I learned, in the same semester, how methodological rigor is the bedrock of all progress in psychological science, and that a moderated mediation model based on questionnaires from 86 undergrad students is rock-solid proof for a theory in social psychology.

Is this a thing in other fields too? The (IMO large) bad portion of the psych literature typically violates basic principles that we teach undergrads in intro methods & stats. Feeling increasingly embarrassed when I think of how awful published papers look compared to what I’m asking of my students

Bad news: additional capacity goes to patients who look remarkably similar to those already receiving care. Hence, outcomes are nonreactive. Thus, expanding the workforce doesn't inevitably reach those with the greatest need. 7/n

New meta finds no correlation between testosterone and risk preference, buuuuut testosterone was mainly measured using 2D:4D (nonsense) or saliva (still bad) and we know from Frey et al. 2017 that the risk measures don't tap into a coherent preference. www.sciencedirect.com/science/arti...

Do you sometimes think "oh boy, I would really like to hear Julia ramble some more about the topics about which she doesn't stop talking to begin with?" The wait is finally over! @guruspod.bsky.social and had a chat about open science, causal inference, and apparently birth order effects.

Really cool work!

Great talk from @lhdjung.bsky.social at the SwissRN Research-On-Research day on his, our, and other folks' work to develop trustworthiness assessment tools. Finally his {scrutiny} R package has a logo!

Very useful set of books on statistics with R #rstats #StatsSky

Just learned about this study looking at methodological trends in psych and econ over time: online.ucpress.edu/collabra/art.... Matches my perception well: Nobody in psych bothers to (explicitly) try causal inference unless they conducted an experiment, not a lot of theoretical work either.

New blog post introducing Causion - a web app for causal inference teaching and learning: pedermisager.org/blog/causion....

In sum: all global prevalence rates about gaming addiction/disorder seem to be a partial combination of both gaming *and* gambling prevalence. The same applies to other studies, which use gaming measures in relevant languages. Chinese seems to be a major exception.

behold, we found great variation in how people think! Many activities that we thought would be “gaming” weren't & vice versa, eg half of the participants interpreted ‘gambling’ to be ‘gaming’. Ergo: surveying ‘gaming’ without defining it creates data mess

..we then reviewed the next 358 studies to see if we could find more information in papers & public materials. Basically the only case where gambling was excluded was inherent language: ~30% of the studies used Chinese, where confusion shouldn’t exist. Field-wide measurement error is hence ~70%

📣 Our introduction to structural causal models in science studies is now published: doi.org/10.1162/QSS.... @tklebel.bsky.social and I tried to make our introduction as accessible as possible. We illustrate the theory by three case studies based on a simulated model of Open Science. 🧵(1/6)

We looked at 100 IGT studies and found abysmal reporting standards, and 244 different scoring techniques. Applied to a new dataset, the average correlation between these 244 techniques was 0. 5/15 IGT meta-analyses we looked at did not account for this hetereogenity.

Foody et al 2013 has over 130 citations (top 1%) as support for an element of Acceptance and Commitment Therapy's model, but it contains no evidence for that claim. This is a case study in flawed original studies being cited favorably and uncritically until it becomes a common scientific belief.🧵

The raw data is now lost to the sands of time, but a multiverse analysis can still be conducted on the differences between the conditions at post by extracting data from the figures. Results show no differences in means under any set of analytic choices.

To understand the impact of this flexibility in scoring, we ran a multiverse analysis on an open IGT dataset using 205 of the identified scores. The correlations ranged from -0.942 to 0.998 with a median r = 0.022.

But the most striking finding was in the scoring: We found 244 distinct scores used to analyze IGT outcomes. 177 of those scores appeared only once in our sample, showing a massive fragmentation in how IGT data is analyzed.

FYI to anyone whose "task queued" status never changed - there was a small bug preventing them from being processed, and this is now fixed. Your reports should be ready soon!

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...

6/🧵 I have also added integration with the ClinicalTrials.gov API. You can now provide a ClinicalTrials.gov identifier and RegCheck will automatically retrieve the registration.

5/🧵 Crucially: quote extraction is NOT done by a generative LLM. Instead, it uses embeddings-based comparisons between text chunks and user-defined comparison dimensions. This means extraction is deterministic: run RegCheck with the same inputs, you'll get the same quotes as outputs.

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

Journals that work hard to meet the needs of both authors and readers should be acknowledged publicly — encouraging others to follow suit, says researcher Jennifer A. Byrne go.nature.com/4sgKWzg

Ultimately, we may care more about the specific mechanisms than about isolating period effects. After all, those are what we can intervene on! But we can't really make progress on them just looking at variables over time and suggesting that changes are attributable to one thing or another.

