Michael Boo-tancourt
banner
betanalpha.bsky.social
Michael Boo-tancourt
@betanalpha.bsky.social
Zealous modeler. Annoying statistician. Reluctant geometer. Support my writing at http://patreon.com/betanalpha. He/him.
Randomly sampling from SO(3).
November 23, 2025 at 5:02 PM
Did I tweak nearly every slide of my regression deck in preparation for next month’s charity course? Only one way to find out!

Join us by dropping a 50 USD donation to World Central Kitchen or United Farm Workers. A few sponsored spots available. Details at betanalpha.github.io/courses/.
November 18, 2025 at 5:26 AM
Curious how to justify statements like “linear is good enough”? Join us on Wed Dec 10 for a comprehensive introduction to regression to raise funds for World Central Kitchen and United Farm Workers. Course details and registration instructions at betanalpha.github.io/courses/.
November 12, 2025 at 3:10 PM
The Legend of Zelda: Skyward Sword
November 7, 2025 at 7:05 PM
🥂
November 5, 2025 at 2:49 AM
Wednesday, December 10!

Bayesian regression modeling!

Stan exercises!

Raising money for World Central Kitchen and United Farm Workers!

betanalpha.github.io/courses/!
November 4, 2025 at 2:33 PM
epsilon > 0
October 31, 2025 at 4:46 PM
Oh, do you not check your retros?
October 28, 2025 at 2:16 PM
Tesselate this
October 26, 2025 at 2:31 AM
Not all graphical models are the same. Join us in December to dig into the probabilistic modeling structure of Bayesian regression analysis while raising money for World Central Kitchen and United Farm Workers. For details on the course and how to register check out betanalpha.github.io/courses/.
October 21, 2025 at 2:24 PM
Up late balancing trees.
October 14, 2025 at 4:10 AM
On Wed Dec 10 join me to learn about what a regression model is, and what a regression model is not, while raising funds for World Central Kitchen and United Farm Workers. For details on how to register, sponsored registration possibilities, and more see betanalpha.github.io/courses/.
October 13, 2025 at 1:22 PM
👀👀👀
October 12, 2025 at 7:13 PM
I don't think there's anything that will satisfy anyone expecting a one sentence explanation (which, sadly, is most people) but given little bit of time I think the geometric picture where the odds ratio is a slope,
OR = N_success / N_failure
N_success = OR * N_failure
is reasonably intuitive.
September 25, 2025 at 2:57 AM
September 11, 2025 at 2:28 PM
September 10, 2025 at 1:54 PM
A cathedral for worshipping conditional probability theory.

www.symplectomorphic.com/assets/chapt...
September 9, 2025 at 1:33 PM
Recollection of a dream.
September 9, 2025 at 12:12 AM
Cinderella and the Three Attempted Partitions

www.symplectomorphic.com/assets/chapt...
September 8, 2025 at 1:56 PM
September 5, 2025 at 1:16 PM
Haha, or not.
September 4, 2025 at 2:20 PM
Testing...
September 4, 2025 at 1:20 PM
September 4, 2025 at 1:17 PM
September 3, 2025 at 2:20 PM
Icy to dull the transformation and hot to relax it away.

www.symplectomorphic.com/assets/chapt...
September 2, 2025 at 1:13 PM