iiinova — where your digital self keeps evolving

yeah, I given up on commenting on these small details at this points lol

010

I guess they meant "asymmetrical" instead of "a symmetrical"

Xu, T., & Wang, H. (2024). The effectiveness of artificial intelligence on English language learning achievement. System, 125, 103428. doi.org/10.1016/j.sy...

doi.org

Redirecting

100

And another one: > As Fig. 2 indicates, the funnel plot had a symmetrical distribution, indicating no publication bias in this meta-analysis. Besides, the results of the classic fail-safe N ... reveals that 6619 missing studies would be needed to nullify the effect size ...

Beth Clarke @bethclarke.bsky.social · 21/08/2026

Another meta-analyses on AI in education. > Fig. 2 provides a visual representation of the distribution of effect sizes, indicating that the effect sizes are nearly symmetrically distributed... This distribution suggests that there is no evidence of publication bias present...

121

Reposted by František Bartoš

I’m hiring a PhD student to work with me on metascience in psychology at @zpid.bsky.social! The position is very open - could cover a wide range of topics/themes 🤸🏻‍♀️✨ If you have questions, please reach out! Applications are open until October 1st. leibniz-psychology.onlyfy.jobs/en/job/fyjwt...

leibniz-psychology.onlyfy.jobs

PhD in Psychological Meta-Science (m/f/d)

Become part of the open science movement The Leibniz Institute for Psychology Information (ZPID) in Trier (Germany) is an internationally recognized research-based psychology service center located in...

36157

František Bartoš @fbartos.bsky.social · 11/08/2026

My supervisor vibecoded a nice visualization for the same-side bias in coin flips effect:

bayesianspectacles.org

Coin precession simulation with same-side fraction

021

František Bartoš @fbartos.bsky.social · 05/08/2026

For the revision for our "Meta-Analysis with JASP, Part I: Classical Approaches" tutorial, I recorder a series of YouTube videos walking through the examples in JASP www.youtube.com/watch?v=mbou... First time doing this. Do you find walkthroughs like this useful? Let me know any suggestions!

youtube.com

Meta-Analysis with JASP, Part I: Classical Approaches (Example 1)

YouTube video by JASP Statistics

095

František Bartoš @fbartos.bsky.social · 21/07/2026

Join the JASP workshops at the last week of August!

000

František Bartoš @fbartos.bsky.social · 18/07/2026

- Good Scientific Practices for Sim. Studies - Toward Reporting Standards for Methodological Research - Transparency Over the Life-Cycle of a Sim. Study - Multi-Method Specification Curves for Presenting Sim. Results - Living Synthetic Benchmarks: A Neutral and Cumulative Framework for Sim. Studies

020

František Bartoš @fbartos.bsky.social · 18/07/2026

Come to our #IMPS2026 symposium on methodology of simulation studies with Richard Feinberg, @karolinehuth.bsky.social , Mirka Henninger, and David Kronthaler on Tuesdat at 12:45 to room 102. The symposium has the following talks:

151

František Bartoš @fbartos.bsky.social · 11/07/2026

New features: - Classical Generalized (GLMM) Meta-Analysis - Effect Size Aggregation - separate Forest Plot builder - Risk of Bias Plot - variable exports for derived fit information in classical analyses (i.e., residuals, predicted values, weights...) - several small updates ...

090

František Bartoš @fbartos.bsky.social · 11/07/2026

@jaspstats.bsky.social released a new of the Meta-Analysis module -- if you have the latest version of JASP you should see a small blue download icon next to the Meta-Analysis module on the ribbon. You can update it via the Module Store (see screenshot below).

1100

František Bartoš @fbartos.bsky.social · 02/07/2026

I was presenting a poster at ISBA overviewing the RoBMA R package for Bayesian meta-analysis. Check it below to see a brief summary of the latest changes with the new 4.0 version and the future directions!

170

Reposted by František Bartoš

Wolfgang Viechtbauer @wviechtb.bsky.social · 22/06/2026

The standard random-effects model in meta-analysis assumes that the amount of heterogeneity is homoscedastic. This assumption may not be true. I derived and examined various tests for heteroscedastic heterogeneity. See osf.io/cavhy for a preprint describing these methods. #MetaAnalysis #RStats

osf.io

OSF

13112

František Bartoš @fbartos.bsky.social · 18/06/2026

doi.org/10.1016/j.co... doi.org/10.3389/fpsy... doi.org/10.1057/s415...

