Adrien Fillon
LightNews LightNews
adrienfillon.bsky.social
Adrien Fillon
@adrienfillon.bsky.social
1.1K followers 640 following 290 posts
Social psychologist working at LAPSCO, CNRS in Clermont-Ferrand. Meta science - meta-analysis - policy change
Posts Replies Media Videos
Reposted by Adrien Fillon
richardmonvoisin.bsky.social
J'ai fini les 6 épisodes du super entretien sur la fraude en psycho avec Nick Brown, dans "Répare ta science".
Quelle opiniâtreté dans la quête des fraudes en #psycho !
(je n'ai pas tout tout compris mais ce n'est pas grave)
Merci Adrien Fillon et Nathanaël Larigaldie !
logo de Répare ta science, avec un marteau photo de Nick Brown
January 28, 2026 at 5:51 PM
Reposted by Adrien Fillon
peerreviewcongress.bsky.social
#OA articles are cited more, help citizen scientists learn more about the topic they've helped on, but there’s little strong evidence they have other long-lasting effects on research, or many economic and social benefits www.science.org/content/arti...
@jeffreybrainard.bsky.social @science.org
Is ‘open science’ delivering benefits? Major study finds proof is sparse
It’s hard to measure social and economic impacts of making papers and data free, researchers say
www.science.org
January 2, 2026 at 10:54 AM
Reposted by Adrien Fillon
monicamedhist.bsky.social
This report in Nature on the costs of competing for & administering scientific grants is shocking: "In other words, European taxpayers will have spent more on the funding process than on the funding itself, and the scientific ecosystem has been drained." www.nature.com/articles/d41... 🧪
Point of no returns: researchers are crossing a threshold in the fight for funding
With so little money to go round, the costs of competing for grants can exceed what the grants are worth. When that happens, nobody wins.
www.nature.com
December 19, 2025 at 6:46 PM
Reposted by Adrien Fillon
paulgp.com
Check out the new and improved @paperposterbot.bsky.social using Typst to construct abstract images
apoorvalal.com apoorva lal @apoorvalal.com · 26d
in action [no author info embedded here because it grabbed something off the arxiv archive where metadata wasn't stored properly]
bsky.app/profile/pape...
paperposterbot.bsky.social ArXiv Paperboy (Stat.ME+Econ.EM) @paperposterbot.bsky.social · 26d
arXiv📈🤖 New Paper
KSD Aggregated Goodness-of-fit Test
By
January 2, 2026 at 1:50 PM
Reposted by Adrien Fillon
tkes.bsky.social
01 Nov, Sleuths: 👋Hey, @bmj.com ! This RCT you just published is filled with 🐂💩 and data is obviously fabricated😱
14 Nov, BMJ: 🙏"Might we [...] harness the talents of internet sleuths who are expert at identifying flaws?"
[🐌🥱]
05 Jan, Sleuths: 😤Hey, still not retracted
05 Jan, BMJ: Let me cook!🥸
January 6, 2026 at 2:59 AM
Reposted by Adrien Fillon
jayvanbavel.bsky.social
Does AI improve or undercut academic scholarship?

A new study finds that academics who use AI increased both the quantity & quality of their academic scholarship and it appears to reduces inequality (helping junior and non-english speaking scholars the most).
arxiv.org/pdf/2510.02408
October 11, 2025 at 3:39 PM
Reposted by Adrien Fillon
dszlosek.bsky.social
S-Values are much more interpretable than P-values, yet adoption seems near impossible. I wonder what it would take to make the leap? #statssky #episky #rstats #statistics
October 10, 2025 at 3:50 PM
Reposted by Adrien Fillon
markrubin.bsky.social
Stagnant Research Programmes

"There are good reasons why thousands of physicists are still spending their lifetimes on research programmes which, according to Lakatos, can in no way be considered progressive, and in which the occasional empirical problem shift may be forever absent."
Stagnant Lakatosian research programmes - European Journal for Philosophy of Science
We extend Lakatos’s classical dichotomy of research programmes—progressive vs. degenerative—by introducing a neutral third category: the stagnant research programme. First, a critical examination of the primary literature with its often criticized definitional gaps justifies such a category. By deriving general criteria for stagnation, we clearly distinguish stagnant programmes from those that are progressive or degenerative. An empirical cross-check is subsequently employed for support: Both a series of examples from fundamental physics and a general analysis of today’s research landscape also suggest on an empirical level the need to go beyond the traditional Lakatosian conception. Attributing stagnation is entirely in line with Lakatos’ original intentions, which aimed not to hastily discard promising research but to exercise patience until the lifting of certain external constraints potentially enables empirical progress once again.
doi.org
October 10, 2025 at 2:49 PM
Reposted by Adrien Fillon
dingdingpeng.the100.ci
Evolutionary psychologists have claimed that "humans evolved heightened sensitivity to harm directed at women." This excellent (albeit at times gruesome) post makes the point that the ethnographic evidence does not really support this narrative.
Did humans evolve to 'protect' women?
Ethnography complicates a convenient narrative
traditionsofconflict.substack.com
October 7, 2025 at 7:28 AM
Reposted by Adrien Fillon
rmcelreath.bsky.social
This is a nice paper. It faces down a common problem: in order to explain to why a common approach cannot work even in theory, we first need to teach a framework in which regression is not magic that tells us which variables on right cause the variable on left. It's exhausting.

