Adrien Fillon
@adrienfillon.bsky.social
Social psychologist working at LAPSCO, CNRS in Clermont-Ferrand. Meta science - meta-analysis - policy change
Reposted by Adrien Fillon
Whenever I see campaigns such as this, I'm reminded of the 2021 tweet from Surrey Poilce
November 27, 2025 at 9:37 AM
Whenever I see campaigns such as this, I'm reminded of the 2021 tweet from Surrey Poilce
Reposted by Adrien Fillon
Absolutely none of which matters when motorists speed, play on their phones, drive drunk/drugged/tired, or simply believe they own the road.
My first email this morning is from a resident about motorists speeding through pedestrian lights near homes, schools, a church and a library.
It's constant.
My first email this morning is from a resident about motorists speeding through pedestrian lights near homes, schools, a church and a library.
It's constant.
👀 Can you see me now?
The importance of visibility on our roads cannot be understated, particularly for vulnerable road users including pedestrians, cyclists, e-scooter drivers and motorcyclists.
#CanYouSeeMeNow #KeepingPeopleSafe
The importance of visibility on our roads cannot be understated, particularly for vulnerable road users including pedestrians, cyclists, e-scooter drivers and motorcyclists.
#CanYouSeeMeNow #KeepingPeopleSafe
November 27, 2025 at 9:02 AM
Absolutely none of which matters when motorists speed, play on their phones, drive drunk/drugged/tired, or simply believe they own the road.
My first email this morning is from a resident about motorists speeding through pedestrian lights near homes, schools, a church and a library.
It's constant.
My first email this morning is from a resident about motorists speeding through pedestrian lights near homes, schools, a church and a library.
It's constant.
Reposted by Adrien Fillon
All three books I've co-authored are freely available online for non-commercial use:
- #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/
- #Regression and Other Stories at avehtari.github.io/ROS-Examples/
- Active Statistics at avehtari.github.io/ActiveStatis...
- #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/
- #Regression and Other Stories at avehtari.github.io/ROS-Examples/
- Active Statistics at avehtari.github.io/ActiveStatis...
August 2, 2024 at 1:35 PM
All three books I've co-authored are freely available online for non-commercial use:
- #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/
- #Regression and Other Stories at avehtari.github.io/ROS-Examples/
- Active Statistics at avehtari.github.io/ActiveStatis...
- #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/
- #Regression and Other Stories at avehtari.github.io/ROS-Examples/
- Active Statistics at avehtari.github.io/ActiveStatis...
Reposted by Adrien Fillon
New paper in @jclinepi.bsky.social led by my super cool PhD student @kahin-tai.bsky.social with the SHARE-CTD (@sharectd.bsky.social) crew. It is the 2nd paper in a “JCE trilogy” on data sharing by SHARE-CTD: the 1st one addressed the topic in broad terms, and the third will focus on data reuse.
Key Concepts in Clinical Epidemiology: FAIRification of Biomedical Research Data
The FAIR guiding principles promote Findability, Accessibility, Interoperability,
and Reuse of data to enhance data management and stewardship. In biomedicine, particular
ethical, legal, and technical...
www.jclinepi.com
August 10, 2025 at 7:21 AM
New paper in @jclinepi.bsky.social led by my super cool PhD student @kahin-tai.bsky.social with the SHARE-CTD (@sharectd.bsky.social) crew. It is the 2nd paper in a “JCE trilogy” on data sharing by SHARE-CTD: the 1st one addressed the topic in broad terms, and the third will focus on data reuse.
Reposted by Adrien Fillon
When the World Bank publishes new poverty estimates, it makes headlines. But making sense of these numbers is harder than it looks! Inflation, PPPs, national poverty lines, real incomes…There’s a lot going on.
In this article my colleagues explain where the new numbers come from and what changed
In this article my colleagues explain where the new numbers come from and what changed
$3 a day: A new poverty line has shifted the World Bank’s data on extreme poverty. What changed, and why?
