I wish I could write like this. And I wish Lindy West wrote tutorial papers in psychometrics. (Source: Lindy West, 2019 essay collection 'The Witches Are Coming')

{easystats} is not only highly functional and powerful, but their help is also a goldmine of accessible #statistics advice. Here explaining how to address high VIF values (hint: generally not by removing predictors, as often done) easystats.github.io/performance/... Thanks @easystats.github.io

The methods section is the most important section of a paper. Without knowing the methods, the results are literally meaningless. So it's not OK to relegate the methods to the end. Because this suggests they are an optional afterthought rather than the essential core of the entire paper.

Is it just me, or are Zenodo DOI links (for GitHub README markdown files) broken? I just get a broken link symbol, even for repos that used to work. If I use the image link separately, it renders fine in the browser. Example repo: github.com/pgmj/easyRas...

I think this is relevant for most complex tasks.

#StatsPubs No matter how many times you read it, this paper on hierarchical GAMs keeps giving. Clear model explanations together with R code (mgcv). So useful! doi.org/10.7717/peer... Thanks for writing @ericjpedersen.bsky.social, D. Miller, @gsimpson.bsky.social @noamross.net

#MetaScience How useful are open data when we do not have open results? (At least APA does not claim to be a scientific organization) replicationindex.com/2026/05/16/o...

New Jamovi module functionality to determine appropriate model fit cutoffs for confirmatory factor analysis now available in easyRasch2jmv v0.4.0. Install/update from Jamovi Library within the app. #rstats #psychometrics #stats #openscience

Oh my. This is spectacular. sinceyouarrived.world/taken

Speaking of crazy d values, this reminds me of this feature I was thinking about adding to the forest() function in metafor. #Rstats #MetaAnalysis

So tired of the mindless use of mean/SD to describe data when it is obviously not very useful. Most recent example "patients had suffered from depression on average for 7.6 years (SD = 7.1)" Same paper reports BDI post treatment scores with mean 6.64 (SD = 8.04), when 0 is the lowest possible score.

Does anyone know of a tidy dataset with a large number of common multi-item self-report psychology scales? Ideally clinical. The data does not have to be within-subject, just a variety of common scales with decent N. I have: - Bainbridge et al - AIID dataset - Ideologies 2.0 dataset

I did not know this.

New family member today.

Two simulation studies in this paper show that doubly robust methods for causal inference—especially regression weighted by inverse propensity scores—are more robust to model misspecification than traditional regression across many scenarios. link.springer.com/article/10.3...

🔥 Announcing StanCon 2026 Program 🔥 Now we have a program for StanCon 2026 in Uppsala in August 17-21! discourse.mc-stan.org/t/announcing...

I just tried some initial data visualization of a new dataset using {ggauto} by @nrennie.bsky.social and it makes the process quite a bit faster. Nice addition to the toolbox!

I've made an R package for Bayesian Rasch #psychometrics with brms models, easyRaschBayes (on CRAN), implementing simple functions to create figures and tables with model fit metrics, etc. Attaching figures from conditional item infit, item-restscore with GK gamma, and the log-likelihood criterion.

Good news everyone 🥳 Our (w @vincentab.bsky.social) primer on models as prediction machines (with the marginaleffects package) is finally officially published!> journals.sagepub.com/doi/10.1177/...

“Dear friends, you, however, are real persons! Creation itself has a body, a breath, a life to be listened to and safeguarded.”

Up to 2008 there were over 1700 published gene/schizophrenia association studies implicating over 1000 genes. Now none of these studies are viewed as useful. -- Legge et al., 2025 What a fascinating post-mortem this would make for a meta-science project. #neuroscience #stats #metascience

I've made a Jamovi module for modern psychometric analysis using Rasch Measurement Theory, "easyRasch2jmv", that is available in Jamovi's library. The module implements simulation-based (dynamic) cutoff values for conditional item fit and residual correlations, amongst other things. #psychometrics

What if rebuilding the middle class started at the community level? Our newest post looks at how local systems shape opportunity—and how we can create real change from the ground up. Read, like, comment, and share: snapt.io/MoGFe Subscribe for more: #CommunityChange #EconomicJustice #SystemsChange

I've made a Jamovi module for modern psychometric analysis using Rasch Measurement Theory, "easyRasch2jmv", that is available in Jamovi's library. The module implements simulation-based (dynamic) cutoff values for conditional item fit and residual correlations, amongst other things. #psychometrics

“If people worldwide biked at rates of Dutch, avg 2.6 km per person per day, global emissions could fall by 686 million tonnes of CO2 annually, comparable to Canada’s total annual emissions … For short trips, cycling is often faster, cheaper, and healthier” www.nationalobserver.com/2026/04/07/o...