Anyway great paper!
October 7, 2025 at 11:38 AM
Reposted by Adrien Fillon
uneheuredepeine.bsky.social
Une alerte de plus sur l’état gravissime d’une profession et surtout du plus grand des services publics www.lemonde.fr/societe/arti...

Mais pourquoi en faire un enjeu politique hein ? Pourquoi en parler ?
L’ampleur du mal-être des enseignants français confirmé par une enquête internationale
L’enquête Talis, menée par l’OCDE sur un échantillon de 280 000 enseignants et publiée mardi, est la plus grande étude consacrée à la profession. Les résultats de l’édition 2024 de ce bilan quinquenna...
www.lemonde.fr
October 7, 2025 at 4:11 AM
Reposted by Adrien Fillon
moritzdrupp.bsky.social
🌍📈 Paper “The Economics of Inequality and the Environment” out today in the Journal of Economic Literature @aeajournals.bsky.social, joint with Jasper Meya, Lutz Sager & Ulrike Kornek.

See short summary and PM by PIK linked below, and the paper here
👉 pubs.aeaweb.org/doi/pdfplus/...
September 1, 2025 at 11:28 AM
Reposted by Adrien Fillon
dingdingpeng.the100.ci
Just finished reading this *excellent* article by Gabriel et al. which discusses which effects can be identified in randomized controlled trials. With DAGs!>

link.springer.com/article/10.1...
Elucidating some common biases in randomized controlled trials using directed acyclic graphs Although the ideal randomized clinical trial is the gold standard for causal inference, real randomized trials often suffer from imperfections that may hamper causal effect estimation. Stating the estimand of interest can help reduce confusion about what is being estimated, but it is often difficult to determine what is and is not identifiable given a trial’s specific imperfections. We demonstrate how directed acyclic graphs can be used to elucidate the consequences of common imperfections, such as noncompliance, unblinding, and drop-out, for the identification of the intention-to-treat effect, the total treatment effect and the physiological treatment effect. We assert that the physiological treatment effect is not identifiable outside a trial with perfect compliance and no dropout, where blinding is perfectly maintained Table 1 showing the Identifiability of target estimands depending on whether there is blinding, full compliance, and no drop-out An example DAG from the paper. Fig. 4: A blinded trial with noncompliance. U are unobserved confounders, Z is treatment assignment, C is compliance, X is the realized treatment, S is the subject's physical and mental health status, Xself and Xcln are the treatment that the participant and the clinician believed the participant received, Y is the outcome.
October 2, 2025 at 8:09 AM
Reposted by Adrien Fillon
mitildide.bsky.social
En 2023, la psychologue Caroline Goldman avait réalisé cette chronique sur @franceinter.fr, où elle reprenait plusieurs fake news anti-trans.

On apprend aujourd'hui que Caroline Goldman est membre de l'Observatoire de la Petite Sirène, un lobby anti-trans.
www.radiofrance.fr/franceinter/...
La dysphorie de genre
Le fait de ne pas se sentir appartenir à son sexe biologique était un motif de consultation assez rare quand j’ai commencé ma carrière il y a 20 ans. Aujourd’hui, cette question occupe beaucoup la péd...
www.radiofrance.fr
January 26, 2026 at 10:31 AM
Reposted by Adrien Fillon
randalljellis.bsky.social
I started a podcast! Metascience Matters features conversations with metascientists.

Two episodes are live:

Chirag Patel on Exposomics, and Vibration of Effects: youtu.be/RT2nypyb-iM?...

