Anders Huitfeldt
@andershuitfeldt.net
Aspiring rationalist. Medical doctor (PGY 5, addiction medicine). In a past life, I was an epidemiologist. MB BCh BAO (Royal College of Surgeons in Ireland, 2008). ScD (Harvard School of Public Health, 2015).
Reposted by Anders Huitfeldt
Fun article about “outsider” scientists and their breakthroughs.
“Academia filters most funding, publishing, and hiring decisions through senior insiders, which favors ideas within existing paradigms.”
worksinprogress.co/issue/why-sc...
“Academia filters most funding, publishing, and hiring decisions through senior insiders, which favors ideas within existing paradigms.”
worksinprogress.co/issue/why-sc...
Why science needs outsiders - Works in Progress Magazine
Science has forgotten that the greatest breakthroughs often come from outsiders who are able to take a fresh perspective.
worksinprogress.co
September 19, 2025 at 4:29 AM
Fun article about “outsider” scientists and their breakthroughs.
“Academia filters most funding, publishing, and hiring decisions through senior insiders, which favors ideas within existing paradigms.”
worksinprogress.co/issue/why-sc...
“Academia filters most funding, publishing, and hiring decisions through senior insiders, which favors ideas within existing paradigms.”
worksinprogress.co/issue/why-sc...
Reposted by Anders Huitfeldt
Reckon I can submit this as a figure for a paper?
July 9, 2025 at 10:21 AM
Reckon I can submit this as a figure for a paper?
Reposted by Anders Huitfeldt
New post: “Marginal” and “conditional” are relative descriptions of an estimand
July 7, 2025 at 3:10 PM
New post: “Marginal” and “conditional” are relative descriptions of an estimand
Reposted by Anders Huitfeldt
New paper posted on Arxiv: "When do composite estimands answer non-causal questions?"
This can happen more often than you think, and can have a dramatic impact on trial results (e.g. a false-positive rate of almost 90%)
arxiv.org/abs/2506.22610 @timpmorris.bsky.social
This can happen more often than you think, and can have a dramatic impact on trial results (e.g. a false-positive rate of almost 90%)
arxiv.org/abs/2506.22610 @timpmorris.bsky.social
When do composite estimands answer non-causal questions?
Under a composite estimand strategy, the occurrence of the intercurrent event is incorporated into the endpoint definition, for instance by assigning a poor outcome value to patients who experience th...
arxiv.org
July 1, 2025 at 9:31 AM
New paper posted on Arxiv: "When do composite estimands answer non-causal questions?"
This can happen more often than you think, and can have a dramatic impact on trial results (e.g. a false-positive rate of almost 90%)
arxiv.org/abs/2506.22610 @timpmorris.bsky.social
This can happen more often than you think, and can have a dramatic impact on trial results (e.g. a false-positive rate of almost 90%)
arxiv.org/abs/2506.22610 @timpmorris.bsky.social
After two years of trying to avoid this discussion, I just necroed *that thread* on datamethods (discourse.datamethods.org/t/should-one...) in order to share an excellent preprint by philosopher Veli-Pekka Parkkinen (philsci-archive.pitt.edu/24785/1/efme...)
Should one derive risk difference from the odds ratio?
I urge all readers of this thread to read the excellent new preprint from philosopher of science Veli-Pekka Parkkinen, “Choice of effect measure, extrapolation, and decision-making in patient care an...
discourse.datamethods.org
February 26, 2025 at 10:00 AM
After two years of trying to avoid this discussion, I just necroed *that thread* on datamethods (discourse.datamethods.org/t/should-one...) in order to share an excellent preprint by philosopher Veli-Pekka Parkkinen (philsci-archive.pitt.edu/24785/1/efme...)
Reposted by Anders Huitfeldt
I’m George Takei and I approve of this message.
February 19, 2025 at 3:47 PM
I’m George Takei and I approve of this message.
Reposted by Anders Huitfeldt
🤢 horrifying piece of work, which we’ll see idiots quoting.
For goodness sake @jclinepi.bsky.social
For goodness sake @jclinepi.bsky.social
Treatment Effects in Pharmacological Clinical Randomized Controlled Trials are Mainly Due to Placebo - @jclinepi.bsky.social www.jclinepi.com/article/S089...