In June 2025, the World Bank increased its extreme poverty estimates by 125 million people. This doesn’t mean the world has gotten poorer: it reflects a new, higher International Poverty Line of $3 a ...
ourworldindata.org
August 11, 2025 at 5:51 PM
When the World Bank publishes new poverty estimates, it makes headlines. But making sense of these numbers is harder than it looks! Inflation, PPPs, national poverty lines, real incomes…There’s a lot going on.
In this article my colleagues explain where the new numbers come from and what changed
In this article my colleagues explain where the new numbers come from and what changed
Reposted by Adrien Fillon
Want to get deeper intuition for a mathematical or statistical concept?
I find that one of the best ways is to dig into its history.
New post: kucharski.substack.com/p/to-underst...
I find that one of the best ways is to dig into its history.
New post: kucharski.substack.com/p/to-underst...
To understand mathematical concepts, look to history
Someone, somewhere came up with it for a reason
kucharski.substack.com
August 11, 2025 at 5:31 PM
Want to get deeper intuition for a mathematical or statistical concept?
I find that one of the best ways is to dig into its history.
New post: kucharski.substack.com/p/to-underst...
I find that one of the best ways is to dig into its history.
New post: kucharski.substack.com/p/to-underst...
Reposted by Adrien Fillon
Reminder that all three books I've co-authored are freely available online for non-commercial use (and the fourth will be, too)
All three books I've co-authored are freely available online for non-commercial use:
- #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/
- #Regression and Other Stories at avehtari.github.io/ROS-Examples/
- Active Statistics at avehtari.github.io/ActiveStatis...
- #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/
- #Regression and Other Stories at avehtari.github.io/ROS-Examples/
- Active Statistics at avehtari.github.io/ActiveStatis...
August 11, 2025 at 5:44 PM
Reminder that all three books I've co-authored are freely available online for non-commercial use (and the fourth will be, too)
Reposted by Adrien Fillon
Perfect algorithmic timeline
November 27, 2025 at 7:09 AM
Perfect algorithmic timeline
Reposted by Adrien Fillon
Now might be a good time to repost this story about what scientists actually know about the complex causes of autism, and what's behind the increasing prevalence.
www.nature.com/articles/d41...
www.nature.com/articles/d41...
Autism is on the rise: what’s really behind the increase?
RFK Jr has vowed to find out what’s responsible, but scientists say he is ignoring answers from decades of research.
www.nature.com
September 22, 2025 at 3:17 PM
Now might be a good time to repost this story about what scientists actually know about the complex causes of autism, and what's behind the increasing prevalence.
www.nature.com/articles/d41...
www.nature.com/articles/d41...
Reposted by Adrien Fillon
If you're a journal or publisher using institutional email addresses to verify the identity of authors or reviewers, you'll want to read this story by @joelving.bsky.social.
University email addresses no longer effective bulwark against fake peer review
To guard against identity theft, academic publishers have been using institutional email addresses to verify authors and reviewers are who they say they are. Now, however, findings appearing in a p…
retractionwatch.com
September 22, 2025 at 1:55 PM
If you're a journal or publisher using institutional email addresses to verify the identity of authors or reviewers, you'll want to read this story by @joelving.bsky.social.
Reposted by Adrien Fillon
Reposted by Adrien Fillon
New blog post from Data Colada, responding to the recent criticisms on p-curve analysis. It is a *very* good response. As in, it addresses exactly the points I would have expected in a reply, and it explains why I will still teach p-curve analysis. datacolada.org/129
September 23, 2025 at 12:41 PM
New blog post from Data Colada, responding to the recent criticisms on p-curve analysis. It is a *very* good response. As in, it addresses exactly the points I would have expected in a reply, and it explains why I will still teach p-curve analysis. datacolada.org/129
Reposted by Adrien Fillon
"OpenAi déclare ne pas être responsable du suicide d'un utilisateur dont le chat a encouragé le suicide, parce que se suicider est interdit par les conditions d'utilisation"
...est une des phrases les plus dystopiques que vous lirez aujourd'hui
Mais bordel.
