Discover and read the best of Twitter Threads about #Statistics

Most recents (15)

I didn't know that the distribution of heads is approximately a normal one. Didn't even think it that way previously.

Found it while playing with random walk approximated with coin toss, by with transition probability of 1/2. Interesting...

#Mathematics #Statistics #Probability
On a side note, the original random walk problem was:
- n nodes arranged linearly
- start with the mid node
- try to go to the extreme node (1 or n)
- transition probability of 1/2 ( being on ith node, there's equal probability of going to i-1 or i+1)

#Mathematics
The result is interesting:
If given a long-run, the total number of steps reaching to the extreme node (1 or n) is approximately equal to n^2 (n-squared).

This can, in fact, be derived from the distribution of the very coin toss I mentioned.

#Mathematics #Programming
Read 5 tweets
Bayesian #MachineLearning Part 1 — Understanding Bayes Theorem from an Analytics Perspective: bit.ly/2KAJaHS #abdsc
—————
#BigData #DataScience #Statistics #StatisticalLiteracy #DataLiteracy #Algorithms
Bayesian #MachineLearning Part 3 — building Bayesian models & inference networks: bit.ly/2O2afGr #abdsc
—————
#BigData #DataScience #Statistics #StatisticalLiteracy #DataLiteracy #Algorithms
—————
+See also these books: amzn.to/30jbwuk
Read 5 tweets
My next #APA2019 presentation is from David MacKinnon: "Modern Causal Inference and Third-Variable Effects." #psychology
MacKinnon: As the number of variables increases, the number of possible relationships among them increases exponentially.

#APA2019 #psychology
MacKinnon explains the difference between mediators, confounders, and colliders. #APA2019 #psychology

Confounder: a causal variable that needs to be controlled for to understand true X&Y relationship.
Collider: a variable caused by X&Y. Don't adjust from colliders!
Read 5 tweets
Full room on a Thursday morning to learn about making an impact with #statistics in the era of #DataScience at #JSM2019
Data Science = w*Statistics + (1-w)*Computer Science
What a great definition!! #JSM2019
Sparsity and complexity are a defining aspect of big data. You need knowledge of the problem you’re solving, and that needs to be baked into our models. #JSM2019
Read 53 tweets
Thursday thoughts on #risk assessment tools, roughly paraphrased from Janus & Prentky, 2003. "Like any tool of science, actuarial risk assessment can be used for good or ill." Used well, it can make decision-making more transparent.
Used poorly, ARA can have unintended consequences, including justification for "increasingly aggressive and expansive preventive detention #laws." Janus and Prentky "urge caution and mindfulness in using ARA."
In other words, we should consider not only the #science, but also the effects of relying on ARA. The accuracy of these tools does not address underlying concerns about legal paradigms that promote incapacitation based on group-based risk #Statistics. #cjreform
Read 4 tweets
33. The Legacy of US, UK, France, Israel, Saudi Arabia, Turkey, Bahrain, Canada, Qatar, United Arab Emirates, Germany, Belgium, Netherlands, Australia, Jordan, Nato in Syria

#RegimeChange #FakeNews #FalseFlag #terrorism #SyriaInvasion #WarCrimes #CrimesAgainstHumanity
1 to 20. The Legacy of US, UK, France, Israel, Saudi Arabia, Turkey, Bahrain, Canada, Qatar, United Arab Emirates, Germany, Belgium, Netherlands, Australia, Jordan, Nato in Syria 🤨👇🏼
threadreaderapp.com/thread/1136642…
21. The Legacy of US, UK, France, Israel, Saudi Arabia, Turkey, Bahrain, Canada, Qatar, United Arab Emirates, Germany, Belgium, Netherlands, Australia, Jordan, Nato in Syria🤨👇🏼
threadreaderapp.com/thread/1137566…
Read 130 tweets
Thomas Bouchard speaking at #ISIR2019 now. His talk is entitled "Finding Out How Things Work."

He mentions Popper's requirement that science must test ideas that are refutable. "But I discovered how resistant psychologists were to refutation and science." #psychology
In graduate school he contested the idea that genetics might influence autism. "It was a bloodbath. No one else in the room wanted to entertain the idea that genes could influence psychopathology." #psychology #ISIR2019
Bouchard discussed the evidence of the time, such as the Tryon (1924) study showing that rats could be bred to select for behavior. "What more evidence do you need that genetics can influence behavior?" #psychology #ISIR2019
Read 39 tweets
#Bigdata vs Machine Learning vs Artificial Intelligence
By Irene Aldridge
☝️author High-Frequency Trading: A Practical Guide to #Algorithmic Strategies& #Trading Systems
☝️co-author Real-Time Risk: What Investors Should Know About #Fintech,#highfrequencytrading and FlashCrashes
1. ☝️🧐➿🔢 In traditional #statistics or #econometrics, researchers make assumptions about #data distributions ahead of the analysis
2. 🥇💪#machinelearning = the 1st discipline to apply #efficiency to #problemsolving brought by #computers & their enhanced computational power
3. 🤗➿🔢#ML scientists try to reduce #assumptions about the data as much as possible&let the data (&computers) decide what fits best.
4. ♾➡️🔤🌐#Datascience identifies core characteristics of the data, summarized by what has been known as #characteristic values (#eigenvalues)
Read 6 tweets
Below is an interesting #statistics on the number of #Germans killed in #WW2;I do not retweet this to proclaim this as the truth, but rather as a proposal which has to be corroborated or refuted. I don't know who created this statistics, or how.
My translation:
'The casualties..
.. of the German People during and after the Second World War