@floriannaudet.bsky.social on Clinical Trials, Registered Reports, and Psychiatry: youtu.be/fn4qtnc99Xo?...
Exposomics, Vibration-of-Effects, and the Future of AI in Health | Metascience Matters #1
YouTube video by Metascience Matters
youtu.be
January 23, 2026 at 12:49 PM
Reposted by Adrien Fillon
floriannaudet.bsky.social
New post on ResToRes's website: "The Lancet–WCRIF commission on research integrity"
A new Lancet–WCRIF Commission on Research Integrity takes aim at the growing crisis of fake science and questionable research practices, calling for coordinated global action.
restores.univ-rennes.fr/highlights/l...
October 5, 2025 at 7:52 AM
Reposted by Adrien Fillon
xkcd.com
Replication Crisis

xkcd.com/3117/
4-panel comic. (1) [Person 1 with ponytail flanked by person with short hair and another person speaking into microphone at podium] PERSON 1: In the early 2010s, researchers found that many major scientific results couldn’t be reproduced. (2) PERSON 1: Over a decade into the replication crisis, we wanted to see if today’s studies have become more robust. (3) PERSON 1: Unfortunately, our replication analysis has found exactly the same problems that those 2010s researchers did. (4) [newspaper with image of speakers from previous panels] Headline: Replication Crisis Solved
July 21, 2025 at 11:54 PM
Reposted by Adrien Fillon
gunnarblohm.bsky.social
www.nature.com/articles/d41...
How to find the papers you need to read — and avoid the ones you don’t
With thousands of papers being published everyday, it can be a task working out which matter. Here are some tips to help you decide.
www.nature.com
October 2, 2025 at 12:54 AM
Reposted by Adrien Fillon
rmcelreath.bsky.social
Was asked about collinearity again, so here's Vahove's 2019 post on why it isn't a problem that needs a solution. Design the model(s) to answer a formal question and free your mind janhove.github.io/posts/2019-0...
tl;dr Collinearity is a form of lack of information that is appropriately reflected in the output of your statistical model. When collinearity is associated with interpretational difficulties, these difficulties aren’t caused by the collinearity itself. Rather, they reveal that the model was poorly specified (in that it answers a question different to the one of interest), that the analyst overly focuses on significance rather than estimates and the uncertainty about them or that the analyst took a mental shortcut in interpreting the model that could’ve also led them astray in the absence of collinearity. If you do decide to “deal with” collinearity, make sure you can still answer the question of interest.
October 1, 2025 at 5:29 AM
Reposted by Adrien Fillon
dingdingpeng.the100.ci
Looks like my favorite paper on the age trajectory of happiness is finally out!!! So happy for the authors. Go check it out, it’s great.
September 29, 2025 at 6:38 PM
Reposted by Adrien Fillon
dingdingpeng.the100.ci
Some years ago I wrote a paper for an Econ journal (don’t ask) and the editor/reviewers suggested to control our age trajectories for all sorts of variables, which resulted in this blog post with my favorite TL;DR to date:

www.the100.ci/2017/04/21/w...
What’s an age-effect net of all time-varying covariates?
TL;DR: What’s an age-effect net of all time-varying covariates? The sound of one hand clapping. Recently, we submitted a paper with some age trajectories of measures of individuals’ (un-)well-being....
www.the100.ci
September 30, 2025 at 5:30 AM
Reposted by Adrien Fillon
floriannaudet.bsky.social
Super happy to be interviewed by Randy Ellis for his Metascience Matters podcast 🎙️

Really fun and open discussion. Less about meta-science in the narrow sense, and more about science as it’s actually practiced, plus the everyday realities of academic life.

Thanks Randy for the great conversation!
Esketamine for depression, registered reports, and alcohol use disorder | Metascience Matters #2
YouTube video by Metascience Matters
www.youtube.com
January 23, 2026 at 8:00 AM
Reposted by Adrien Fillon
ianhussey.mmmdata.io
RegCheck is one of our group's most exciting projects IMO, and I'm particularly happy to see the codebase now be open scourced!
jamiecummins.bsky.social Jamie Cummins @jamiecummins.bsky.social · 6d
8/🧵

Finally, I fulfill something long-promised: a full, open-source release of the entire RegCheck codebase.

This comes with instructions on how to run RegCheck locally, both as a local implementation of the GUI, and as a standalone CLI application. Find the code here:

github.com/JamieCummins...
GitHub - JamieCummins/regcheck
Contribute to JamieCummins/regcheck development by creating an account on GitHub.
github.com
January 22, 2026 at 11:57 AM
Reposted by Adrien Fillon
jamiecummins.bsky.social
Comparing registrations to published papers is essential to research integrity - and almost no one does it routinely because it's slow, messy, and time-demanding.

RegCheck was built to help make this process easier.

Today, we launch RegCheck V2.

🧵

regcheck.app
RegCheck
RegCheck is an AI tool to compare preregistrations with papers instantly.
regcheck.app
January 22, 2026 at 11:05 AM
Reposted by Adrien Fillon
Once more about the z-curve method
statmodeling.stat.columbia.edu/2026/01/20/o...
Once more about the z-curve method | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
January 20, 2026 at 6:30 PM