Discover and read the best of Twitter Threads about #GIGO
Most recents (12)
I have stated all along, that constitutional challenges, trying to end the mandates, etc. - will NOT work UNTIL you take out the foundation!
Here are some facts to knock out the foundation (the "data" used to justify ALL measures, restrictions, mandates, etc.):
1/...🧵
Here are some facts to knock out the foundation (the "data" used to justify ALL measures, restrictions, mandates, etc.):
1/...🧵
1) In any research, data collection, statistical analysis, etc. - you always start FIRST with a definition of "who" you are studying.
That definition largely consists of definitive parameters of "inclusion" and "exclusion" criteria...
2/...🧵
That definition largely consists of definitive parameters of "inclusion" and "exclusion" criteria...
2/...🧵
...to insure the integrity of the data - & eliminate (or try to eliminate) confounding variables, etc.
If you get your inclusion criteria (aka "case definition" for COVID-19) wrong, then ALL of your data is corrupted & completely useless.
"Garbage in, garbage out" #GIGO
3/...
If you get your inclusion criteria (aka "case definition" for COVID-19) wrong, then ALL of your data is corrupted & completely useless.
"Garbage in, garbage out" #GIGO
3/...
The case for #fraud charges in #Ontario
The following 🧵will attempt to establish that @fordnation & members of his cabinet including, but not limited to, @celliottability WILLFULLY & KNOWINGLY "by deceit, falsehood or other fraudulent means" defrauded the public AND...
1/...
The following 🧵will attempt to establish that @fordnation & members of his cabinet including, but not limited to, @celliottability WILLFULLY & KNOWINGLY "by deceit, falsehood or other fraudulent means" defrauded the public AND...
1/...
...significantly "affecting public markets" via those INTENTIONAL fraudulent actions.
Further, as #Canada 's most populous province by a significant margin - #Ontario 's COVID-19 data also makes up a significant portion of the national data on cases, hospitalizations, etc.
2/..
Further, as #Canada 's most populous province by a significant margin - #Ontario 's COVID-19 data also makes up a significant portion of the national data on cases, hospitalizations, etc.
2/..
#Ontario 's COVID-19 data therefore not only has a significant impact on the markets within the province, but nationally AND internationally to the degree of Canada's impact on trade & international markets.
3/...
3/...
Welcome to #Ontario !
#YoursToDiscover - ONLY if you are quadruple vaccinated, wear 3 N-95 masks & shower 3 times daily in 100% alcohol.
#APlaceToGrow - ONLY variants that ignore our #shortcutvaccine !
#FlawedData - because "transparency" was never a license plate slogan.
1/..
#YoursToDiscover - ONLY if you are quadruple vaccinated, wear 3 N-95 masks & shower 3 times daily in 100% alcohol.
#APlaceToGrow - ONLY variants that ignore our #shortcutvaccine !
#FlawedData - because "transparency" was never a license plate slogan.
1/..
#FlawedDataUpdate:
We put out some pretty little graphs for you!
They give the ILLUSION of #transparency - but we're NOT going to tell you which group the has more UNvaccinated vs Vaccinated - NOR how many shots they've had. NOPE!
Rumors of testing bias? PLS don't ask!
2/
We put out some pretty little graphs for you!
They give the ILLUSION of #transparency - but we're NOT going to tell you which group the has more UNvaccinated vs Vaccinated - NOR how many shots they've had. NOPE!
Rumors of testing bias? PLS don't ask!
2/
We are quite pleased that most of #Ontario & the media actually thought that adding the numbers in these graphs gave you correct totals.
We were quite tickled that many of you calculated rates using these graphs.
973 are missing from the 1st graph!
150 from the 2nd!
3/...
We were quite tickled that many of you calculated rates using these graphs.
973 are missing from the 1st graph!
150 from the 2nd!
3/...
Imagine if...
1) ... @fordnation or @JustinTrudeau would have NOT accepted a #shortcutvaccine that was quicker to make, but provided INFERIOR immunity compared to traditional vaccines?
1/...
1) ... @fordnation or @JustinTrudeau would have NOT accepted a #shortcutvaccine that was quicker to make, but provided INFERIOR immunity compared to traditional vaccines?
1/...
2) ... @fordnation & @JustinTrudeau had heeded the warnings that mass vaccination with this #shortcutvaccine would likely (& predictably) eventually provide the selective advantage for variants like #Omicron - which would lead to a #pandemicofthevaccinated ?
2/...
2/...
3) ... @fordnation & @JustinTrudeau had actually "followed the science" and NOT dictated #vaccinemanates prior to evaluation of real-world data?
3/...
3/...
Anybody who says “the #data don’t lie” either is ignorant or manipulative or both. The data are merely a tool that must be used responsibly & ethically to try to approximate “the truth” …some of which is unmeasurable (yet?). There are MANY #datascience methods & varying results
Everybody gets super excited about this new #AI #ML #machinelearning technique or that
You cannot build a RELIABLE house with low #quality bricks
First, look at the building blocks… meaning, how the #data fields are even defined & how the data are obtained
Who defined them?
