Learning Bayesian Statistics cover image

#65 PyMC, Aeppl, & Aesara: the new cool kids on the block, with Ricardo Vieira

Learning Bayesian Statistics

00:00

Pims Version 3 - The Shape Issues

pi m c three grew very gradually, organically. One thing that kind of was not planned in advance was the dimensionality of our variables. We created a very stable a p p i about how the shapes of random variables should be handled. And we always start by just thinking about te pure case. So people might say, orka, instead of a normal distribution, i want a vactor of three volumes, each of one follows a normal distribution. For that you can give means, or You can give three sigmas, or you can give three means and three sigmas,. Or you can give one mean, one sigma. N just say, give me something with the shape

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
 Get the app