Just gave my last talk of the year!
2025 was quite packed, I gave talks about:
- the age-period-cohort problem
- making rigorous causal inference more mainstream
- mediation analysis
- marginaleffects
- causal graphs (x10)
If you're curious, check out my slides here: juliarohrer.com/resources/
What your audience is thinking about at your conference presentation. Cartoon from @upmicblog. #PhDchat #ECRchat #postdoc #gradschool
@nature.com made a news piece on our new @pnas.org paper. Good job Anne Ravndal!
Menβs brains shrink faster than womenβs: what that means for Alzheimerβs.
www.nature.com/articles/d41...
#DataMethods #OpenScience
#GESISMethodsHub: An open portal for computational social science researchβfind tools, tutorials, and code, directly usable in your browser. Methods Hub makes it easy to learn, apply, and reproduce computational methods in the Social Sciences.
methodshub.gesis.org/
Brilliant design! Makes me want to have a new website as well!
Psychological Methods is looking for Editorial Fellows. We are looking forward to applications of early-career psychologists who will bring experiential diversity to their work. If you are interested, reach out to me or directly apply here to work with a wonderful team: www.apa.org/pubs/journal...
Anke Schneider and I put together a short brochure on sample size planning, aimed at Bachelor psychology students. Our goal: help students justify their sample size plan (other than just relying on defaults) and help avoid common pitfalls. π
For now, itβs only available in German.
osf.io/n46vg/
Also see the press release, which may have contributed to this by their opener "A university degree is linked to a heightened risk of developing a brain tumour":
medicalxpress.com/news/2016-06...
Not exactly 'low quality,' but a brilliant example of how correlational findings can start to take on a life of their own. The paper title is "Socioeconomic position and the risk of brain tumour" but see the Mirror's headline. Original paper: jech.bmj.com/content/70/1...
What is their recommendation to use instead?
A new preregistration template for simulation studies is now live on OSF. Thanks to the creators and the preregistration template working group for proposing and shepherding this to make it available to users.
See the post if you would like to propose a new template.
www.cos.io/blog/introdu...
New preprint: Stop thinking of Cohen's d as an effect size.
Cohen's d confounds magnitude of effect and reliability. Yet, we pretend our measurements are flawless when interpreting it. What if we thought of Cohenβs d as a measure of detectability instead?
osf.io/preprints/ps...
New study out in Nature Medicine: Education does not protect against age-related decline of memory. Read more here: Reevaluating the role of education on cognitive decline and brain aging in longitudinal cohorts across 33 Western countries www.nature.com/articles/s41...
The package supports R/quarto files with small hiccups. The next package release will hopefully fully support quarto.
In my latest (and last!) column for Scienceβs Expert Voices series, I write about the reasons behind AI chatbotsβ βdeceptiveβ behaviors (and why Claude threatened a fictional CEO with blackmail).
www.science.org/doi/10.1126/...
More info on the basics here: online.ucpress.edu/collabra/art...
And use cases in our vignettes, e.g.:
brandmaier.github.io/reproducible... -- click "Articles" to see more.
Want automated reproducibility checks for your R Markdown docs on GitHub?
reproducibleRchunks v1.2.0 is now on CRAN!
β
Generates GitHub Actions for cloud-based reproducibility checks (with cool badges)
π¦ Supports renv for dependency management
π cran.r-project.org/package=repr...
love when a paywall sounds like itβs drawing a gun on you
Finally: Ecologically valid MRI studies.
Seen at Max Planck Campus of Cognition #noai
Interested in the latest metascience? Come to Eindhoven October 17th to listen to Dr. Duygu Uygun-Tunç (University of Chicago) and Dr. Lisa Spitzer (Leibniz-Institut für Psychologie) as keynote speakers, and Dr. Aaron Peikert for a workshop collaboration through Git! All free!
The German Research Foundation @dfg.de publishes the English edition of their Funding Atlas!
gasps of awe!
Thrilled to see our TinyRNN paper in @nature! We show how tiny RNNs predict choices of individual subjects accurately while staying fully interpretable. This approach can transform how we model cognitive processes in both healthy and disordered decisions. doi.org/10.1038/s415...
CRAN release of reproducibleRchunks v1.1.0 - now with full support of all standard knitr code chunk options.
There are also some example vignettes to get you started: brandmaier.github.io/reproducible...
or just read our Open Access article in Collabra: Psychology: doi.org/10.1525/coll... #rstats
@anoukbouma.bsky.social makes wonderful remarks on how scientific software often misses users' need. Where is the: "Design, test, and iterate" cycle in scientific software?
Yes, yes, yes. And particularly thank you for quoting the essential βWriting is thinking. To write well is to think clearly. Thatβs why itβs so hard.β
A few months ago, Nature published how-to guide for using ChatGPT to write your peer reviews in 30 minutes.
This is, of course, a horrible idea. Hereβs my response with @jbakcoleman.bsky.social .
@markuswb.bsky.social @myriamsander.bsky.social @yeeleeshing.bsky.social
PCI Psychology is here!! ππ₯³
After over a year of hard work by so many people, we are thrilled to announce that we are open for submissions! Join us in making publishing more efficient, equitable, and open: psych.peercommunityin.org
#PsychSciSky #scipub
What? How? Why?
