Plots that went wrong

There’s loads of these on, here are some of mine from the past couple of years:

The beach?
You can never have too many violins
A nice smooth likelihood surface
Always good to see the zero contour
Apply some smoothing then I’m sure it will be fine, right?
R2 = 0.11, p < 10E-10


1) Let’s cram everything in to 1/10 of the space. 2) The ever so informative labels: ‘1’, ‘2’, ‘3’, …
Machine learning (or would we call this AI now?). Bonus: the large white bit at the bottom which I couldn’t get rid of
A more breezy Rothko
Sheet metal


One Reply to “Plots that went wrong”

  1. Some clunky scientists may say otherwise but It only just takes removing a little bit of outliers and a bit smoothing to make the patterns show themselves.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.