Thank you for taking the time to make and publish these - I normally do not like to learn from videos but the density of the information in these videos is well worth the time investment.
I’m here after finishing my MBA to unlearn the shit I had to study to earn my certificate, thank you Nassim ! I cannot believe that people who spend a lifetime in academia or working with statistics never sat and gave the concepts behind the theories they work with a deep thought, the Incerto makes more sense to me with time
I did some work on Stable distributions (as the error distribution on time series models) on my Stats undergrad back in ~2011. One of the worse things was the very heavy computational cost to compute integrals (which have no closed form most times). There were some pretty good approaches based on the empirical characteristic function, which is somewhat uncommon for the regular statistician. Fun stuff.
I usually keep my mouth shut because I am a fool. But I would like to say thank you so much for the knowledge. I will strive to get better to become less ignorant!
Discrete uniform distribution Bernoulli distribution (with p=0.5) Binomial distribution -> Gaussian distribution The first 3 have équiprobable outcomes Pareto distribution (observations are Not équiprobable)-> fat tailed Gaussian distribution
Good Morning Nassim, but the black & scholes do consider that the change of the stock price is a fat tail distribution, because they use the log normal distribution of the change of the stock price (gaussian) and not the distribution of the change of the stock price directly
I agree... I was reading a paper who claims that Student-t Distributions it's a better fit for estimate the daily returns of a stock than Black Scholes (underestimates) and Cauchy Distribution (overestimates). Do you agree? Which distribution is the best estimate considering the fat tails?
Mr Taleb - je vous remercier pour ces videos. J'ai q'un question: connaissez-vous la recherche sur la causalité de Bernhard Scholkopf et al? Qu'est-ce que vous pensez? C'est en quelque sorte frauduleux?
Prof. Taleb, would you mind discussing the true meaning of impact factors? A colleague argues that they too are subject to power law. However, our discussion couldn't truly come to a conclusion! It would be greatly appreciated! Thank you for your videos!
Hello Nassim! Have been following the entire series, its great! Just a small request, do a technical presentation of key topics from "Statistical Cons. of Fat Tails" too. Thanks!
Thank you. I watch these from behind enemy lines where I work on exposing the frauds in the data science industry. My ex colleagues all privately admit they have never done anything useful in their entire careers. Few bother to ponder why
@@nntalebproba Thank you. I wrote that comment before watching the whole video. After watching the whole video, I understood "summation". The reason why I asked if "sampling" was implied was because the way I was exposed to CLT in the past was: the plot of sample means (from any distribution, assuming a fixed sample size) should show up as a normal distribution.
nice video although i don't see what the second example shows when it's just a special case of the first, maybe if p was not 1/2 it would have been more interesting
Are you familiar with phase shifts in thermodynamics? How water turns from a liquid to a solid to a vapor depending on various combinations of temperature and pressure? I've always thought that financial markets behaved in a similar way, where most of the time they are in a "normal" phase, but then under the right conditions of debt/income ratios and uncertainty, they can shift to a "panic" phase. Is there any relationship of this idea of a phase shift to fat tails?
Of course there is a relationship in so far that if you want to model the size of an outcome at a randomly selected point of time, you will need a fat tailed distribution of some kind to capture that really large deviations from the normal phase can happen (even in practice). But if you want to study the phenomenon more closely you should probably look into dynamical systems instead. Check out Steven Strogatz for example.
To invoke the CLT you need a large enough sample size. Today, bootstrapping (a resampling method) allows the statistician to ignore the CLT and essentially substitute computational power for theory. In bootstrapping the computer repeatedly takes samples from your data with replacement to come up with the true distribution that governs your data, no need to assume normality as per Gaussian.
"here the sum or average, same thing, converge to a gaussian". Well both are inaccurate. The latter degenerates to a point, and the first one one has variance diverging to infinity 🙂. Something important is missing ... 🙂
Half of the reason I open these videos is to listen Taleb saying "Friends".
Amigos
kkkk.
É uma das poucas coisas que consigo entender bem, devido ao sotaque libanês dele que me dificulta um pouco a entender.
HAHA SAME
I can't believe I am watching a mini lecture by Nassim Taleb himself, for free. We live in a crazy time.
Yeah, my same thoughts.
Why? Is he a nobel laureate?
What's his invention?
@@hotupnorth8838 you both seem oblivious to the existence of internet
Of course 🙂👌
I was thinking the same thing.
