Sabitlenmiş Tweet
🚨New SimplyAgree (early) release🚨
Proud to announce that SimplyAgree v0.2.0 is now available on GitHub and feedback is welcome/wanted. A few details below 🧵
aaroncaldwell.us/SimplyAgree/
#Rstats
English
Aaron Caldwell
7.7K posts
Aaron Caldwell
@ExPhysStudent
Stats guy that has practicing safe science since 2017. PhD but always a student. #Rstats #OpenScience
Arkansas Katılım Ekim 2011
1.5K Takip Edilen1.6K Takipçiler
Oh percent change, how I continue loathe you
Aaron Rupar@atrupar
RFK Jr: "A Democratic senator claimed it's mathematically impossible to have a drug drop by 600%. I said, 'Well, if the drug was $100 and it raises to $600, that would be a 600% rise. If it drops from $600 to $100, that's a 600% savings.'" Trump: "Right"
English
@LGHemkens @lakens @GuyattGH Developing a widely used framework doesn’t grant infallibility on every statistical claim. The criticism was about specific statements, not about GRADE. Conflating the two is pretty telling.
English
This author did not understand the difference between a hypothesis test and an estimate in 2007. Nor did he knew about correction methods for sequential designs. You should probably not read articles by people like this.
Gordon H. Guyatt@GuyattGH
This article in @AnnalsofIM highlights ethical problems in stopping trials early for benefit: seriously inflated overestimates of treatment effect violates ethical requirements of scientific validity and social value and leads to misguided patient choices. pubmed.ncbi.nlm.nih.gov/17577007/
English
@f2harrell @GuyattGH @AnnalsofIM I assume your disagreement would largely align with Goodman’s? pubmed.ncbi.nlm.nih.gov/17577008/
English
@GuyattGH @AnnalsofIM What a serious misunderstanding of #Statistics, fostered by only being trained in frequentist statistics.
English
This article in @AnnalsofIM highlights ethical problems in stopping trials early for benefit: seriously inflated overestimates of treatment effect violates ethical requirements of scientific validity and social value and leads to misguided patient choices.
pubmed.ncbi.nlm.nih.gov/17577007/
English
Aaron Caldwell retweetledi
There's a form of secular creationism that we might call Malicious Design: The idea that the limitations imposed by nature are actually the product of human systems designed to exploit or otherwise harm the masses. 🧵
Out of Context Human Race@NoContextHumans
Yep
English
As a stats reviewer, can confirm and agree with all this!
Rod Dunn@redunndant
I review the statistics in ~200 manuscripts a year for some of the top urology journals in the world. Here's what I actually do — and the mistakes I see in almost every paper. 🧵
English
Tunnel Vision Challenge update!
1. University Hills Loop: Great initial meetings with regulators. Many more to come. Hoping to submit a permit application in April. Goal is to strengthen access to transit/jobs in South Dallas, and possibly then extend/connect to North Dallas.
2. NOLA Loop: Great initial meetings with elected officials and the Convention Center. Many more meetings to come. Goal is to strengthen connectivity by the Convention Center and Business District, and reduce event related congestion.
3. Ravens Loop: After initial meetings, this project unfortunately will not be moving forward as part of the competition.
What does everyone think? Should TBC select another project to fill the now-open third slot?
The Boring Company@boringcompany
Tunnel Vision Challenge results! We've been overwhelmed with the amazing submissions…so we are announcing three winners! The Thrilling Three are: - NOLA Loop (New Orleans, LA) - Ravens Loop (Baltimore, MD) - University Hills Loop (Dallas, TX) What happens next? TBC and the project stakeholders enter into a rigorous diligence process which includes: - Meetings with elected officials, regulators, community leaders, and business leaders - Geotechnical borings - Utility and subsurface infra investigation Once the diligence (100% funded by TBC) is complete, if all 3 projects are feasible, will fund/build all 3 - this would be awesome. If only 1 is feasible, will fund/build 1. IN ADDITION, there were multiple other projects that TBC thought were so compelling that we are going to continue to work with the entrants and try to get them built. This includes the following two: - Hendersonville Utility Tunnel (Hendersonville, TN) - Morgan's Wonderland Tunnel (San Antonio, TX) Thanks again to all of the participants - your enthusiasm and positivity has been inspiring for the TBC team.
English
Aaron Caldwell retweetledi
"How to Lower Electricity Bills to $100 a Month"
The biggest impact is equalizing industrial and residential rates which currently reflect cost to serve but don't have to. I don't endorse all of these ideas but it's a serious proposal worth considering.
…derbiltpolicyaccelerator.substack.com/p/a-simple-way…
English
Aaron Caldwell retweetledi
So they are trying to blacklist Anthropic for having red lines, then agreed to the exact same red lines with OpenAI.
It's an entire administration of tryhard cosplay dorks, obsessed with the appearance of toughness, stumbling through it like drunk toddlers.
Axios@axios
NEW: The Pentagon has agreed to OpenAI's rules for deploying its technology safely in classified settings, though no contract has been signed, a source tells Axios. The department appears to have accepted conditions similar to those put forth by Anthropic. axios.com/2026/02/27/pen…
English
@VickersBiostats I feel a rebellion against RE meta coming soon. This advice, as you indicate, seems to be applied thoughtlessly
English
COULD EVERYONE PLEASE STOP USING RANDOM EFFECTS META-ANALYSIS WHEN COMBINING 3 OR 4 TRIALS? AND COULD REVIEWERS STOP DEMANDING IT?
