Great video. Just started learning about Bayesian statistics, and we haven't been told why we were working with this distribution. This makes so much more sense now.
Your tuts are always my go-to resource when trying to learn some new Machine Learning concepts. Straightforward and beginner friendly, making it easy for me to understand. Thank you for your hard work.
So favorite distributions: beta, normal, and Poisson. Glad you did a video on beta distribution. I've found beta distribution to be really helpful in the real world. You can boil alot of things down into a binary outcome in the real world. Like if someone is going to click something or not or make a purchase. Something I wish most curriculum did was dive in more deeper into distributions. Alot of classes teach it but don't really go into detail on how you can apply it. Wish for example, there was more simulation assignments or fun real world applications of it. Thanks for helping bridge the education gap and making these videos fun and easy and informative.
Great video! It would be amazing to have the cards you are using available for purchase, or imagine an app where people can review topics using those cards that would be awesome! Very concise, yet triggers all the right questions.
Excellent explanation! I'm already somewhat familiar with the beta, but I really liked your treatment of the mean and variance and the relationship between those and the variance of the sampling distribution of a proportion. I thought that really it really tied the room together, like a really good rug.
Ritvik falling in love with Data Science thanks to you! You explain complex topics so well. Just curious which our your top 3 distributions in data science. Would love to hear the names. Thank you again for sharing your knowledge so generously!!!
Love to hear that and excited for your journey through data science. Hmmm right now my top 3 distributions would have to be: - Normal Distribution - Beta Distribution - Poisson Distribution But there’s so many other good ones out there!
Finally found the intro I've been looking for on this topic. Really clear in how you explain the concepts without getting bogged down in equations. Question: can this be used even if I'm trying to model very low probability? Eg after sixty days R=0 and B=60. Does mean and sd still make sense?
@ritvikmath Thanks for the great explanation! Have you done more on Bayesian stats and how to apply the prior binomial distribution to the beta? I'm been looking for explanations of Bayesian updating.
Thank you for the great video! I just have a quick question! So the empirical proportion becomes the mode right? But you later explained that the mean ends up being the empirical proportion. Shouldn't the two be different?
Was reading an article and came across the Beta distribution so wanted to understand more about it. Thank you for the clear and intuitive explanation. I think it's kinda funny that the distribution is written as Beta(Success+1, Failure +1). I mean, why not just let it be Beta(Success, Failure), it's simpler that way. Is it just stats being stats, or is there a good reason behind this?
I was buying a used book through Amazon this evening. Three resellers offered the book at essentially the same price. Here were their ratings: 94% positive out of 85,193 reviews 98% positive out of 20,785 reviews 99% positive out of 840 reviews Which reseller is likely to give the best service? Do you approach this question thru beta distribution?
Great video. Just started learning about Bayesian statistics, and we haven't been told why we were working with this distribution. This makes so much more sense now.
Glad it was helpful!
Loving your intuitive approach to mathematics .... this is how it should be !
Glad you think so!
THANK YOU SO MUCH! I am shocked at the fact the professors don't talk about this, and start using it all of a sudden in class.
glad I could fill in a gap!
Your tuts are always my go-to resource when trying to learn some new Machine Learning concepts. Straightforward and beginner friendly, making it easy for me to understand. Thank you for your hard work.
Glad to help!
Do one for gamma distribution too! This explanation is so clear and intuitive. Love it!
Really a standout video from this channel. Perfectly intuitive
Glad you think so!
A very clear explanation, which helps me a lot
So favorite distributions: beta, normal, and Poisson.
Glad you did a video on beta distribution.
I've found beta distribution to be really helpful in the real world. You can boil alot of things down into a binary outcome in the real world. Like if someone is going to click something or not or make a purchase.
Something I wish most curriculum did was dive in more deeper into distributions. Alot of classes teach it but don't really go into detail on how you can apply it. Wish for example, there was more simulation assignments or fun real world applications of it.
Thanks for helping bridge the education gap and making these videos fun and easy and informative.
Thanks for the insights!
Great video! It would be amazing to have the cards you are using available for purchase, or imagine an app where people can review topics using those cards that would be awesome! Very concise, yet triggers all the right questions.
Excellent explanation! I'm already somewhat familiar with the beta, but I really liked your treatment of the mean and variance and the relationship between those and the variance of the sampling distribution of a proportion. I thought that really it really tied the room together, like a really good rug.
Ritvik falling in love with Data Science thanks to you! You explain complex topics so well. Just curious which our your top 3 distributions in data science. Would love to hear the names. Thank you again for sharing your knowledge so generously!!!
Love to hear that and excited for your journey through data science. Hmmm right now my top 3 distributions would have to be:
- Normal Distribution
- Beta Distribution
- Poisson Distribution
But there’s so many other good ones out there!
This is an amazing video. Thank you for your intuitive approach in breaking it down!
Glad it was helpful!
You are talented. Thank you so much !
Great Sir, this is easiest and interesting presentation of a boring topic.
Thanks!
Not sure that this line of work is for you if you find this topic boring.
This is so helpful, thanks!
Glad it was helpful!
Thank you
well detailed explanation. perfect!
I don't have money to pay him so leaving a comment instead for the algo. He is the best.
Please consider writing a book in future if possible, it'll save many lives :)
Love the idea
Thanks, this was nice explanation !
Great video!
Thanks!
Excellent, thank you.
You are welcome!
Excellent. Thanks.
Glad you liked it!
Finally found the intro I've been looking for on this topic. Really clear in how you explain the concepts without getting bogged down in equations.
Question: can this be used even if I'm trying to model very low probability? Eg after sixty days R=0 and B=60. Does mean and sd still make sense?
@ritvikmath Thanks for the great explanation! Have you done more on Bayesian stats and how to apply the prior binomial distribution to the beta? I'm been looking for explanations of Bayesian updating.
Thank you for the great video! I just have a quick question!
So the empirical proportion becomes the mode right?
But you later explained that the mean ends up being the empirical proportion.
Shouldn't the two be different?
Was reading an article and came across the Beta distribution so wanted to understand more about it. Thank you for the clear and intuitive explanation.
I think it's kinda funny that the distribution is written as Beta(Success+1, Failure +1). I mean, why not just let it be Beta(Success, Failure), it's simpler that way. Is it just stats being stats, or is there a good reason behind this?
Great explanation.
But what if professor also have green shoes? Is there any distribution for that case?
Thank you!
You're welcome!
I was buying a used book through Amazon this evening. Three resellers offered the book at essentially the same price. Here were their ratings:
94% positive out of 85,193 reviews
98% positive out of 20,785 reviews
99% positive out of 840 reviews
Which reseller is likely to give the best service?
Do you approach this question thru beta distribution?
what if I want the range to be (-inf, inf)? Is there a similar distribution?
The Beta distribution is a parametrization of the Binomial distribution, I believe. So A, B must be non zero.
@@agnelomascarenhas8990 thanks 👍
Perhaps this is dumb but, what does the Y axis represent when looking at beta distributions? Can someone give me an intuitive example and explanation?
The left skew image of the Gamma or Inverse Gaussian?
Would love to see a vid from you on Tweedy GLMs.
Thanks for suggestions!
Top Three Distributions:
1. Discrete Uniform Distribution
2. Normal Distribution
3. Geometric distribution
Don't @ me
Haha! Solid choices
Replace 2 with a more generalized version. There are several. Can you guess which one(s) I'm currently using?
how are beta distribution and Montecarlo simulation related?
love your video. Very helpful🎉
Glad it was helpful!
It's a conjugate prior?
this is why i paid for internet