Magnus Johansson
banner
pgmj.bsky.social
Magnus Johansson
@pgmj.bsky.social

PhD & lic. psychologist. Research specialist at Karolinska Institutet. R package for Rasch psychometrics: pgmj.github.io/easyRasch/
#openscience, #prevention, #psychometrics, #rstats, #photo

Psychology 41%
Sociology 12%
Pinned
My simulation study on item misfit detection in Rasch models is published. We should leave rule-of-thumb critical values for GOF metrics behind us and use simulation/bootstrap methods to determine cutoffs appropriate for the data and items being analyzed. pgmj.github.io/rasch_itemfit/ #psychometrics
Detecting item misfit in Rasch models
pgmj.github.io

I like them, but in this format (from smped.github.io/SimpleUpset/... )
After 5 years of data collection, our WARN-D machine learning competition to forecast depression onset is now LIVE! We hope many of you will participate—we have incredibly rich data.

If you share a single thing of my lab this year, please make it this competition.

eiko-fried.com/warn-d-machi...
WARN-D machine learning competition is live » Eiko Fried
If you share one single thing of our team in 2026—on social media or per email with your colleagues—please let it be this machine learning competition. It was half a decade of work to get here, especi...
eiko-fried.com
My poster got allocated prime real estate at the conference: High traffic, captive audience.

You are welcome! Glad to contribute something back. I've enjoyed reading many of your posts :)

Reposted by Magnus Johansson

The 1.3.0 version of my {brms} + {tidyverse} translation of Kruschke's "Doing Bayesian data analysis" is up!

solomon.quarto.pub/dbda2

#rstats

1/8
Doing Bayesian Data Analysis in brms and the tidyverse
solomon.quarto.pub

That is also recommended in this paper:

Balzer, L. B., & Westling, T. (2023). Invited Commentary: Demystifying Statistical Inference When Using Machine Learning in Causal Research. American Journal of Epidemiology, 192(9), 1545–1549. doi.org/10.1093/aje/...
Invited Commentary: Demystifying Statistical Inference When Using Machine Learning in Causal Research
Abstract. In this issue, Naimi et al. (Am J Epidemiol. 2023;192(9):1536–1544) discuss a critical topic in public health and beyond: obtaining valid statist
doi.org

Having to intermittently save backup copies (since MS OneDrive can't be trusted either) seems like something one should not have to do these days.

I'm writing a report with a deadline two days from now and Word keeps crashing 2-3 times a day. While the document is lengthy and has a lot of figures, it is just astounding that Microsoft haven't been able to make this program more stable after 40+ years of development.
"40 percent of MRI signals do not correspond to actual brain activity"; "Since tens of thousands of fMRI studies worldwide are based on this assumption, our results could lead to opposite interpretations in many of them.”
www.tum.de/en/news-and-...
40 percent of MRI signals misinterpreted
Interpretation of numerous MRI data may be incorrect: blood flow is not a reliable indicator of brain activity.
www.tum.de

Maybe, maybe not. bsky.app/profile/drda...
Yikes!
“Increased oxygen consumption – for instance in areas involved in calculation – did not coincide with the expected rise in blood flow. …analyses showed that these regions met their additional energy demand by extracting more oxygen from the unchanged blood supply.”

www.tum.de/en/news-and-...
40 percent of MRI signals misinterpreted
Interpretation of numerous MRI data may be incorrect: blood flow is not a reliable indicator of brain activity.
www.tum.de
Yikes!
“Increased oxygen consumption – for instance in areas involved in calculation – did not coincide with the expected rise in blood flow. …analyses showed that these regions met their additional energy demand by extracting more oxygen from the unchanged blood supply.”

www.tum.de/en/news-and-...
40 percent of MRI signals misinterpreted
Interpretation of numerous MRI data may be incorrect: blood flow is not a reliable indicator of brain activity.
www.tum.de

I'd ask the same question about any VAS rating scale.

Sounds like a proper winter. Here it only rains and +2-7 C temp. Dark and dreary :(

Linking to the actual research paper in the article would be helpful.

Reposted by Magnus Johansson

Another day, and another reference to these bangers. Contemporary causal inference has fundamentally changed the way I think about control variables and mediation analyses. These can show you why:

doi.org/10.1177/2515...
doi.org/10.1111/spc3...
doi.org/10.1177/2515...
Sage Journals: Discover world-class research
Subscription and open access journals from Sage, the world's leading independent academic publisher.
doi.org
Keeping this at hand in case I need to point to it and tap

Just realized I have an old gdrive folder with similar content, if it could be of interest: drive.google.com/drive/mobile...
Funktionell kontextualism - Google Drive
drive.google.com

Nice. This is also a great read: www.scribd.com/doc/29106580...
Gifford and Hayes - Functional Contextualism 1999 | PDF
Gifford and Hayes - Functional Contextualism 1999
www.scribd.com

Today’s example of “self reported behaviour is a poor proxy of behaviour”: environmental behaviour
Also, "research involving self-reports often leads to fundamentally different results than research focusing on actual behavior in incentivized settings"

2/3

Thanks, lots of interesting things discussed! Curious about why a zero-inflated or hurdle negbin was not used? ”We employ negative binomial regression models, which are well-suited to the outcome variable’s distribution — right-skewed with a large concentration of zero values.”

Lägger till ett tips om ett spel som går utmärkt att köpa, och har en ovanlig mix av samarbete och tävling: www.webhallen.com/se/product/2...
Terraforming Mars (Eng) - Brädspel | Webhallen
www.webhallen.com

You just need to install the `geomtextpath` package. Here is an intro vignette: allancameron.github.io/geomtextpath...
Introduction to geomtextpath
geomtextpath
allancameron.github.io
geomtextpath can really help make a plot easier to interpret. Nice to avoid using a legend. #rstats #dataviz

Och återinföra arvsskatt när en rimligt hög nivå överstigs, vilket rent ideologiskt även borde gå i linje med liberala tankegångar.

Fifteen Years

xkcd.com/3172/

Link to blog does not work.
Meta halted internal research that purportedly showed (young) people who stopped using Facebook became less depressed and anxious, according to an unredacted legal filing released on Friday. www.cnbc.com/2025/11/23/m...
Meta halted internal research suggesting social media harm, court filing alleges
Meta is alleged to have halted internal research suggesting social media harm, according to court documents.
www.cnbc.com

Here is another paper on that topic that has some nice examples: www.tandfonline.com/doi/abs/10.1...