Discover and read the best of Twitter Threads about #stats

Most recents (15)

Hilo recopilatorio de #PerlasMetodologicas

Perla metodológica. Vol. 1
#stats #methods #research Image
Perla metodológica. Vol. 2
#stats #methods #research Image
Perla metodológica. Vol. 3
#stats #methods #research Image
Read 16 tweets
OK, #stats story time again. I've promised @RrrichardZach a thread about the #GermanTankProblem. So imagine it's 1943. You, a statistician for the Allies, would really like to have some idea of how many tanks are rolling off German assembly lines each month. 1/10
The intelligence community is making their own estimates, but you're using information from the serial numbers of various tank parts, mainly the gearboxes and the wheels. 2/10
Here's a simplified version of your problem: suppose your troops have captured tanks with gearboxes with the following serial numbers: 12, 71, 47, 112, 34, 45, 88, and 103. How many tanks would you guess have been produced? Clearly, at least 112... 3/10
Read 10 tweets
Ante la gran actualidad de los test diagnósticos, he pensado en hacer un hilo para explicar brevemente conceptos como Sensibilidad, Especificidad, valores predictivos, etc.

Espero sirva,
#investigación #methods #stats

pd. Imágenes de elaboración propia
Una buena prueba diagnóstica es la que ofrece resultados positivos en enfermos y negativos en sanos. Por lo tanto, las condiciones que deben ser exigidas a un test son:


Una cosa son las pruebas de cribado, que se utilizan para identificar a sujetos asintomáticos que pueden presentar la enfermedad, y otra cosa las pruebas diagnósticas, que se utilizan para identificar o descartar una enfermedad en individuos que si presentan síntomas
Read 18 tweets
Earlier today, we put out a preprint that asked: how do we design and analyze SARS-CoV-2 seroprevalence surveys? @yhgrad wrote a lovely explainer thread, linked here. ] I want to highlight some #stats and #networks results. 1/
First, the basics. This paper's 1st result is like a statistical inference midterm problem: If you observe n+ positive tests, n- negative tests, and you know the sensitivity/specificity of your test, what is the posterior prob. of actual positives? Solution: Bayes' rule. ✅
Now a practical problem: The posterior looks like a binomial posterior, but due to sensitivity/specificity, we end up with incomplete beta functions & small things raised to n+ and n- powers & can't invert the CDF. Solution: take logs and use accept-reject algm to sample.✅ 3/
Read 16 tweets
Resources I like/ used to learn

These articles seem to be released monthly and are great to browse new R packages and stay updated. I like how they're separated into categories too!

#resources #helpfulinfo #stats
I used this way more in college to supplement my classes and it also helped get me started in ....Python.
You can pay for course credit, but can also audit all the courses for free!
3) Might be creepy.. but university professors will post lecture notes and or slides and they can be really helpful when you're stuck or want to get rolling on a new topic but don't know where to start.

Read 6 tweets
10 facts & myth busters!

#1 Social Distancing is not restrictive of social gatherings like malls and movies. We have expanded that to almost any contact outside of family. Each infected person infecting 3 others TIMES 15 will be close to a million infected in 2 wks.
#2 #Handwashing vs #Sanitizer
Precautions are important. The best evidenced based precaution is #Handwashing. Virus can last in surfaces and clothing upto several hours. Also hand washing, done properly is as good or better than hand sanitizers.
#3 #Highrisk groups such as health care workers should protect themselves and their families too. So, please have your own quarantine protocols at home. #Covid is the greatest leveler of mankind, and hurts everyone equally. Stay home, and if not, stay safe!
Read 10 tweets
🔥off the press! 👀 our @biorxivpreprint on human 🧠brain @LieberInstitute spatial 🌌🔬transcriptomics data 🧬using Visium @10xGenomics🎉#spatialLIBD

Our study shows 12 samples from 3 human brain DLPFC neuronal layers + white matter with @10xGenomics's Visium platform. Features📜:

* Largest so far
* Harder to cluster than the example mouse data
* Data is all public
* @Bioconductor #rstats📦
* #shiny web app

2/7 #spatialLIBD
* Assessment of known markers
* Identification of layer-specific markers
* smFISH validation✅
* spatial registration of snRNA-seq data
* Layer-enrichment of neurodevelopmental and neuropsychiatric gene sets
* Data-driven layer-enriched clustering in the DLPFC