000

František Bartoš @fbartos.bsky.social · 18/06/2026

Out of curiosity I checked a the first author's google scholar. He seemed to have co-authored additional three meta-analyses last year. Two of those show quite unbelievable effect sizes again. (I guess the d = 2.5 is fine when the rest contains d around 4)

František Bartoš @fbartos.bsky.social · 18/06/2026

Currenly revising our critique of meta-analyses of AI/LLM on learning. Some of the original meta-analyses are beyond ridicolous. This one has 87 citations since published in 2025. (doi.org/10.1177/0266...)

150

František Bartoš @fbartos.bsky.social · 03/06/2026

We still have a couple of spots left for JASP workshops August! 24: Discovering Statistics using JASP 25: State-of-the-Art Meta-Analysis using JASP 26: A Crash Course in Machine Learning with JASP 27-28: Theory and Practice of Bayesian Hypothesis Testing with JASP jasp-stats.org/workshops/

jasp-stats.org

Workshops - JASP - Free and User-Friendly Statistical Software

The JASP team is excited to support four workshops this year (2026). Each of these workshops can be attended either in person (at the University of Amsterdam) or online: On Monday August 24th, we orga...

071

František Bartoš @fbartos.bsky.social · 02/06/2026

Check out the great program of the *1st Interdisciplinary Symposium on Meta Science for Methods Research* organized 31 August and 1 September in Zürich! Ton of cool speakers and meta-methodological reseach! crsuzh.pages.uzh.ch/msmr/program/ (registration still open)

crsuzh.pages.uzh.ch

index – MSMR 2026

02013

František Bartoš @fbartos.bsky.social · 16/05/2026

I am not sure I will write a preprint about this in particular, but I will post about the new package version!

010

František Bartoš @fbartos.bsky.social · 15/05/2026

Possibly within 2 months with all remaining metafor style 'random' argument functionality

100

The implementation is available in both RoBMA R package (via the `cluster` argument) and in @jaspstats.bsky.social !

010

Interestingly, we find that in a presence of a correlation between cluster size and effect size (as we observed in our second example), most existing methods become severely biased; multilevel RoBMA was the only method to consistently recover the true effect across all simulated conditions.

120

We illustrate the method on two re-analyses (see vignettes: cran.r-project.org/web/packages... and cran.r-project.org/web/packages...) and two simulation studies.

100

Accounting for the multilevel structure in publication bias adjustment is necessary for drawing valid inferences since majority of meta-analyses include multiple effect sizes per study. Ignoring this dependency results in overly narrow intervals and inflated evidence.

This extension fully connects with other features available in RoBMA, e.g., meta-regression, estimated marginal means, etc, making it directly applicable to the usual meta-analytic workflows.

120

František Bartoš @fbartos.bsky.social · 12/05/2026

The multilevel extension to RoBMA was just published in BRM (link.springer.com/article/10.3...). Together with @maxmaier.bsky.social and EJ Wagenmakers, we developed a 3-level version of RoBMA which allows analysts to adjust for publication bias in meta-analyses with estimates nested within studies.

3163

It is, unfortunatelly, not the only poorly conducted meta-analysis on the effect of LLMs on learning in the literature. We have also examined 67 meta-analyses with 1,840 effect sizes showing the same patern across the literature. osf.io/preprints/ps...

osf.io

OSF

040

František Bartoš @fbartos.bsky.social · 12/05/2026

I just found out that a meta-analysis on the effect of ChatGPT on learning that we criticized last year not adjusting for publication bias and overinterpreting the conclussions (osf.io/preprints/ps...) was retracted last month (see notice www.nature.com/articles/s41...)!

182

I have several new upgrades in mind like - flexible random effects structures - coefficient hypothesis tests - multiple inputation in plans!

000

These update unfortunatelly break backwards compatibility and the syntax no longer matches the previously published tutorials. Fully updated vignettes showcasing how to match the previous versions of the package are on the github pages at: fbartos.github.io/RoBMA/index....