You cannot build a RELIABLE house with low #quality bricks
First, look at the building blocks… meaning, how the #data fields are even defined & how the data are obtained
Who defined them?
I can’t tell you how glad I am that I have done coursework at both @MITSloan AND @StanfordGSB - Former immerses you in a ton of hands on analysis & options for analytic techniques useful in a #datascience job. Latter steps back to frame questions, assess missing data, biases.
Below is a response I made (to someone else's comment) on the "Charles McVety Report" FB page, under the post I shared on FB a couple of days ago:
[See thread below.]
1/...
[See thread below.]
1/...
A completely unique, completely faulty, and all-inclusive "case definition" (aka "inclusion criteria" for data) was invented for CV-19 that no other respiratory virus has ever had.
(health.gov.on.ca/en/pro/program…
and
publichealthontario.ca/en/diseases-an…
and...
2/...
(health.gov.on.ca/en/pro/program…
and
publichealthontario.ca/en/diseases-an…
and...
2/...
health.gov.on.ca/en/pro/program…
and
canada.ca/en/public-heal… )
"Hospitalizations", "ICU Admissions", "Deaths", etc. are all just subsets of the total number of "cases" (aka "positive" test results) - and as such are subject to the same "case definition".
3/...
and
canada.ca/en/public-heal… )
"Hospitalizations", "ICU Admissions", "Deaths", etc. are all just subsets of the total number of "cases" (aka "positive" test results) - and as such are subject to the same "case definition".
3/...
Technological debt is insidious, a kind of socio-infrastructural subprime crisis that's unfolding around us in slow motion. Our digital infrastructure is built atop layers and layers and layers of code that's insecure due to a combination of bad practices and bad frameworks.
1/
1/
Even people who write secure code import insecure libraries, or plug it into insecure authorization systems or databases. Like asbestos in the walls, this cruft has been fragmenting, drifting into our air a crumb at a time.
2/
2/
We ignored these, treating them as containable, little breaches and now the walls are rupturing and choking clouds of toxic waste are everywhere.
pluralistic.net/2021/07/27/gas…
3/
pluralistic.net/2021/07/27/gas…
3/
The worst part of machine learning snake-oil isn't that it's useless or harmful - it's that ML-based statistical conclusions have the veneer of mathematics, the empirical facewash that makes otherwise suspect conclusions seem neutral, factual and scientific.
1/
1/
If you'd like an unrolled version of this thread to read or share, here's a link to it on pluralistic.net, my surveillance-free, ad-free, tracker-free blog:
pluralistic.net/2021/08/02/aut…
2/
pluralistic.net/2021/08/02/aut…
2/
Think of "predictive policing," in which police arrest data is fed to a statistical model that tells the police where crime is to be found. Put in those terms, it's obvious that predictive policing doesn't predict what criminals will do; it predicts what POLICE will do.
3/
3/
We live in an attention #economy & what #Tweetiatricians have known for decades (#Twitter started in 2006): importance of drawing attention to factual science-based information as compared to #misinformation & #disinformation, especially on #vaccines
econreview.berkeley.edu/paying-attenti…
econreview.berkeley.edu/paying-attenti…
You have to be fast & prolific to play catch up to this. I have 77K tweets, a moderate sized band of 6K followers interested enough to tolerate my volume but use of hashtags allows reach across Twittersphere. Trending hashtags = better for riding a way for that attention economy
If is unclear if we are now so siloed that tweets are ineffective with anti-vaxx. But not all anti-vaxx are QAnon
The computer science maxim "garbage in, garbage out," (#GIGO) dates back at least as far as 1957. It's an iron law of computing: no matter how powerful your data-processing system is, if you feed it low-quality data, you'll get low-quality conclusions.
1/
1/
And of course, machine learning (AKA "AI") (ugh) does not repeal GIGO. Far from it. ML systems that operate on garbage data produce garbage predictive models, which produce garbage conclusions at vast scale, coated with a veneer of algorithmic objectivity facewash.
2/
2/
The scale and credibility of ML-derived GIGO presents huge risks to our society in domains as varied as the credit system, criminal justice, hiring, education - even whether your kids will be taken away by Child Protective Services.
3/
3/
Thought for the day:
All models are wrong. Some models are useful. But to be really useful, models must be based on accurate data, and a clear understanding of the processes being modeled...
Unfortunately, those two key fundamentals are frequently NOT met. #GIGO
All models are wrong. Some models are useful. But to be really useful, models must be based on accurate data, and a clear understanding of the processes being modeled...
Unfortunately, those two key fundamentals are frequently NOT met. #GIGO
Here's an introduction to the "known unknowns" that a "good" model of any pandemic (let alone COVID-19) would include. fivethirtyeight.com/features/why-i…
Related to this...
After a quick photo op with the @DSP_SPE #scipol #NextGenCanSci #dreamteam, I'm attending the #CSPC2018 panel @sciencepolicy on the social implications of emerging technologies w/ @ideas_idees @SocMedDr @emmeslin @Scienceadvice
Discussion questions for 2-way Q&A at the emerging technologies panel #cspc2018 ⬇️
