Skip to main content


Inspired by @derwinmcgeary's post (https://octodon.social/@derwinmcgeary/111921298436478955) from a couple of days ago, I wrote a quick blog entry about teaching, feedback, and regression towards the mean. I hope I didn't get the explanation wrong and that I understood the point correctly!

http://blog.juanrloaiza.com/posts/2024/03/teaching-feedback-and-regression-toward-the-mean/


Grab a couple of dice. Roll them.

If you get below 5, those are rookie numbers. Shout at the dice, let them know they're underperforming.

If you get above 9, that's what we want to see! They're good dice, and you should acknowledge that.

Repeat that and keep a record. You'll notice that negative feedback often results in better performance on the next roll. Positive feedback, conversely, can make them get lazy.

1/2


well, I definitely enjoyed it and it's a lovely lucid explanation!
Thank you! Happy to hear that :)
your odds are wrong though. If you roll a 3,there are 33/36 odds that the next throw will be be 4 or more which is 91.7% not 75% as there are many combinations that make up numbers nearer the mean.
you need to sum 2 6-sided dice, not use a 12 sided one.
@KevinMarks there are people who definitely feel the difference between 1d12 and 2d6 and I didn't spot it, partly because I was surprised at how clean the chart was even with 1d12
2d6 is a better illustration of regression to the mean, as it approximates a normal distribution rather than a uniform one. It does feel very different and that's partly why gambling games like craps (2d6) and Crown and Anchor (3d6) work, as the house advantage is hidden in the difference between the pias odds and actual odds