50 years ago statistician Frank Anscombe warned us that #dataviz is essential to good statistical analysis
To demonstrate the point he generated what is now known as “Anscombe’s quarter”.
Four datasets that share 10 statistical measures but are from different populations (1/2)
To demonstrate the point he generated what is now known as “Anscombe’s quarter”.
Four datasets that share 10 statistical measures but are from different populations (1/2)
In 2016 @AlbertoCairo produced the Datasaurus Dozen to make this point even more dramatically.
It’s absolutely wild that 50 years later we still need to communicate this to folks who have recently awarded STEM degrees.
Dataviz needs to be a fundamental part of data education
It’s absolutely wild that 50 years later we still need to communicate this to folks who have recently awarded STEM degrees.
Dataviz needs to be a fundamental part of data education
But also, we need to be forgiving of instructors who already have overburdened syllabi and would find it hard to include more than a passing mention of this issue.
Just like we need to be forgiving of me missing the actual 50 year anniversary by 4 days 😬
Just like we need to be forgiving of me missing the actual 50 year anniversary by 4 days 😬
• • •
Missing some Tweet in this thread? You can try to
force a refresh