3/7 #spatialLIBD
Read 7 tweets
Transitioning into #DataScience: A (long) thread—
Transitioning into a new field can be cumbersome, especially #datascience which usually requires some level of #math #statistics #machinelearning #programming. But fret not!
This thread will go over the fundamentals of what you should know to become a #datascientist. First thing first, there are hundreds of tools for visualization (Power BI, Tableau, Dash), cloud computing (GCP, AWS, Azure) and SQL variants (Postgres, MSSQL, MySQL).
Don’t get caught up trying to learn all of these tools/platforms/software! You will be onboarded to these technologies and they differ highly from company to company and sometimes even department to department. But, you should be familiar with what they do at a high level!
Read 20 tweets
This is your second daily pension announcement: Sorry, I have to do another one. I need to tell you more about Kevin and how the institutional investment industry works. #handsoffmypension #ABLeg #abed First, the industry is male dominated and is hyper competitive.
To quote Travis from the @calgaryherald “AIMCo has earned its reputation as a world-class investment manager.” So has ATRF. If I have learned anything about institutional investors it is that they all tend to claim greatness. #handsoffmypension
This industry continually reminds me of a former Minister of Education who, in the 1990’s, claimed that all students could score above the provincial average on Diploma Exams. Almost all asset managers claim to perform in the top quartile. #fail #stats #statsfailure
Read 9 tweets
🌊 A “stock-to-flow debacle” has taken crypto-twitter by storm.

The meme achieved superior performance in nocoiner conversion…

…and flooded your timeline with 🔢math, 💎minerals and 🔥heated opinions you may not understand.

Time to slash FUD and review some of the #stats:
S2F is a measure of scarcity applied to commodities.

“in how many yrs, at current production levels (flow), will the market add *new assets* equivalent to all current outstanding assets (stock)?”

@TraceMayer, @Saifedean flirted w/ applying it to BTC...…
@TraceMayer @saifedean But it was @100trillionUSD who finally laid out the digital SoV thesis in a language that appealed to money managers worldwide.

Visualising BTC’s S2F X other assets also helped.

In the instantly-turned-classic chart, what pops to the eye is Bitcoin’s fierce path to the #moon.
Read 25 tweets
Hi, @FrankPallone

I was one of the alleged bots #NotABot defamed for that @JoeSmyser @DrArturoNJ @NicholsonForNJ @PublicGoodProj @WSJ report.

Shall I expect an invite to @EnergyCommerce offices to sign in, in person, to my account?

We can also discuss manipulation of #data.
@FrankPallone @JoeSmyser @DrArturoNJ @NicholsonForNJ @PublicGoodProj @WSJ @EnergyCommerce 👈#NotABot we can discuss allegations as to why I and other's data has been used to accuse innocent people of committing what I consider crimes @JoeSmyser @DrArturoNJ @NicholsonForNJ @PublicGoodProj @WSJ @EnergyCommerce like marketing to children.
Read 34 tweets
I’ve been getting a lot of new followers lately, so how about an #epitwitter #ScholarSunday so newcomers can get connected to our lovely community!

Here’s a thread of some of my suggestions for who to follow & why! Add your own in the comments👇🏼
Looking for some academic career advice? Have questions about writing grants? Want tips on making delicious pizza or pie? Head on over to @BillMiller_Epi!
Want support for how to #liveyourbestlife, learn to say ‘no’, or throw an amazing party? You’ll be wanting to follow @lisabodnar!
Read 6 tweets
📊#Time for monthly #stats

Good news! #ISIS activity on @Twitter decreased again in June: 7 195 new 🎯That's 12% less compared to May.
Again, 88% of these accounts were hacked: old, inactive, weakly protected.
They could easily be frozen in bulk. 😐

Thanks everyone!
📊Time for monthly #stats

In average, we found 240 new #ISIS accounts per day in #June2019 (May: 263). Always the same guys, coming back again and again, spreading mostly the same propaganda month after month.
A bunch of losers...

📊Time for monthly #stats

Less good news now. With 6 903 suspensions for 7 195🎯, the outcome (96%) slightly dropped again, by 1%.
@TwitterSupport provided a lower service this month for #ISIS accounts removals, both in terms of quantity...

Read 6 tweets
A month after holes in a key database used in GDP estimation were first exposed, the controversy around #India's GDP #data and statistical system has only grown. This #thread is a summary of some answers and many questions on this issue #stats #institutions #economy (1/n)
The latest to question the new GDP series is the former CEA @arvindsubraman who was also among the first to question the new series numbers when they first came out in 2015 (2/n)
His main contention, then and now, is that the new series fails to tally with other economic indicators. Others also have made this point but his recent paper (…) is the most systematic demonstration of that issue (3/n)
Read 24 tweets
I used @ProjectJupyter to investigate @NSERC_CRSNG expenditure over recent years using #opendata from @OpenGovCan. My exploration is freely available via @mybinderteam here:… 1/
According to the @OpenGovCan data, Discovery programs @NSERC_CRSNG increased in budget by 16% between 2013 and 2016. 2/
#NSERC leadership was notified of significant gaps in funding for #math and #stats #research by the math/stats Liaison Committee, by Institute Directors, and (publicly) by @NGhoussoub in May.… 3/
Read 6 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two 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!