Robust Bayesian Meta-Analyses

A framework for Bayesian meta-analysis, including model estimation, prior specification, model comparison, prediction, summaries, visualizations, and diagnostics. The package fits single and model-ave...

100

More flexible publication bias adjustment. The new prior_weightfunction() allows setting custom priors on the selection models (fbartos.github.io/RoBMA/articl...)

Publication-Bias Adjustment

100

All fitting functions (RoBMA, BMA, BMA.glmm, brma, brma.glmm, bselmodel, bPET, bPEESE) recieve following arguments: - `mods` specify moderation (meta-regression) - `scale` specify scale-models - `cluster` allows effects nested within studies (`random` like in rma.mv arrives later)

100

New default prior distributions: the `measure` argument allows specifying default priors based on unit information standard deviation (UISD). For general (nonstandardized effect size measures), those can be estimated from samples sizes and ses directly (fbartos.github.io/RoBMA/articl...)

Prior Distributions

A major release of the RoBMA package (4.0.0) is now on CRAN. Main highlights: - fully redesigned interface closely matching metafor - dedicated brma, bselmodel, bPET, bPEESE for single model fits - fit diagnostics features (residuals, influence, etc) (overview at fbartos.github.io/RoBMA/articl...)

František Bartoš @fbartos.bsky.social · 07/05/2026

Feature Coverage

174

What makes it even more efficient is combining this trick with inverse weighted marginal density estimator (IWMDE). In out settings IWMDE becomes trivial to implement and improves the density estimation tremendously so only a couple thousands posterior samples are needed.

František Bartoš @fbartos.bsky.social · 07/05/2026

In our new preprint we show how to efficiently compute Bayes factor sensitivity analyses for any model comparison. The computation trick is simple -- it rellies on extend the model by a hyper-prior on the parameter(s) for which sensitivity is desired and using transitivity of Bayes factors.

140

Reposted by František Bartoš

Victor Shiramizu @victorshiramizu.bsky.social · 19/03/2026

Our paper is now out in Hormones and Behaviour. We found little evidence for group differences in 2D:4D ratios by sexual orientation when jointly modeling publication bias and heterogeneity. w/ @fbartos.bsky.social, Ben Jones & @tvpollet.bsky.social www.sciencedirect.com/science/arti... 🧵1/9

sciencedirect.com

Little evidence for group differences in 2D:4D ratios based on sexual orientation after adjusting for publication bias

The ratio between the lengths of the second and fourth digits (2D:4D) has been proposed as a putative marker of prenatal androgen exposure and investi…

185

Reposted by František Bartoš

Daniel Lakens @lakens.bsky.social · 10/02/2026

Everything is ready for the Perspectives on Scientific Error conference that starts tomorrow in Leiden! I look forward to hanging out with the mix of metascientists, philosophers of science, and statisticians! So many old friends will be there (and hopefully some new ones)! #PSE8

0509

František Bartoš @fbartos.bsky.social · 06/02/2026

Come to Amsterdam or join online for the full week of JASP workshops (24th-28th of August)! If you can't do the full week or you are only interested in meta-analysis, I will be giving the Meta-Analysis workshop on 25th of August. jasp-stats.org/2026/02/05/h...

040

Reposted by František Bartoš

Björn Siepe @bsiepe.bsky.social · 04/02/2026

Does it make sense to preregister simulation studies? This question has sparked a lot of debate. ▶️We* work through the why, when, and how ▶️We discuss different phases of methodological research to clarify where preregistration might (or might not) add value 📝 Preprint: doi.org/10.31234/osf...

Diagram showing four phases of methodological research (Theory, Exploration, Systematic Comparison, Evidence Synthesis) with an arrow indicating that preregistration usefulness increases from early to late phases. Each phase lists its aim, elements, outcome, and an example from factor retention research.

13713

František Bartoš @fbartos.bsky.social · 28/01/2026

Does it mean that AI/LLMs do not help at education? I personally don't think so. I'm using the AI every day and find it incredibly useful. It would be odd if they didn't help at learning at all. However, the current empirical base does not substantiate strong claims.

011

František Bartoš @fbartos.bsky.social · 28/01/2026

Meta-analysis level re-analysis then further highlights the issue of publication bias. Extremely overstated evidence (left) and mean effect size estimates (middle) due to a large degree of publication bias (right).