Live 2020-05-18!!! Bayes' Theorem

Today we're going to talk about Bayes' Theorem. This is one of those fundamental statistical concepts that underlies how statistics works. Understanding Bayes' Theorem is a key stepping stone towards understanding Bayesian statistics.

For a complete index of all the StatQuest videos, check out:

If you'd like to support StatQuest, please consider...
...or...

...buying a StatQuest Study Guide...

...a cool StatQuest t-shirt or sweatshirt:

...buying one or two of my songs (or go large and get a whole album!)

...or just donating to StatQuest!

Lastly, if you want to keep up with me as I research and create new StatQuests, follow me on twitter:

[mohammadmousavi]

You are on of the greatest channel here on YouTube.👍👍👍👍

[IshwarHosamani]

@23:46, shouldn't the p(no love C) be all the yellow AND red dots?

[taotaotan]

I feel learning Bayesian inference is particularly satisfying in stats and this really brings power to this simple equation.

[samson]

Perfect timing. I was studying Machine Learning at the time this was streamed. :D

[joaojulio]

"Oi brazil" got me dead AHAHAHAHAH Big BAM from Portugal! Underrated explanation, deserves way more than 14k views...

[Han-veuh]

I wish law of total probability was introduced to show how the denominator can be split to multiple terms and that one of these terms is exactly the numerator. That would be clearer than just portraying the denominator as 'scaling'. This was a key insight in helping me think intuitively when learning Bayes Theorem.
At 29:00 you mentioned its possible for likelihood to go over 1, and this denominator makes sure it never happens, however isn't the denominator a probability which is 0-1? How can a denominator capped at 1 scale down something bigger than 1 in numerator? Or this whole video is for discrete/multinomial naive bayes and likelihoods only appear in continuous gaussian naive bayes? How would the denominator look like in gaussian NB? (i couldn't find any mention of denominator in the gaussian NB video)

[PS-jrvi]

Hi Josh, I tried to connect to starquest.org to buy the study guides but it gives error:( can you kindly let me know where to buy them:) thankssss

[shieldofchaos]

What a nice timing! My exam is early next month and this is one of the chapter I am weak in!

[J]

It's so cool to see your "BAM's" live! - Trinidad and Tobago

[demondaze]

After looking for an eli5 explanations and getting all eli25 with math majors answers, I can finally rest my search here. As always Josh saves the day! <3
P.S. I'd like to request an eli5 on ZDDs(Zero-Supressed Decision Diagrams, I understand has more to do with CS than stats) and their applications to statistics.

[forestsunrise]

Each Bam of yours makes statistics sexier and sexier :D Thanks a lot Josh! You are the best!

[FaizFinance]

Always heard ur voice..first time see ur face..big fan from malaysia

[gloriouz]

Hi Josh! Thank you for your hard work and for this video!

[ksrajavel]

Thanks, Josh!!!
BTW, how did you manage to pause your aging process?

[lucha]

Love the video, it gave some very useful insights! Please explain MCMC in the future!

[DreamCodeLove]

Is there a video for hypothesis testing...?

[JscWilson]

The PayPal link on your channel has the name Laurence Torr... Just wanted to check if a tip would reach you?

[gigz]

It's ok that Stat Guy didn't have an accent. I can just imagine that Josh Starmer is telling us about a conversation that he had with Stat Guy.

[julieirwin]

Got the study guides, love it! Please do more, thank you Josh!

[paulsr]

Hey Josh, if I may make a request: can you do a video explaining the difference between how bayesian and frequentist approach to hypothesis testing differs? It looks like you're neck deep in neural networks but if I may put this in the queue. Much appreciated!