More books should show full workflows of how to apply methods.

Williams, McGillycuddy, Brooks, Bolker, Mizuno, Yang, Viechtbauer, Warton, Nakagawa: Meta-analysis with the glmmTMB R package https://arxiv.org/abs/2604.04084 https://arxiv.org/pdf/2604.04084 https://arxiv.org/html/2604.04084

Our research group in Bern has been awarded two @snsf.ch project grants! We will hire a number of new postdocs and PhD students. Congratulations to @jamiecummins.bsky.social @malte.the100.ci and @ndevito1.bsky.social whose project deepens the links between @bennettoxford.bsky.social and @unibe.ch

🎉 ggauto is now on CRAN 🎉 An #RStats package that selects better chart types, and provides more accessible styling for #ggplot2 plots 📊 Blog post explaining why I made it and how it works: nrennie.rbind.io/blog/introdu... #DataViz

Statistical Rethinking 2026 is done: 20 new lectures emphasizing logical and critical statistical workflow, from basics of probability theory to causal inference to reliable computation to sensitivity. It's all free, made just for you. Lecture list and links: github.com/rmcelreath/s...

I made a tiny tool for quickly sharing small datasets (< ~1000 rows) without uploading any data to a server. 🔗 ziptbl.com It compresses the data into the link itself, so there’s no account, hosting, or storage layer involved. Here's Florence Nightingale's famous 📊 data: ziptbl.com#d=eNpdlE-LGz...

Finally got around to try the markdown notes app notable.app which seems really great! No vendor or platform lock-in. Surprised at how well it handles pasting images/screenshots on MacOS.

Zero responses. Is this not a problem?

I had somehow not noticed the 2.0 release of {lme4} last week, which includes functionality to specify structured covariance matrices. Nice! #rstats cran.r-project.org/web/packages...

Any good papers on the problems with meta-analysis when the outcome variable's data generating process is (zero-inflated) negative binomial and not well represented by mean/SD? Suggested solutions also appreciated #stats #rstats

But the policymakers who ultimately determine whether the fines, judgments and criminal penalties outstrip the profits from spying - they work for *us*. They draw their paychecks from the public purse in exchange for safeguarding *our* interests, and they have manifestly failed at this. 10/

Now published in Collabra! online.ucpress.edu/collabra/art... Using test data from TwinLife (N=9,980, Culture Fair Test CFT 20-R), we show that Regularised Prediction and Poststratification yields IQ scores that differ by up to 19 IQ points (mean 4.19 pts) from those reported in the CFT 20-R manual

Finally got around to adding fancy links to my different interactive teaching websites for showing things like p-hacking, p-value interpretations, and (still-in-draft-form) DAGs at www.andrewheiss.com/teaching/ #rstats #QuartoPub #statsky

Americans will do anything to avoid using the metric system.

I joined the boycott. Consider joining yourself. All AI is dangerous but ChatGPT's developers are truly devoid of conscience.

#stats Here's a nifty interactive demo of confidence intervals by Kristoffer Magnusson rpsychologist.com/d3/ci/

Paper on statistical power necessary for interaction effects doi.org/10.1177/2515...

Thanks, Wendy! It's true! #openaccess doesn't have to mean that the author pays fees. We index journals that charge APCS (article processing charges) and/or any other fees. The 14107 journals we index don't charge any fees at all! So no hidden charges! Take a look: doaj.org/u/idD0kN

The stupidity, the criminal vandalism, the wanton destruction of information involved in dichotomisation statmodeling.stat.columbia.edu/2026/02/14/t...

A great read, including damning examples of how @thelancet.com refuses to clean up the scientific literature when they publish papers that are easily shown to be invalid.

This chapter on multicollinearity is a zinger, especially the central point in Section 23.4. If your focus is on model *predictions*, multicollinearity isn't necessarily a problem, and it might even be good. Well posted, @chrisadamsecon.bsky.social!

I wrote a blog for the Meta-Research Center expressing my infinite frustration about not getting data. What else is new, you might think? Well, I added an extra layer of annoyance directed at the journals who do NOTHING to enforce promised data sharing. metaresearch.nl/blog/2026/2/...

I switched from Spotify to Qobuz some time ago, mostly for ethical reasons (pays artists better, etc). But the improvement in sound quality is really obvious when using a decent listening rig. And the curated playlists and magazine articles are really nice, especially on an iPad or similar.

That‘s the spirit.

Unexpected to see the Cochrane Risk of Bias tool v2 (2019) more or less asking for tests of baseline differences in RCTs when this is generally considered bad practice, for instance by the CONSORT guidelines.