Trust was not among the things for which I got into science. Trust no one.

I should probably explain this, with context. Over several years we have caught MANY researchers playing silly buggers with artificial cutoffs designed to engineer group differences. (No one more so than the Vitamin D weirdos. One of the least reliable and most annoying areas of health research.)

@bmj.com has issued an expression of concern for a paper claiming stem cell therapy can reduce the risk of heart failure. The move comes after sleuths and scientists critiqued the “complete mismatch” between the study data and the article itself.

Hey alcohol research folks, is anyone still looking for symposium speakers for RSA? I have some EMA data on rural young adults that I’d love to present but I don’t think I have bandwidth to also organize. Hit me up if you want to hear more!

Well now I'm pondering - what is the best Introductory Biostats book out there that folk have had success with. I used to like Whitlock & Schluter, but have come to find it too test-based and not enough thinking-based (to use a term of art?).

Two-group pre/post data are deceptively simple, and you could analyze them in many different ways, depending on your goals. Here are three blog posts on the topic: solomonkurz.netlify.app/blog/2022-06... solomonkurz.netlify.app/blog/2020-12... solomonkurz.netlify.app/blog/2023-06...

Peer reviewers-I’m curious, why do you track your reviews with web of science?

This one surely has something on offer for every one: In this cross-sectional mediation analysis, the "effects" of soft drink consumption on depression were "mediated" by abundance of Eggerthela in the gut microbiome. This was sent to me via dm and now you all got to suffer as well.

Agreed. I'd go further and say if you see language like this in a paper, it's a huge red flag the research team has a poor grasp on statistics.

This is related to a private conversation I had recently. IMO, if you want to use Bayesian statistics in your professional work, either (a) work through at least one Bayesian textbook yourself or (b) collaborate with someone who has already done that work themselves. Take your data seriously.

Which version of the faceted plot do you prefer: A or B? #rstats

We have at least TWO postdoctoral fellowship openings on our @unm.edu @casaa.bsky.social T32 NIAAA Training Grant, best consideration date for applications is Nov 15 2025. Join our phenomenal community and enjoy incredible quality of life in beautiful New Mexico. casaa.unm.edu/training/ins...

Re-upping since we're just over a week away from the deadline to apply to the TT asst prof position in our clinical area at Vanderbilt! Please consider applying if you're on the job market! RTs appreciated.

"Open Science needs reliable infrastructure"

I strongly recommend @hugoreasoning.bsky.social's book "Not Born Yesterday" if you've been exposed to too much social psychology about irrationality in your youth. press.princeton.edu/books/hardco...

It's starting to look really bad for this RCT. Do scroll through the PubPeer comments. They're striking. On the other hand, this is a big win for open science and post-publication peer review.

This, by @vincentab.bsky.social, is the most straight-up *useful* book I’ve bought in a long while.

I’ve finally had time to write another blog post after a couple of busy months. It’s a tutorial on how to create UpSet plots using only tidyverse packages (and patchwork) in #rstats https://www.gl-eb.me/blog/posts/2025-11-02_upset/ #dataviz #ggplot2

New effect size just dropped: The PVPP

Relatedly, I think SESOI is a tremendously useful and under-appreciated concept. It's become a regular tool in my power analysis workflows, and I wish I understood it sooner in my career.

Great points about the clarity the SESOI brings in this context

Hey #stats and #rstats people - is there a name for this type of plot? (If not, can we come up with one??) I use to to visualize ICC in multilevel designs (x axis are the random groups, sorted by their mean outcome level).

New release of PowerLMM.js! Browser-based power analysis for longitudinal models with dropout. Now includes: - Power analysis summary report - Reproducible & shareable configs (URL/JSON) - Calculations validated against R - Hypothesis region visualization powerlmmjs.rpsychologist.com

We wrote an article explaining why you shouldn't put several variables into a regression model and report which are statistically significant - even as exploratory research. bmjmedicine.bmj.com/content/4/1/.... How did we do?