English
@JohnHolbein1 Possible implications for the “Mississippi Miracle”?
English
Retaining 3rd graders because of their low test scores reduces their incomes 20 years later by 19%.
English
@f2harrell @datavisFriendly Agreed. I’ve seen similar talk around the “diagnosis” of gestational diabetes. Talked to a few physicians that think problematic cases are missed because patients don’t meet the binary classification on 3 separate tests.
English
@datavisFriendly I'd like to know more of the history. But I think there is still a problem. Type II diabetes is not a diagnosis; it is a matter of degree. See acpjournals.org/doi/10.7326/00…
English
Some very useful ideas here! Still, didn’t Reaven & Miller discover type 1 & 2 diabetes by observing clusters and confirmed using PRIM9?
Frank Harrell@f2harrell
#Statistics thought of the day: If you think you can find new disease subtypes by empirically clustering patients, think again: fharrell.com/post/cluster/i…
English
Aaron Caldwell retweetledi
@JohnHolbein1 We did a lab experiment that showed this behavior years ago.
link.springer.com/article/10.105…
English
Aaron Caldwell retweetledi
I learned all this really secret awful stuff that shows the hoaxes and conspiracies really happened, but I can't tell you because it's secret and can't do anything about it because I quit because going to work every day is really hard.
Sean Hannity 🇺🇸@seanhannity
.@dbongino says details he uncovered at the FBI of the Russia collusion hoax are shocking, warning the abuse of power against President Trump shows a total systematic breakdown: “I was reading through some stuff that you could only read in the office, and it basically involved the collusion hoax, Crossfire Hurricane as it went by, and the various other spinoffs. And when you read it from the inside, when you see the details of what these absolute animals did to President Trump—I mean, I’m not shocked often, Sean—just reading through it and seeing it in detail for the first time, all put together. You can’t run a republic like this. You can’t—you absolutely cannot. It’s just stunning how all these guardrails broke down at the exact same time. It’s frightening how nobody thought to speak up and say, ‘Hey man, not only is this wrong, this is demonic—this is evil stuff.’”
English
Aaron Caldwell retweetledi
Someone made a 2025 College Football season montage to One Shining Moment and it’s amazing 😭
English
@bendreyfuss @notjessewalker Man, this guy would be shocked to see all the professional grade logistics I saw from dads and moms in sweat pants at my local Walmart before the snow storm!
English
@notjessewalker “This is professional grade logistics”
a box of hand warmers, some saltines and a few quarts of milk?
Lol
English
Can't conceive of bottom-up cooperation. No wonder he supports a big-government philosophy like MAGA.
Gunther Eagleman™@GuntherEagleman
🚨 BREAKING: The “No-Go-Zone” in Minneapolis is getting fully stocked like a pop-up leftist supply depot, free hand warmers, winter gear, coffee, food, milk, you name it. This is PROFESSIONAL-grade logistics. Someone is BANKROLLING this autonomous zone.
English
Aaron Caldwell retweetledi
Why is this illegal you might ask?
Anti-massing design guidelines.
Guidelines against using one material.
If you want to see these in your city, please advocate for stripping the overwrought design guidelines, AND as many other BS regulations as possible, so that builders can spend money on actual design and quality materials!
You do that by attending your local city planning meetings.
By bugging your elected officials on the local and state level to discard these outdated concepts.
Thank you for coming to my TED Talk
YIMBYLAND@YIMBYLAND
It doesn’t get much better than this. It’s a real shame that it’s illegal to build like this on 90% of land in this country.
English
Aaron Caldwell retweetledi
Motor vehicle theft is the easiest property crime to address through tech and yet it's the one that we've gone backwards on over the past 15 years. The tools exist today to essentially end car theft if adopted: PIN to drive, remote disable, GPS tracking, cameras, encrypted keys.
English
Aaron Caldwell retweetledi
I resigned from the board of advisors of the University of Austin (UATX, not to be confused w U T Austin) within weeks of their inaugural announcement, because they "had no coherent vision of what higher education in the 21st century ought to be. Instead, they created UnWoke U led by a Faculty of the Canceled." Also: science was an afterthought. And they were so knee-jerk anti-woke that they were unprepared for the genuine issues that led to woke overreach, like sexual harassment. Four years later, my worst fears came true. Expose in Politico: They Wanted a University Without Cancel Culture. Then Dissenters Were Ousted. politi.co/49ELxlM via @politico
English
@S_Surprenant Huh, I remember reading a book by Milankovic years ago, and thought it was decent. Should I have been a bit for skeptical of his work?
English
Read the names again. Piketty, Milankovic? Come on, man.
Has any of them fit any model to data, whether statistical or theoretical, to justify their bold forecast? Did they cite others who did so?
You can't blame the field over economists who stopped doing economics.
Sandy Petersen 🪔@SandyofCthulhu
100 economists signed a letter about how Javier Milei’s election would destroy Argentina’s finances. This should completely discredit all modern economics.
English
Aaron Caldwell retweetledi
🚨New RFP Alert!🚨 @Arnold_Ventures Evidence & Evaluation team released just two new RFPs to support research evaluating the causal impacts of U.S. social programs and policies: bit.ly/4aXA43k
A short 🧵on what we're prioritizing and what's new this cycle (1/n)
English