...est une des phrases les plus dystopiques que vous lirez aujourd'hui
Mais bordel.
OpenAI says they aren't liable for the suicide of a user their chat bot urged to kill himself because suicide is a violation of the TOS
Additionally, OpenAI argues its not liable because Raine, by using ChatGPT for self-harm, broke its terms of service
November 26, 2025 at 7:43 AM
"OpenAi déclare ne pas être responsable du suicide d'un utilisateur dont le chat a encouragé le suicide, parce que se suicider est interdit par les conditions d'utilisation"
...est une des phrases les plus dystopiques que vous lirez aujourd'hui
Mais bordel.
...est une des phrases les plus dystopiques que vous lirez aujourd'hui
Mais bordel.
Reposted by Adrien Fillon
Reposted by Adrien Fillon
Following the controversy surrounding the p-curve technique, I wanted to better understand how the z-curve (a technique that solves several problems with the p-curve) works. I created a Bayesian version of the z-curve in Stan, and I'm quite pleased with the outcome 🙂
August 10, 2025 at 8:03 PM
Following the controversy surrounding the p-curve technique, I wanted to better understand how the z-curve (a technique that solves several problems with the p-curve) works. I created a Bayesian version of the z-curve in Stan, and I'm quite pleased with the outcome 🙂
Reposted by Adrien Fillon
NEW PREPRINT
Explainable AI refers to an extremely popular group of approaches that aim to open "black box" AI models. But what can we see when we open the black AI box? We use Galit Shmueli's framework (to describe, predict or explain) to evaluate
arxiv.org/abs/2508.05753
Explainable AI refers to an extremely popular group of approaches that aim to open "black box" AI models. But what can we see when we open the black AI box? We use Galit Shmueli's framework (to describe, predict or explain) to evaluate
arxiv.org/abs/2508.05753
August 11, 2025 at 6:53 AM
NEW PREPRINT
Explainable AI refers to an extremely popular group of approaches that aim to open "black box" AI models. But what can we see when we open the black AI box? We use Galit Shmueli's framework (to describe, predict or explain) to evaluate
arxiv.org/abs/2508.05753
Explainable AI refers to an extremely popular group of approaches that aim to open "black box" AI models. But what can we see when we open the black AI box? We use Galit Shmueli's framework (to describe, predict or explain) to evaluate
arxiv.org/abs/2508.05753
Reposted by Adrien Fillon
Not actually the fall, but the less rapid rise.
August 11, 2025 at 6:22 AM
Not actually the fall, but the less rapid rise.
Reposted by Adrien Fillon
OpenAlex intégré au Web of Science, ou la capture du travail des “commoners” | carnetist.hypotheses.org/2572
OpenAlex intégré au Web of Science, ou la capture du travail des “commoners”
C’est une annonce qui est passée relativement inaperçue, mais qui mérite que l’on s’y arrête un instant. Clarivate a récemment annoncé l’intégration d’OpenAlex comme une nouvelle base de données au se...
carnetist.hypotheses.org
November 25, 2025 at 7:11 AM
OpenAlex intégré au Web of Science, ou la capture du travail des “commoners” | carnetist.hypotheses.org/2572
Reposted by Adrien Fillon
Scientific error-checking, difficulty: easy
Find some issues in this table of results from an RCT of vitamin D for COVID-19. There's a couple of obvious issues, and some that are less easy to spot.
Find some issues in this table of results from an RCT of vitamin D for COVID-19. There's a couple of obvious issues, and some that are less easy to spot.
November 25, 2025 at 4:59 AM
Scientific error-checking, difficulty: easy
Find some issues in this table of results from an RCT of vitamin D for COVID-19. There's a couple of obvious issues, and some that are less easy to spot.
Find some issues in this table of results from an RCT of vitamin D for COVID-19. There's a couple of obvious issues, and some that are less easy to spot.