No matter how much we'd have studied these elsewhere, I feel we get an enhanced perspective. Thanks Naseem.
Mr. Taleb, thank you for your books and these lectures!
Please do more lectures/courses, I think it will be significantly beneficial to society.
Man i feel lucky watching this. Nassim’s my favorite teacher i never had in school
"The central limit theorem it's what allows idiots to do statistics"
- N.N.Taleb 2022
Thank you for taking the time to make and publish these - I normally do not like to learn from videos but the density of the information in these videos is well worth the time investment.
Nassim, thank you for taking the time to put this together. And for free!
I’m here after finishing my MBA to unlearn the shit I had to study to earn my certificate, thank you Nassim !
I cannot believe that people who spend a lifetime in academia or working with statistics never sat and gave the concepts behind the theories they work with a deep thought, the Incerto makes more sense to me with time
Thank you for the lecture Profesor Taleb. This is a great complement to your last book.
Thank you. I read Fooled by Randomness in 2002 and have been following NN Taleb ever since. Thank you for these fantastic discussions.
Amazing...summed up my entire undergraduate probability class in one video.
I really enjoy these mini-lectures. Thanks a lot Mr Taleb!
I could listen to moocs all day. Thank you for sharing these!
Thanks Taleb for such a beautiful lecture! The last example was a killer! Absolutely WOW!😁👍🙏
Great work sir. Praying for your long life and good health. May more teachers become like you
Thanks. This is great, the other stats channels never mention the problem with thick tails and convergence
Just lovely. Keep'em coming fast and friendly
Are these videos getting out exponentially faster?
I did some work on Stable distributions (as the error distribution on time series models) on my Stats undergrad back in ~2011. One of the worse things was the very heavy computational cost to compute integrals (which have no closed form most times). There were some pretty good approaches based on the empirical characteristic function, which is somewhat uncommon for the regular statistician. Fun stuff.
Thank you again. Enjoyed seeing how the distributions converged as you added observations realtime. Very illustrative.
Excellent and simple explanation. Muchas gracias Maestro!
So much value in such short time!! Είσαι κορυφή Nassim!
Ευχαριστώ
I usually keep my mouth shut because I am a fool. But I would like to say thank you so much for the knowledge. I will strive to get better to become less ignorant!
Thanks Maestro. Very much appreciated.
You are very welcome
This is amazing. Thank you so much.
Amazing example. I will be teaching the same one today thanks to you!
I screamed in the middle of the video when it all clicked.
Thank you Professor for making such complex topics easily understandable in 10 minutes!
Discrete uniform distribution
Bernoulli distribution (with p=0.5)
Binomial distribution -> Gaussian distribution
The first 3 have équiprobable outcomes
Pareto distribution (observations are Not équiprobable)-> fat tailed Gaussian distribution
Many thanks, huge help to this aging liberal arts major
I LOVE IT. "ACTUALLY, IT ALLOWS IDIOTS TO USE STATISTICS." I LOVE IT.
When you get your "Friends" dose twice in a single video!
2estez ya Nassim!
Big thank you... Maestro. ❤️
This is amazing. Thanks so much for putting this together
Good Morning Nassim, but the black & scholes do consider that the change of the stock price is a fat tail distribution, because they use the log normal distribution of the change of the stock price (gaussian) and not the distribution of the change of the stock price directly
Yes but not enough.
I agree... I was reading a paper who claims that Student-t Distributions it's a better fit for estimate the daily returns of a stock than Black Scholes (underestimates) and Cauchy Distribution (overestimates). Do you agree? Which distribution is the best estimate considering the fat tails?
Thanks, Nassim. Please keep up the good work.
Thanks for this Nassim.
Watching him massage the data is really helpful
Oh my god!!! I can’t believe it!!!! Welcome!!!
Speechless! But what was the program you used for the visualisation? I was unable to read the typing, did get your point though. 😞
Thanks for the lesson! Which program is this, by the way?
Loving these mini lessons
What's the program you're using to run that?
Mr Taleb - je vous remercier pour ces videos. J'ai q'un question: connaissez-vous la recherche sur la causalité de Bernhard Scholkopf et al? Qu'est-ce que vous pensez? C'est en quelque sorte frauduleux?
Thanks Professor Taleb!