Treatment Effects in Pharmacological Clinical Randomized Controlled Trials are Mainly Due to Placebo
The placebo response in clinical trials has four components: regression to the mean (RTM), measurement artefacts, natural tendency (NT) of the disease, and the genuine placebo effect. Our objective is to determine what contributes to the size of the placebo-effect in clinical trials by meta-regressions of randomized placebo-controlled clinical trials.
www.jclinepi.com
January 3, 2025 at 1:39 PM
🤢 horrifying piece of work, which we’ll see idiots quoting.
For goodness sake @jclinepi.bsky.social
For goodness sake @jclinepi.bsky.social
Reposted by Anders Huitfeldt
In economics, editors, referees, and authors often behave as if a published paper should reflect some kind of authoritative consensus.
As a result, valuable debate happens in secret, and the resulting paper is an opaque compromise with anonymous co-authors called referees.
1/
As a result, valuable debate happens in secret, and the resulting paper is an opaque compromise with anonymous co-authors called referees.
1/
December 24, 2024 at 2:44 PM
In economics, editors, referees, and authors often behave as if a published paper should reflect some kind of authoritative consensus.
As a result, valuable debate happens in secret, and the resulting paper is an opaque compromise with anonymous co-authors called referees.
1/
As a result, valuable debate happens in secret, and the resulting paper is an opaque compromise with anonymous co-authors called referees.
1/
Reposted by Anders Huitfeldt
People say estimating a causal effect sets the bar unattainably high.
But estimating an association is a bar that is literally so low that you can't go under it.
Better to aim for what you want and fall short than to, in Homer Simpson's words, "aim so low, no one will even care if you succeed."
But estimating an association is a bar that is literally so low that you can't go under it.
Better to aim for what you want and fall short than to, in Homer Simpson's words, "aim so low, no one will even care if you succeed."
a cartoon of homer simpson and marge simpson with the words you tried your best
Alt: a cartoon of homer simpson and marge simpson with the words you tried your best and you failed miserably, the lesson is never try.
media.tenor.com
December 10, 2024 at 2:08 PM
People say estimating a causal effect sets the bar unattainably high.
But estimating an association is a bar that is literally so low that you can't go under it.
Better to aim for what you want and fall short than to, in Homer Simpson's words, "aim so low, no one will even care if you succeed."
But estimating an association is a bar that is literally so low that you can't go under it.
Better to aim for what you want and fall short than to, in Homer Simpson's words, "aim so low, no one will even care if you succeed."
Reposted by Anders Huitfeldt
The Justice Department has filed a lawsuit against approximately two dogs.
December 10, 2024 at 8:50 PM
The Justice Department has filed a lawsuit against approximately two dogs.
Unpopular opinion: Blinded peer review was a mistake. If someone is able to block my paper based on their midwit opinions, they should at the very least be forced to put their name on the review, and publicly stake their reputation on the (false) claim that my work is flawed.
December 10, 2024 at 9:44 PM
Unpopular opinion: Blinded peer review was a mistake. If someone is able to block my paper based on their midwit opinions, they should at the very least be forced to put their name on the review, and publicly stake their reputation on the (false) claim that my work is flawed.
Reposted by Anders Huitfeldt
Same. Have no desire to speak ill of the dead, but I wished they had left this sentence out of the obituary: "He will be remembered for his remarkable contributions to the psychology world and as a defender of expression without undue fear of reprisal." Simply not true.
December 6, 2024 at 3:25 PM
Same. Have no desire to speak ill of the dead, but I wished they had left this sentence out of the obituary: "He will be remembered for his remarkable contributions to the psychology world and as a defender of expression without undue fear of reprisal." Simply not true.
Reposted by Anders Huitfeldt
Can anyone point me to a convincing intro to / explanation of ‘in silico’ trials?
Everything I’ve read & heard about them just makes the writer/presenter sound nuts.
What am I missing??
Everything I’ve read & heard about them just makes the writer/presenter sound nuts.
What am I missing??
December 4, 2024 at 9:04 AM
Can anyone point me to a convincing intro to / explanation of ‘in silico’ trials?
Everything I’ve read & heard about them just makes the writer/presenter sound nuts.
