Deleted tweet detection is currently running at reduced
capacity due to changes to the Twitter API. Some tweets that have been
deleted by the tweet author may not be labeled as deleted in the PolitiTweet
interface.
Showing page 262 of 658.
Nassim Nicholas Taleb @nntaleb
@uri_sohn Is your graph for equal weight averaging? — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@uri_sohn Mr Uri, is the below correct? This is not a "sum" of random variables, but a linear combination of mostly 1 and part of car 2. If a sum of 4 uniforms yields a mean = ½ std, the individuals must have a mean = std, no? https://t.co/VoBuKBoKRb — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
An interesting point concerning the scaling of noise: if the daily mean is twice the standard deviation, the annual mean must be ~ 38 times the annual standard deviation. https://t.co/NdF15J1430 — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@Toshiki_trades @pedroscasal @gallir 1) You know the distribution is not realistic: too skewed for a 365 day sum. 2) These fakers are not going to use a lornormal or gamma dist. If they were sophisticated they would not have mean = ½ STD. Uniform on Excel is the easiest. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@pedroscasal @gallir Consider that each entry is a sum of 365 random variables... — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
Note: the "MUST" is ~MUST since there are other candidate distributions (gamma, lognormal) but then must be monstrously skewed for STD to be uninformative under v. Large summation. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@pedroscasal @gallir Also when for n of >10k, when the std is half the mean you can eliminate lognormal, gamma, etc. simply because it doesn't add up. STD is meaningless as 2 sigmas can't make it negative. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@pedroscasal @gallir I agree. But they ended up using the Uniform --much more likely. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
Note: I used "~" because the uniform is decomposable, but into a weird combination of Bernouilli + uniform. The discrete uniform, I believe, can be indecomposable. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@trishankkarthik Not necessarily him! — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
3) The Ariely paper (cont): This very very short video explains why ~ NO sum can be uniform. https://t.co/CvycQjwry0 — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@Bhargavmehta666 MErci! — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
3) This very very short video shows why NO sum can be uniform. https://t.co/OkmpuZvuN9 — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
2) Here is the story (softly) retracted from PNAS. Someone cheated in the food chain, and there was no need for the graphs below to figure it out. https://t.co/QUxEE3uvq0 https://t.co/2mQuG2IJQL — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
PROBABILITY DU JOUR You can see with the naked eye that the data in the Ariely paper was fabricated: for annual miles driven, STDEV ~ ½ mean. For a one-tailed distribution, this MUST be Uniform, flat frequ. in [a,b]. Miles per annum CANNOT be uniform SINCE they are a sum: CLT! https://t.co/aEm6lwWey8 — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
RT @EdmondShami: I have been wondering about why Jesus told the people he healed not to tell anyone? And then this came to mind: “Informa… — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
When you envy someone, they will know it before you do. #BedofProcrustes 3rd Ed. (Revised) — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
When people envy you, you know it before they do. #BedofProcrustes 3rd Ed. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@lawzinaj Amioun kamén — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@RobertLepenies @DataColada Is it that people who talk about honesty are not honest? — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@DrDamluji OK, let me say as follows and sorry to take your time: what is the probability of having a fatal event conditional on 1) good stress test, 2) good imaging? Just the ballpark. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@DrDamluji I will describe the question later in formal categories if you wish. It is just to check the predictive power of these tests. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@DrDamluji The reason I was wondering: how many people have little blocage on imaging (and a good stress test) end up having a fulminant heart attack, assuming imaging doesn't predict detached plaque (unstable)? — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@bishopb0b @twistall Page 38: “(natural) logarithm” — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@DrDamluji Dottore, what is the ratio of heart attack from unstable plaque to total? Very very rough estimate. THanks. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@bishopb0b @twistall Plus Spitz said "natural log" somewhere before. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@bishopb0b @twistall Not needed. Log in finance is ALWAYS base e unless specified and this comes from is about continuous compounding since you exponentiate in the VERY equation you are complaining about. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@BartosiakUkasz Hi Luckasz. Not a mistake. https://t.co/mVrn3R2UQ3 — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
@coldbluefeather I block people for sophistry. Sorry, nothing personal. — PolitiTweet.org
Nassim Nicholas Taleb @nntaleb
Lebanon: suicidal parasites who kill their host. — PolitiTweet.org