Prof. Taleb, would you mind discussing the true meaning of impact factors? A colleague argues that they too are subject to power law. However, our discussion couldn't truly come to a conclusion! It would be greatly appreciated! Thank you for your videos!
Central limit theorem works like a charm.
Does anyone know what software he is using here? Would love to tinker around myself.
Very clear, thank you
Can we have this series on a playlist
Hello Nassim! Have been following the entire series, its great! Just a small request, do a technical presentation of key topics from "Statistical Cons. of Fat Tails" too. Thanks!
So, in the end you got Landau distribution?
I didn't hear him say what the "r" stands for when he started playing around in Mathematica, did any of you catch what it means??
Thank you kindly ✍️
Thank you. I watch these from behind enemy lines where I work on exposing the frauds in the data science industry. My ex colleagues all privately admit they have never done anything useful in their entire careers. Few bother to ponder why
Reminds me of the 2 dices or more examples. The most common outcome would be 6.
5:08 the moment of clarity
moment o shock too
Btw. effect well-known to people who play board games with two dice.
Using Mathematica ... a man of erudition.
Thank you so much I was trying to find out what he was using. I just bought two books on how to use mathematica so I'm glad it was that 🤣
at 2:32 NNT says that via summation, a non-gaussian turns into a gaussian. What does he mean by "summation". Did he mean "sampling"? I think he did.
Summation.
@@nntalebproba Thank you. I wrote that comment before watching the whole video. After watching the whole video, I understood "summation". The reason why I asked if "sampling" was implied was because the way I was exposed to CLT in the past was: the plot of sample means (from any distribution, assuming a fixed sample size) should show up as a normal distribution.
Thank you. appreciate it.
Can anyone please let me know, What software NNT is using?
Mathematica
can anyone tell me the name of software he is using.
Mathematica
@@cob666fuk thanks
nice video although i don't see what the second example shows when it's just a special case of the first, maybe if p was not 1/2 it would have been more interesting
Merci beaucoup
Always great to rehearse the fundamentals.
Are you familiar with phase shifts in thermodynamics? How water turns from a liquid to a solid to a vapor depending on various combinations of temperature and pressure? I've always thought that financial markets behaved in a similar way, where most of the time they are in a "normal" phase, but then under the right conditions of debt/income ratios and uncertainty, they can shift to a "panic" phase. Is there any relationship of this idea of a phase shift to fat tails?
Of course there is a relationship in so far that if you want to model the size of an outcome at a randomly selected point of time, you will need a fat tailed distribution of some kind to capture that really large deviations from the normal phase can happen (even in practice). But if you want to study the phenomenon more closely you should probably look into dynamical systems instead. Check out Steven Strogatz for example.
What software is that
Wolfram Mathematica
To invoke the CLT you need a large enough sample size. Today, bootstrapping (a resampling method) allows the statistician to ignore the CLT and essentially substitute computational power for theory. In bootstrapping the computer repeatedly takes samples from your data with replacement to come up with the true distribution that governs your data, no need to assume normality as per Gaussian.
Luv u taleb
Thank you
Great lesson
Is r a random variable? and if so, does adding them mean the same thing as taking a sample from a population with a discrete uniform distribution?
You are taking samples and ADDING them.
What is the name of the software that Taleb is using in the examples in this video?
Looks like Wolfram Alpha Notebook.
Mathematica
@@avnavcgm thanks was looking for this
The quality of this video is nostalgic. Reminds me of how a 2007 laptop webcam used to be.
My mans
It took me a sec, but v+v+v is not the same thing as 3v in algebra.
Each v is a fresh Monte Carlo run.
"here the sum or average, same thing, converge to a gaussian". Well both are inaccurate. The latter degenerates to a point, and the first one one has variance diverging to infinity 🙂. Something important is missing ... 🙂
This is how a game of Settlers of Catan works
I hope he gets a dry erase white board. Clearer Me doesn't make that scrapy chalky sound.
Imagine thinking you know better than NNT because you bought a few Bitcoins.
Who the hell avoids new made drinks but wears bluetooth radiation headsets in the same breath
What is bluetooth radiation?
@@Sp0nge5 pure evil
Right at the start, did he say "actually, it's what allows Indians to do statistics" ?! LOL
No, says "actually, it's what allows idiots to do statistics"
any cs70 students here LMFAO
What app is that?
I was wandering too; I think someone said here Mathematica