What am I missing??
Everything I’ve read & heard about them just makes the writer/presenter sound nuts.
What am I missing??
Reposted by Anders Huitfeldt
The Onion should buy Elsevier next
November 14, 2024 at 8:28 PM
The Onion should buy Elsevier next
Reposted by Anders Huitfeldt
Gotta be honest here, Rhian is one of my favorite authors. I always enjoy her papers so much. I’m currently reading her paper on collapsibility and I feel like this one will be a natural follow up.
This new paper with Rhian Daniel and Daniel Farewell is an excellent opportunity to revive the classic discussions about odds ratios vs other measures of the effect academic.oup.com/jrsssa/artic... #episky #statssky #statistics
‘Does God toss logistic coins?’ and other questions that motivate regression by composition
Abstract. Regression by composition is a new and flexible toolkit for building and understanding statistical models. Focusing here on regression models for
academic.oup.com
October 15, 2024 at 12:56 AM
Gotta be honest here, Rhian is one of my favorite authors. I always enjoy her papers so much. I’m currently reading her paper on collapsibility and I feel like this one will be a natural follow up.
Reposted by Anders Huitfeldt
This new paper with Rhian Daniel and Daniel Farewell is an excellent opportunity to revive the classic discussions about odds ratios vs other measures of the effect academic.oup.com/jrsssa/artic... #episky #statssky #statistics
‘Does God toss logistic coins?’ and other questions that motivate regression by composition
Abstract. Regression by composition is a new and flexible toolkit for building and understanding statistical models. Focusing here on regression models for
academic.oup.com
September 18, 2024 at 7:47 AM
This new paper with Rhian Daniel and Daniel Farewell is an excellent opportunity to revive the classic discussions about odds ratios vs other measures of the effect academic.oup.com/jrsssa/artic... #episky #statssky #statistics
Reposted by Anders Huitfeldt
What is common knowledge in your field, but shocks outsiders?
Most published medical research is essentially junk, and most health professionals aren’t sufficiently trained to tell the difference.
Most published medical research is essentially junk, and most health professionals aren’t sufficiently trained to tell the difference.
What is common knowledge in your field, but shocks outsiders?
People would not regularly die at 30 in pre-industrial times, and it only looks like that on graphs of average life spans because historians - for some reason - insists on including infant deaths in them. The actual number is ~55-60.
People would not regularly die at 30 in pre-industrial times, and it only looks like that on graphs of average life spans because historians - for some reason - insists on including infant deaths in them. The actual number is ~55-60.
What is common knowledge in your field but shocks outsiders?
We don't all have the same number of bones or muscles. There's an average, I guess. We all kind of cluster around it. Some muscles are pretty rare. Some people just invent their own artisanal bones.
We don't all have the same number of bones or muscles. There's an average, I guess. We all kind of cluster around it. Some muscles are pretty rare. Some people just invent their own artisanal bones.
September 5, 2024 at 9:24 AM
What is common knowledge in your field, but shocks outsiders?
Most published medical research is essentially junk, and most health professionals aren’t sufficiently trained to tell the difference.
Most published medical research is essentially junk, and most health professionals aren’t sufficiently trained to tell the difference.
Reposted by Anders Huitfeldt
Unwisely concluding that X causes Y because Y tends to follow X needs a better name than this. I suggest:
Granger Danger
Granger Danger
I think so. The post hoc fallacy is the argument that since Y follows X, X caused Y. It remains surprisingly pervasive in clinical research (e.g., interpretation of within-arm change) and clinical practice (trust own observation of treatment effect over research).
en.wikipedia.org/wiki/Post_ho...
en.wikipedia.org/wiki/Post_ho...
Post hoc ergo propter hoc - Wikipedia
en.wikipedia.org
June 16, 2024 at 1:10 PM
Unwisely concluding that X causes Y because Y tends to follow X needs a better name than this. I suggest:
Granger Danger
Granger Danger
Reposted by Anders Huitfeldt
With #TargetTrial emulation becoming increasingly popular, it's important to understand what it can and can't do.
In this podcast I discuss how target trial emulation can improve causal inference from observational data and extend inferences from randomized trials
edhub.ama-assn.org/jn-learning/...
