Stanford CS109 Probability for Computer Scientists I Variance Bernoulli Binomial I 2022 I Lecture 7

To follow along with the course, visit the course website:
web.stanford.e...
Chris Piech
Assistant Professor of Computer Science at Stanford University
stanford.edu/~c...
Learn more about the course and how to enroll: online.stanfor...
To view all online courses and programs offered by Stanford, visit: online.stanford...

[@allantourin]

43:00 Using the binomial distribution to model NBA game odds is wrong. The negative binomial is the correct one, because we need the last trial to be a success. Moreover, we need to compute b*(4; 4, 0.55) + ... + b*(7; 4, 0.55), where b*(n; k, p) is the negative binomial distribution

[@mdrasheduzzaman7613]

I was thinking this way: It is stated that all the 7 matches are independent from each other (in anther words, the team playing better in a given day win the match). And to win a series, you don't need to win the last one. A team just have to win one more than their opposite team, in any possible combination of winning and losing. Here, it should be at least 4:3 (5:2, 6:1, 7:0, etc. were also the possibilities). To note, there is no "draw" in this series, a team either win or lose a match. So, binomial probability distribution is completely fine here. Do you agree? Or feel free to enlighten me.

[@BlooBleep]

It comes out to the same answer. Both are valid.

[@mdrasheduzzaman7613]

The expression at 27:27-27:29 was something else!😂😂

[@hichametaoufik8277]

for the exemple of NBA when i put the cdf for x=4 is not 0.608 as the sum of range form 4to7

[@xinpengkang2256]

I think prof means for real situation if you win 4 games and stop the game, the probability of winning is still 0.608, think of you lose the game, it's x

[@asma_shakeel]

Where can I get the psets?

[@suchalooser1175]

cooool!