn from it!


New comment

By submitting your comment you agree that the content of the field "Name or nickname" will be stored and shown publicly next to your comment. Using your real name is optional.

About this podcast

The podcast from statisticians for statisticians to have a bigger impact at work. This podcast is set up in association with PSI - Promoting Statistical Insight. This podcast helps you to grow your leadership skills, learn about ongoing discussions in the scientific community, build you knowledge about the health sector and be more efficient at work. This podcast helps statisticians at all levels with and without management experience. It is targeted towards the health, but lots of topics will be important for the wider data scientists community.

by Alexander Schacht and Benjamin Piske, biometricians, statisticians and leaders in the pharma industry


Follow us