banner
betanalpha.bsky.social
Michael Boo-tancourt
@betanalpha.bsky.social
2.7K followers 160 following 1.6K posts
Zealous modeler. Annoying statistician. Reluctant geometer. Support my writing at http://patreon.com/betanalpha. He/him.
patreon.com
Posts Media Videos Starter Packs
Pinned
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · Oct 8
Are you excited about the elegant philosophy of Bayesian inference, but struggling to see how it can be applied beyond the idealized examples in introductory texts and tutorials? Over the past few months I’ve released a series of demonstrative analysis that might help. 👇
2 11 48
Reposted by Michael Boo-tancourt
konsta.happonen.eu
Konsta Happonen @konsta.happonen.eu · 1d
Relatedly, ages ago @betanalpha.bsky.social wrote "Remember that using Bayes' Theorem doesn't make you a Bayesian. Quantifying uncertainty with probability makes you a Bayesian". I still think about this regularly.
2 3 13
Reposted by Michael Boo-tancourt
banalplay.bsky.social
L @banalplay.bsky.social · 2d
When your custom character appears in a cut scene
The Portland frog backing down an army of jackboots
59 1.8K 9.7K
Reposted by Michael Boo-tancourt
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 2d
Friendly reminder that on Dec 10 I will be offering my Bayesian regression modeling course at a steep discount in an effort to raise funds for World Central Kitchen and United Farm Workers. Details about the course and registration process can be found on my website, betanalpha.github.io/courses/.
Courses
betanalpha.github.io
1 5
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 2d
> git check —retro
2
Reposted by Michael Boo-tancourt
stevehorton.mst3k.fan
Steve Horton is writing a graphic novel @stevehorton.mst3k.fan · 2d
fuck the moon @fuckthem00n FUCK THE MOON fly me to the moon let me kick it's fucking ass let me show it what i learned in my moon jujitsu class 3:05 PM • 10/17/19 • Twitter for Android 28K Retweets 111K Likes FUCK THE MOON fuck the moon @fuckthem00n • 1d wow this blew up. wish the moon would. 29 LX238 4,182 V
1 12 95
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 2d
Friendly reminder that on Dec 10 I will be offering my Bayesian regression modeling course at a steep discount in an effort to raise funds for World Central Kitchen and United Farm Workers. Details about the course and registration process can be found on my website, betanalpha.github.io/courses/.
Courses
betanalpha.github.io
1 5
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 3d
Good news! There’s nothing predictive about them. Functions like that implement _retrodictive_ comparisons, making them PR checks which is slightly less embarrassing to say.

<steps off soapbox>
2 5
Reposted by Michael Boo-tancourt
dopestatistics.bsky.social
Dragon Moll Z 🎃 @dopestatistics.bsky.social · 3d
Telling my professor I cant turn in my homework because my expected value is now sentient
2 2 34
Reposted by Michael Boo-tancourt
almostsure.bsky.social
Almost Sure @almostsure.bsky.social · 3d
Helter skelter
1 2 7
Reposted by Michael Boo-tancourt
cscheid.net
Carlos Scheidegger @cscheid.net · 6d
In case it isn't clear: it's obviously the right thing because

1) one of those two options is easy to undo.
2) Given the choice, a command that is easy to undo should always be the easiest to reach for.
1 1 11
Reposted by Michael Boo-tancourt
bghgmg.bsky.social
ChûgFromABigHûgMûg @bghgmg.bsky.social · 6d
gender norms admit the existence of gender metrics which can be abstracted to gender topologies which, here, we categorify into gender locales, also known as pointless genders
1 4 11
Reposted by Michael Boo-tancourt
poorlydrawnlines.bsky.social
Poorly Drawn Lines @poorlydrawnlines.bsky.social · 6d
smarter
37 310
Reposted by Michael Boo-tancourt
chelseaparlett.bsky.social
Chelsea Parlett @chelseaparlett.bsky.social · 7d
HMC: *has lots of divergent transitions*

Me: *fixing it*
Russel from up saying “the target distribution must be explored”
1 2 31
Reposted by Michael Boo-tancourt
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 7d
On Wed, Dec 10 I will be offering my comprehensive introduction to regression modeling at a steep discount in an effort to raise funds for World Central Kitchen and United Farm Workers. Details about the course and registration process can be found on my website, betanalpha.github.io/courses/.
Courses
betanalpha.github.io
5 8
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 7d
On Wed, Dec 10 I will be offering my comprehensive introduction to regression modeling at a steep discount in an effort to raise funds for World Central Kitchen and United Farm Workers. Details about the course and registration process can be found on my website, betanalpha.github.io/courses/.
Courses
betanalpha.github.io
5 8
Reposted by Michael Boo-tancourt
thegatesofmel.blacksky.app
Mel @thegatesofmel.blacksky.app · 7d
This has had me #enshambled for two days.
12 66 180
Reposted by Michael Boo-tancourt
poorlydrawnlines.bsky.social
Poorly Drawn Lines @poorlydrawnlines.bsky.social · 8d
owl and seagull
4 110 620
Reposted by Michael Boo-tancourt
joshgondelman.bsky.social
Josh Gondelman @joshgondelman.bsky.social · 10d
Sure there’s no ethical consumption under capitalism but some of it is waaaaay less ethical.
2 83 580
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 14d
The key insight is that OR = 1 <-> p = 1/2 <-> symmetric line. Anything larger is a steeper line that moves towards p = 1, and anything smaller is a steeper line that moves towards p = 0.
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 14d
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.
1
Reposted by Michael Boo-tancourt
lolennui.bsky.social
Amy @lolennui.bsky.social · 14d
ladies if he’s a matador that is a huge red flag
48 370 2.6K
Reposted by Michael Boo-tancourt
mrgeorgewallace.bsky.social
George Wallace @mrgeorgewallace.bsky.social · 14d
What a weird-ass Rapture. Only the Constitution disappeared.
220 4.3K 19K
Reposted by Michael Boo-tancourt
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 14d
Full agreement with Danielle that odds ratios are strictly less interpretable, and hence useful, than probabilities when considering a homogeneous behavior. That said odds ratios do have some utility when considering _heterogeneous_ behaviors.
1 1 15
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 14d
"Alternatively this connection makes it clear that understanding logit probabilities is as subtle and complex as understanding special relativity, which may help set the proper expectations when approaching this material!"
2
betanalpha.bsky.social
Michael Boo-tancourt @betanalpha.bsky.social · 14d
Anyways for much more see Section 2.2 of betanalpha.github.io/assets/case_... (and the appendix if you want to learn how to impress your friends by dropping "rapidity" in casual conversation).
General Taylor Models
betanalpha.github.io
4