Reposted by Adrien Fillon
Le fichier TES centralise les photos et empreintes digitales que nous donnons pour faire nos titres d'identité. Nous révélons que la police se sert allègrement dans cette base de données pour identifier des personnes lors de ses enquêtes, en violation du droit. www.laquadrature.net/2025/11/24/l...
La police détourne le fichier des passeports et des cartes d’identité
Fournir sa photographie et ses empreintes quand on demande son passeport ou sa carte d’identité est plus lourd de conséquence que ce qu’on imagine. Ces données, qui sont enregistrées dans le fichier…
www.laquadrature.net
November 24, 2025 at 12:07 PM
Le fichier TES centralise les photos et empreintes digitales que nous donnons pour faire nos titres d'identité. Nous révélons que la police se sert allègrement dans cette base de données pour identifier des personnes lors de ses enquêtes, en violation du droit. www.laquadrature.net/2025/11/24/l...
Reposted by Adrien Fillon
One of the giants of social psychology was a serial sexual harasser.
This new report reveals how Miles Hewstone touched, bullied, and sexual harassed numerous women during his 18 years at the University of Oxford. It's amazing how often bullying and sexual harassment go together in academia.
This new report reveals how Miles Hewstone touched, bullied, and sexual harassed numerous women during his 18 years at the University of Oxford. It's amazing how often bullying and sexual harassment go together in academia.
November 19, 2025 at 10:30 PM
One of the giants of social psychology was a serial sexual harasser.
This new report reveals how Miles Hewstone touched, bullied, and sexual harassed numerous women during his 18 years at the University of Oxford. It's amazing how often bullying and sexual harassment go together in academia.
This new report reveals how Miles Hewstone touched, bullied, and sexual harassed numerous women during his 18 years at the University of Oxford. It's amazing how often bullying and sexual harassment go together in academia.
Reposted by Adrien Fillon
Yesterday we were delighted to welcome @adrienfillon.bsky.social for two sharp and thought-provoking talks on scientific publishing practices and the limits of meta-analyses.
Thank you for inspiring us to pursue science that is more open and built on integrity.
Thank you for inspiring us to pursue science that is more open and built on integrity.
November 22, 2025 at 1:21 PM
Yesterday we were delighted to welcome @adrienfillon.bsky.social for two sharp and thought-provoking talks on scientific publishing practices and the limits of meta-analyses.
Thank you for inspiring us to pursue science that is more open and built on integrity.
Thank you for inspiring us to pursue science that is more open and built on integrity.
Reposted by Adrien Fillon
Interesting read, but worth considering (as the article does) the selection bias introduced by a) who is willing to initiate an adversarial collaboration and b) who manages to compete and publish it.
📚 Reflections on adversarial collaboration from the adversaries: was it worth it?
link.springer.com/article/10.1...
link.springer.com/article/10.1...
Reflections on adversarial collaboration from the adversaries: was it worth it? - Theory and Society
There is much enthusiasm, in principle, for adversarial collaborations (ACs), a scientific conflict resolution technique that encourages investigators with clashing models to collaborate in designing ...
link.springer.com
August 8, 2025 at 9:50 AM
Interesting read, but worth considering (as the article does) the selection bias introduced by a) who is willing to initiate an adversarial collaboration and b) who manages to compete and publish it.
Reposted by Adrien Fillon
Thank you for this very impressive resource of 50 (!) reproducibility/replicability metrics; also includes a searchable online table at rachelheyard.com/reproducibil...
August 8, 2025 at 12:31 PM
Thank you for this very impressive resource of 50 (!) reproducibility/replicability metrics; also includes a searchable online table at rachelheyard.com/reproducibil...
Reposted by Adrien Fillon
In our next episode of Nullius In Verba we will dive into the history of metascience. The first mention of 'metascience' in the literature we could find is Morris, 1938. Do you know of an earlier mention of the term 'metascience'?
August 6, 2025 at 4:40 PM
In our next episode of Nullius In Verba we will dive into the history of metascience. The first mention of 'metascience' in the literature we could find is Morris, 1938. Do you know of an earlier mention of the term 'metascience'?