The 0.5.0 version of my {brms} + {tidyverse} translation of McElreath's "Statistical Rethinking" (2nd ed) is up! solomon.quarto.pub/sr2/ 1/3 #rstats

There's still time to get your nominations in the UKRN Dorothy Bishop Prize to celebrate early career researchers! Nominations close this Sunday, 18 January 2026.

> "There is no suggestion of malpractice" The article's pubpeer thread would strongly disagree. pubpeer.com/publications...

The program for the Perspectives on Scientific Error conference Februari 11 to 13 in Leiden is online! Registration is open! perspectivesonscientificerror2026.wordpress.com This is one of the most inspiring and fun metascience meetings around - lots of time to interact, great talks - so do come!

Sign up now for the Perspectives on Scientific Error Conference (PSE) on 11 - 13 Feb in Leiden, the Netherlands We will be hosting a mentor-mentee lunch during the conference. Sign up, and you will be matched to another academic based on shared research interests! Don't miss out! See you there 🙌

As a result, children receive more vaccines today, but fewer and more targeted antigens than they did back in 1900, when only the smallpox vaccine was widely available.

NEW article by me! We can now visualize pathogens down to atoms; design vaccines in weeks; manufacture them in microbial factories; engineer them more precise than ever before. We're living through a golden age of vaccine development, but only if we continue to invest in them.

New post! There was a lot of innovation in medicine and biomedical research this year, and I've tried to summarize the biggest ones in this blogpost. Medical breakthroughs in 2025. Plus a serious note at the end. www.scientificdiscovery.dev/p/medical-br...

After 5 years of data collection, our WARN-D machine learning competition to forecast depression onset is now LIVE! We hope many of you will participate—we have incredibly rich data. If you share a single thing of my lab this year, please make it this competition. eiko-fried.com/warn-d-machi...

Explainers & tutorials are a great way to criticize current practices with a positive twist. Tailoring them to a specific substantive (!) subfield can greatly increase uptake. Forget about novelty; if some statistican said sth in the 70s but no one was around to hear it, say it again.>

Here's a suggestion for a New Year's resolution: If you see influential bad research, say something. One part of the whole replication crisis story is that a lot of psychological researchers privately knew that a lot of stuff was bad, but it wasn't discussed publicly.

The Dutch Health Council advised against default chickenpox vaccination in 2020. Meanwhile 95% of children in NL get infected by age 6 and ~250 are hospitalised per year. You could cut that number by 99%, prevent all young deaths, protect older people, AND save money! Just mind-boggling

It seems bookdown is shutting down, and so I've migrated the free online version of Evaluating What Works here: dorothybishop-evaluating-what-works.share.connect.posit.cloud Hard copy also available here: www.routledge.com/Evaluating-W...

Woohoo! Chickenpox vaccines are on the menu in the UK - finally!! www.theguardian.com/commentisfre...

The 1.3.0 version of my {brms} + {tidyverse} translation of Kruschke's "Doing Bayesian data analysis" is up! solomon.quarto.pub/dbda2 #rstats 1/8

Fantastic! $650k awarded via the Research Software Maintenance Fund for “Enabling the Next Generation of Contributors to R”—mentoring new contributors, modernizing R’s dev infrastructure, and strengthening the R Foundation. r-consortium.org/posts/650K-f... #rstats

See @jamiecummins.bsky.social 's work

Did you know that from tomorrow, Qualtrics is offering synthetic panels (AI-generated participants)? Follow me down a rabbit hole I'm calling "doing science is tough and I'm so busy, can't we just make up participants?"

Very happy to have received a replication grant from NWO! We will be reproducing power analyses of large scale replication projects, to learn how to improve power analyses, and increase quality control in large team Science projects! www.openscience.nl/en/news/27-s...

Oh, I thought it was a quantifounder (a quantifier for confounders). iirc there are two of them 'exposome': exposure at least one confounder 'exposall': exposed to all the confounders

Post-publication peer review is at it best when it's thoughtful, scrupulous, steeped in detail – and challenges key claims of the paper. @janhove.bsky.social's discussion of a recent paper on multilingualism exemplifies this.

I’ll leave it to onlookers to decide for themselves what this implies about the floor of credibility of articles published in an outlet with such a prestigious name @nataging.nature.com

That any association disappears when GDP is taken into account might not be surprising, but I’m glad Jan actually put in the necessary work to reanalyse 🫡 true community service.

You remember that Nature Aging paper about how multilingualism protects against accelerated aging? Well…