In this podcast I discuss how target trial emulation can improve causal inference from observational data and extend inferences from randomized trials
edhub.ama-assn.org/jn-learning/...
Target Trial Emulation for Causal Inference From Observational Data With Dr Hernán
Miguel A. Hernán, MD, DrPH, professor of epidemiology, Harvard T.H. Chan School of Public Health, discusses Target Trial Emulation: A Framework for Causal Inference From Observational Data with JAMA Statistical Editor Roger J. Lewis, MD, PhD.
edhub.ama-assn.org
May 18, 2024 at 8:42 PM
With #TargetTrial emulation becoming increasingly popular, it's important to understand what it can and can't do.
In this podcast I discuss how target trial emulation can improve causal inference from observational data and extend inferences from randomized trials
edhub.ama-assn.org/jn-learning/...
In this podcast I discuss how target trial emulation can improve causal inference from observational data and extend inferences from randomized trials
edhub.ama-assn.org/jn-learning/...
Reposted by Anders Huitfeldt
New post in which I advocate for signing your peer reviews.
As always, I’m curious to hear your thoughts.
open.substack.com/pub/tpmorris...
As always, I’m curious to hear your thoughts.
open.substack.com/pub/tpmorris...
March 28, 2024 at 5:22 PM
New post in which I advocate for signing your peer reviews.
As always, I’m curious to hear your thoughts.
open.substack.com/pub/tpmorris...
As always, I’m curious to hear your thoughts.
open.substack.com/pub/tpmorris...
My attempts to convince epidemiologists and biostatisticians about the switch relative risk
March 6, 2024 at 11:59 AM
My attempts to convince epidemiologists and biostatisticians about the switch relative risk
Reposted by Anders Huitfeldt
‘Estimands: addressing some recent objections’
Just posted this one. As ever, very diplomatic!
open.substack.com/pub/tpmorris...
Just posted this one. As ever, very diplomatic!
open.substack.com/pub/tpmorris...
February 8, 2024 at 9:46 AM
‘Estimands: addressing some recent objections’
Just posted this one. As ever, very diplomatic!
open.substack.com/pub/tpmorris...
Just posted this one. As ever, very diplomatic!
open.substack.com/pub/tpmorris...
Reposted by Anders Huitfeldt
Making every researcher seek grants is a broken model
Funding should go to larger labs with many researchers, not to “principal investigators”
rootsofprogress.org/...
1/3
Funding should go to larger labs with many researchers, not to “principal investigators”
rootsofprogress.org/...
1/3
Making every researcher seek grants is a broken model
Funding should go to larger labs with many researchers, not to “principal investigators”
rootsofprogress.org
January 30, 2024 at 12:18 PM
Making every researcher seek grants is a broken model
Funding should go to larger labs with many researchers, not to “principal investigators”
rootsofprogress.org/...
1/3
Funding should go to larger labs with many researchers, not to “principal investigators”
rootsofprogress.org/...
1/3
Reposted by Anders Huitfeldt
Ooh what’s *this* on the BMJ’s front page?
‘The estimands framework: a primer on the ICH E9(R1) addendum’
Kahan, Hindley, Edwards, Cro & Morris
@brennankahan.bsky.social
www.bmj.com/content/384/...
‘The estimands framework: a primer on the ICH E9(R1) addendum’
Kahan, Hindley, Edwards, Cro & Morris
@brennankahan.bsky.social
www.bmj.com/content/384/...
The estimands framework: a primer on the ICH E9(R1) addendum
Estimands can be used in studies of healthcare interventions to clarify the interpretation of treatment effects. The addendum to the ICH E9 harmonised guideline on statistical principles for clinical ...
www.bmj.com
January 23, 2024 at 3:09 PM
Ooh what’s *this* on the BMJ’s front page?
‘The estimands framework: a primer on the ICH E9(R1) addendum’
Kahan, Hindley, Edwards, Cro & Morris
@brennankahan.bsky.social
www.bmj.com/content/384/...
‘The estimands framework: a primer on the ICH E9(R1) addendum’
Kahan, Hindley, Edwards, Cro & Morris
@brennankahan.bsky.social
www.bmj.com/content/384/...