Anne Scheel

ZPID Trier: Junior professorship (W1-equivalent) Psychological Metascience (with tenure-track to W2 LBesG-equivalent) (f/m/d) leibniz-psychology.onlyfy.jobs/job/10kku5n7 #Stellenangebot

If you’re into beautiful graphs and rigorous science, check out Ruben’s new position at Uni Witten/Herdecke. I’ve worked with him for over a decade, and it’s been an inspiring, supportive collaboration throughout.

I moved all my student Slack workspaces to Discord earlier this year bc of stricter limits on free plans, and most other random Slacks I'm in have also made the switch

All that to say that I just learned you can put servers in folders by dragging them on top of each other in the sidebar à la iOS

Metacheck can now automatically 1) download a preprint from PsyArXiv, 2) create a report of the checks (stats, reporting guidelines, references, code, etc), 3) retrieve the authors email, and 4) send them the report.

Would you as an author appreciate this? When yes, when no?

I thought it was obvious that I’m using “p-values” as shorthand for “significance test”. If you want to do the test with CIs or p-values (plus alpha, _obviously_), I don’t really care.

‘A fragmented field: Construct and measure proliferation in psychology.’ (2025)

From ‘Language models accurately infer correlations between psychological items and scales from text alone.’ (2025)

From ‘Not within spitting distance: salivary immunoassays of estradiol have subpar validity for predicting cycle phase.’ (2023)

Work in progress with cycle tracking data from the app Clue

Want to make nice graphs with me, starting next year? I'm hiring for a position at the University of Witten/Herdecke.
uni-wh.softgarden.io/job/61280592...

Fig. 3. Effects of the intervention. In (a) are shown effects 7 months after the intervention; in (b) are shown interaction effects 7 months after the intervention. Models show the effects of the intervention on expressive-language skills in the grade 1 posttest, with an interaction between expressive-language skills in the pretest and after the intervention. Standardized coefficients (with 95% confidence intervals) are shown, except for the intervention dummy variable and the interaction where y-standardized values are indicated. Rectangles and circles contain observed variables and latent variables, respectively. Solid arrows point to significant regression or factor loadings (arrows from latent variables to their observed indicators); the arrow with dotted lines shows nonsignificant regression. The interaction (Fig. 3b) is illustrated by the arrow from the black circle to expressive language in the posttest. **p < .01.

Fig. 4. Long-term effects of the intervention on expressive-language skills. Model showing the effect of the intervention on expressive-language skills in the grade 4 posttest. Standardized coefficients (with 95% CIs) are shown, except for the intervention dummy variable where y-standardized values (equal to Cohen’s d) are indicated. Rectangles and circles contain observed variables and latent variables, respectively. Solid arrows point to significant regression or factor loadings (arrows from latent variables to their observed indicators); arrows with dotted lines show nonsignificant regression. **p < .01.

Fadeout of cognitive training remains one of the more replicable
findings in psychology in this preregistered study of 300 preschool children. Well-done study with a 4 year follow up. The language gains either faded or the control group caught up.
journals.sagepub.com/doi/full/10....

100% agree. I feel like these types of projects might be our only hope for getting actually reusable open data. And it’s a great incentive for authors!

Projects like this & applying integrative analysis methods are very exciting. I bet there's more to do with all the data we collect & curation and good use of metadata is currently underappreciated

P-values and power are relevant when you want to test a claim. Effect sizes and measures of precision are relevant when you want to estimate an effect. Large N are better for both.
Of course p-values don’t tell you the effect size. If you want to estimate, you should estimate, regardless of N.

In the running for greatest human accomplishment.

Incredible. I might never refer to you as Malte again

I think you just discovered a meme

Significantly more devastating when I ask it. Ouch.

Perfect time to join the PYMS Discord if you haven’t already! We have a Meme Channel now!

Holy shit, congratulations Eiko!!

We just preprinted a huge meta-meta-analysis examining the effects of exercise on cognition, memory, and executive function

In short
- 2239 effect sizes
- extreme between-study heterogeneity
- extensive publication bias
- some subgroup/exercise-specific effects

More below (doi.org/10.31234/osf...)

I think that the field needs to clean up the published literature a bit. Additional small studies are not going to move the needle at this point; maybe a couple of large-scale, pre-registered studies might provide more insight?

Choropleth map of property sales prices in Germany

I had a lot of fun making this choropleth map of property sales prices in Germany.

Predictably, big cities have the highest property prices. This pattern is typical now.

I had the same intuition!

IMO one of the absolute coolest projects in psych at the moment — solving the toothbrush problem in measurement with really clever use of LLMs. Incredibly useful!

Non-representative samples! What could possibly go wrong? Earlier this year I saw that a study was making the rounds on Twitter under the catchphrase “Representative samples may be overrated.” Claims like this tend to spread like wildfire in certain parts of...

@dingdingpeng.the100.ci taught me that causal inference is inescapable even for description: www.the100.ci/2023/03/07/n...

I maintain that once somebody published a study, anybody can criticize it publicly, & there is no *obligation* to wait for the original authors' (OA) to reply.

1st, why would the OAs get to have the last word at every step?
2nd, waiting opens up a loophole for the OAs to derail the process.

IMO one of the absolute coolest projects in psych at the moment — solving the toothbrush problem in measurement with really clever use of LLMs. Incredibly useful!

🚨 SynthNet is out 🚨
Researchers propose new constructs and measures faster than anyone can track. We (@anniria.bsky.social @ruben.the100.ci) built a search engine to check what already exists and help identify redundancies; indexing 74,000 scales from ~31,500 instruments in APA PsycTests. 🧵1/3

The scandal of medical research still failing to adopt the Registered Report format for trial publications.

Great example of failure to weed out Questionable Research Practices by clinical trial register (preregistration)+ journal review + multiple systematic reviews + guideline development process

The history of vaccines

Imagine you lived in the 18th century.

Smallpox kills 1 in 3 cases. Yet you can’t culture pathogens, don’t know germ theory, and have no idea what a virus is. How would you invent a vaccine?

In a new episode of HARD DRUGS, we trace the history of vaccines!

“The articles in AMPPS offer, month in and month out, the invitation to practice aligning your values, intentions, and actions to do less scientific harm and reach for the methodological ceiling”

Grateful to @dsbarra.bsky.social for continuing what @profsimons.bsky.social & co started at AMPPS!

Has anyone tried the trackdown package for collaborative quarto editing? Love writing papers on Quarto, but switching back to Word for co-author edits is still an awkward missing link claudiozandonella.github.io/trackdown/

New workshop announced: Quarto: Write, Code, Reproduce | Paul Meehl Graduate School We are thrilled to announce that registration is now open for our new workshop. In this workshop, Ambra Perugini will...

Registration is now open for our Quarto workshop at Paul Meehl Graduate School!
Join us on December 12 in Eindhoven to learn how to use Quarto for reproducible research and communication.

More details and registration here:
paulmeehlschool.github.io/2025-11-03-q...