My own TLDR for the message from this paper: statsepi.substack.com/p/sorry-what...

Latent group analyses are the singing sirens of applied statistics

What is it like to be a grad student now that AI is a thing? Are we seeing more slop? Are people switching from SaS/STATA to python/R because the learning curve is much less steep with AI?

I am hiring PhD candidates to study the psychology of attention & technology use at @tilburg-university.bsky.social. We're looking for motivated & curious scholars with expertise in cognitive psychology and statistics, and offer a friendly work environment with great terms & benefits. tiu.nu/22989

I’m beginning to suspect that many academics and pundits don’t realize demography is a distinct discipline. As in, it has its own methods, theories, and actual training programs. You can’t just call yourself a demographer because you find demographic topics interesting and are good at math.

1/n I'm considering writing a paper with many authors & wanted to ask for feedback from people who have experience (e.g., manylabs). Assume a core team of 25 authors, and then 500 people who participate in a delphi study who I want to give authorship specifically for the participation in delphi

The recording is now available so that you can confirm that I indeed have a German accent and color-match my outfits with my Zoom background. youtu.be/YL0co26ng-g?...

Just posting because everyone needs to see a walking moai. 😝

Does anyone know a workaround for modeling residual correlations in multivariate models in {brms}? It only works for Gaussian and Student distributions right now, but maybe someone has a hack… #RStats (Maybe @solomonkurz.bsky.social?)

Any Italian speakers who might have a little time to proofread some llm-generated pkgdown translations? github.com/r-lib/pkgdow...

PSA: seems like the update broke the ability to directly download files with a link, like osf.io/XXXX/download this lead to an error in one of my R package vignettes, and presumably will break lots of code.

Would any fluent speakers of Korean or Chinese have a couple of minutes to review some updated pkgdown translations at github.com/r-lib/pkgdow... ? These were generated by claude code, so they're probably ok, but I'd love a human to double check.

Results of the replication are in! Chocolate is more desirable than poop: Cohen's d_rm = 6.20, 95%CI [5.63, 6.78] N = 486, two single item 1-7 Likert scales of desirability. w/ @jamiecummins.bsky.social

Duke University is holding virtual office hours for students to get feedback on their psychology PhD applications! Due October 31st! docs.google.com/forms/d/e/1F...

"Dunbar's Number" is a zombie that lives forever in the science press it seems. Estimates of Dunbar's Number with 95% intervals, for a range of model specifications (from doi.org/10.1098/rsbl... ):

Against Publishing: universonline.nl/nieuws/2025/... Preprints are read, shared, and cited, yet still dismissed as incomplete until blessed by a publisher. I argue that the true measure of scholarship lies in open exchange, not in the industry’s gatekeeping of what counts as published.

Replication science isn't always fun, but this one is. Help a guy out:

it does kinda suck that every pre-4.0.0 ggplot2 plot that set theme(base_size) will look different now

My blog has moved! It’s now at sometimesimwrongblog.wordpress.com If you have links to posts in your syllabus, let me know if you have any trouble finding the corresponding post!

In Ch 19 (nyu-cdsc.github.io/learningr/as...) of his 2nd edition, Kruschke used *residual* SD as a standardizer for group differences from a multilevel ANCOVA. Is there any precedent for using a *residual* SD as a standardizer for a standardized mean difference effect size? #RStats

Happy to announce that I'll give a talk on how we can make rigorous causal inference more mainstream 📈 You can sign up for the Zoom link here: tinyurl.com/CIIG-JuliaRo...

My article "Data is not available upon request" was published in Meta-Psychology. Very happy to see this out! open.lnu.se/index.php/me...

If you've ever wanted to learn how to make beautiful websites with #QuartoPub and #rstats , check out this workshop I'm giving in a couple weeks! It'll be a blast (and we're covering Quarto's brand new _brand dot yaml system!)

Despite heroic efforts by a small cadre of people in the field, the vast majority of senior PIs in clinical psychology continue to be uninterested or hostile to OS practices. It makes me think they just don't care, and it's really depressing.