Deaths:

[ca.] 3.250*10^6 German soldiers,
[ca.] 1.000*10^6 women, children and eldery fell victim to terror bombings in violation of international law,
..
..
[ca.] 3.242*10^6 German soldiers died as prisoners of war of the allied forces,
of which [ca.] 2*10^6 died in Soviet camps, [ca.] 1*10^6 died in American camps, [ca.] 1.2*10^5 died in French camps, [ca.] 1*10^5 died in Yugoslav camps,
..
Read 9 tweets
Regional #AmfestExpoIbadan2018 - The report - Day 2:

Sequel to the successful ‘Lagos 2018’ that held in the summer and matters discussed at the Business Summit, it became necessary that a Regional program be developed to cater to issues discussed,
like authenticity and originality of our Arts and Culture. Professionals that practise at the regional level are closer to traditional inspiration, so the program is to support in bringing them mainstream.
The International #AMFESTEXPOLAGOS2018’ was well attended by the core professionals of these industries. Delegates from
United State of America, England, Ghana, Malawi, Benin participated in the conference.
Read 23 tweets
The new @wiiw_news Handbook of #Statistics 2018 contains updated key #macroeconomic & structural indicators for 22 economies in #CESEE serving as easy-to-use reference tool & facilitating comparisons across topics, countries & time.
wiiw.ac.at/wiiw-handbook-…
Thread: 1/11
New features of the 2018 ed. include e.g.
- new key indicators at #regional levels
- #wages & #investment data by activity now also available for #Turkey
- comparable #structural breakdown for all countries
Find below examples of some conclusions from the newly released data
2/11
All countries in #CESEE experienced positive #economic #growth in 2017, clear leader was #EUCEE with average real GDP growth of 4.9%. Ten economies achieved their highest real #GDP growth rates over the last 5 years.
3/11
Read 11 tweets
1/ I have been asked by many people how I managed to be accepted to @MILAMontreal after two years of trying. Here's my story. Last year I reached out to a new prof at MILA and I audited their class.
2/ They were interested, but when I applied, the semi-automatic system from MILA admission rejected me almost instantly because of my GPA. The admission completely ignored my 6 publications in child #psychology, 2 of which are #statistics paper where I'm first author.
3/ It frustrated me and it still does that this wasn't considered as relevant. Research is research, and research skills are easily transferable from a field to another. People are obsessed with labels and boxes and I didn't tick the correct #AI box.
Read 9 tweets
1/ Earlier today, @RVAwonk referenced a study that showed the correlation between Trump's rallies and violence, further supporting the concept of #StochasticTerrorism and shedding light on the events on what has occurred since Trump's public embrace of nationalism.
@RVAwonk 2/ In contrast to this well designed study, @Ali_H_Soufan describes a distinct yet equally problematic issue. A biased report that was shown to decision makers.

thesoufancenter.org/intelbrief-cor…
@RVAwonk @Ali_H_Soufan 3/ #Statistics tip: If you choose a sample that contains members outside of the target population, you will collect meaningless statistics.
Read 9 tweets
Bayes’ Theorem Definitions:
The vertical bar | stands for "given that".
P = Probability.
A & B are events.
P(A) & P(B) are the probabilities of events A and B. Each event is separate from the other.
P(A|B) is the probability of A being true given that event B is true.
#SoDS18 #ML
Example:
Say we have 2 coolers at an owambe: Cooler A is filled with 10packs of small chops only. Cooler B has 5packs of small chops and 5packs of Asun. You are then asked to close your eyes and pick a pack out of one cooler, which pack would you pick? #MachineLearning #SoDS18
Because you know that we have more of small chops in both coolers, your brain is most likely going to tell you have picked a pack of small chops - even when your eyes are closed. This is not wrong.
#MachineLearning #SoDS18
Read 14 tweets
1/6 Data and the Quest for Truth: A short cartoon talking about the value of data in establishing truth. First, distinguish between matters of opinion and matters of fact.

#datascience #scientificmethod #machinelearning

#think2018 #IBMPartner @ibmanalytics
2/6 You can have a preference and that’s cool. You like one thing. I like another. We run into problems when we argue about verifiable facts. Watch out for #confirmationbias

#datascience #analytics #confirmationbias

#think2018 #IBMPartner
3/6 Ignoring evidence can impact people around you… and that’s bad. We live in a #BigData in which everything is quantified. To solve our problems, we need to become data-literate.

#datascience #machinelearning

#think2018 #IBMPartner
Read 6 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just three indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!