Sign in

Matti Vuorre

@matti.vuorre.com
2.1K followers 578 following 1.4K posts

I am an assistant professor at Tilburg University's Department of Social Psychology. I have a website at vuorre.com. All posts are posts.

PostsRepliesMedia
Matti Vuorre @matti.vuorre.com · 10h
You can't post likelihood based memes on a Saturday afternoon and expect to go viral in this day and age
010
Reposted by Matti Vuorre
Kristina Šekrst @epiphenomenal.bsky.social · 02/10/2026
Middle-age crisis contd. #philosophy #consciousness #cogsci #consci
1142
Matti Vuorre @matti.vuorre.com · 14h
tej.as/blog/aleph-a... Time to start faxing in your prompts y'all.
tej.as
Aleph Alpha Kolibri: How the Sovereign German LLM Works
Kolibri is Aleph Alpha's open-weight German and English LLM: 78B parameters, 3.5B per token. How it works, what it's good and bad at, and when to use it.
010
Matti Vuorre @matti.vuorre.com · 14h
a most niche meme 💅
2111
Matti Vuorre @matti.vuorre.com · 15h
11910
Reposted by Matti Vuorre
JsonGeller @jgeller1phd.bsky.social · 02/10/2026
link.springer.com/article/10.3...
link.springer.com
A beta way: A tutorial on Bayesian beta regression for psychological research - Behavior Research Methods
Rates, percentages, and proportions are common outcomes in psychology and the social sciences. These outcomes are often analyzed using models that assume normality, but this practice overlooks importa...
1113
Matti Vuorre @matti.vuorre.com · 17h
This is also a good strategy with bigger data because the estimation speedup can be huge
000
Matti Vuorre @matti.vuorre.com · 18h
I think for now they should be safe but the future does indeed seem uncertain. Psyarxiv will survive!
010
Matti Vuorre @matti.vuorre.com · 02/10/2026
I'm not sure those bots run on the osf ( @malte.the100.ci ?), but rather get preprint updates from the osf api. That shouldn't be affected for now, but would certainly be easier to implement on openalex now.
100
Matti Vuorre @matti.vuorre.com · 02/10/2026
One could also use (e.g.) v1 as the pre-registration and v2 the write up--it would then be very easy to see what changed (vs. comparing documents across platforms).
010
Matti Vuorre @matti.vuorre.com · 02/10/2026
Right yes sorry, too many pre-s. You can probably get pretty far with pre-registrations on Zenodo but it is true they don't satisfy some of the stricter criteria (e.g. can't really look at all preregistrations etc.)
010
Matti Vuorre @matti.vuorre.com · 01/10/2026
This is very good; I usually just push back and add a "for readers unfamiliar with this, look at kruschke, rouder, mcelreath, gelman (bda)." 60% of the time, it works every time.
020
Matti Vuorre @matti.vuorre.com · 01/10/2026
Do you mean that you can't eg search zenodo for all preregistrations that haven't yet been realized etc? It may offer a bit more in this space but am not sure.
110
Matti Vuorre @matti.vuorre.com · 01/10/2026
Research box is actually pretty sweet. Sure the API/metadata can be lacking (and this may prove very important in the future) but it also just works and is simple. Zenodo imo seems to be a all in one solution, I don't fully get the point that preprints there aren't part of a formal registry.
110
Matti Vuorre @matti.vuorre.com · 01/10/2026
Good talk. There's a lot of (over)thinking of this at the moment. Zenodo just works. (Until it doesn't when we and our bots ruin that as well.) Collaborate on GitHub and refer to zenodo.
2359
Matti Vuorre @matti.vuorre.com · 01/10/2026
psych.peercommunityin.org
110
Matti Vuorre @matti.vuorre.com · 01/10/2026
I use linear.app/docs because it's incredibly fast & keyboard driven. You can get the paid version for free as academic but sadly not FOSS. You can also easily ignore all the ai stuff.
010
Matti Vuorre @matti.vuorre.com · 29/09/2026
I do like a good revolution, but here the thoughtful application of established methods seems a more fruitful approach.
161
Reposted by Matti Vuorre
jon ben-menachem @jbenmenachem.com · 29/09/2026
"Replication crisis" reforms like preregistration & pre-analysis plans were developed to control false positives in experimental research. Does that work in observational studies? Our new paper in Sociological Methods & Research argues for a different approach. 🧵 journals.sagepub.com/doi/10.1177/...
A Replication Framework for Observational Research: From Specification Restriction to Specification Expansion
Jonathan Ben-Menachem https://orcid.org/0000-0002-8092-0848 jbenmenachem@gmail.com, Ari Galper https://orcid.org/0000-0001-7909-8837, and Nic Fishman
Abstract
Sociology has remained relatively insulated from debates about the “replication crisis.” Heeding calls to consider replication more deeply, we introduce a distinction between two types of research reforms that have emerged in the wake of the crisis: specification-restricting and specification-expanding reforms. Specification restriction is often promoted as a way to increase the repeatability of research findings by controlling false positives. We argue that this statistical justification is less compelling in observational contexts—where the assumptions licensing false-positive control are harder to sustain and rigid ex ante analytical commitments can instead enshrine fragile specifications—than in experimental contexts. We further argue that apparently low replication rates do not necessarily imply a high prevalence of false positive findings. Instead, we propose a replication framework centered on specification-expanding reforms, stronger incentives for confirmatory research, and meta-analysis. This approach equips sociologists to assess the repeatability of findings and build a more cumulative discipline.
28129
Reposted by Matti Vuorre
Andrew Reid @reid-lab.org · 11/09/2026
www.reid-lab.org/blog/22 My (interactive) blog post focused on how #EEG #MEG signals are generated. Aimed at anyone interested in learning about these methods on a biophysical level. Let know what you think -- and share if you think it may interest your followers! #neuroscience #Neuroskyence
reid-lab.org
Learning about EEG (part 1) | Andrew's Blog
This is a teaching-oriented post about the fundamental concepts underlying electroencephalography (EEG), and to some extent magnetoencephalography (MEG). I explore how electromagnetic fields are gener...
22911
Matti Vuorre @matti.vuorre.com · 25/09/2026
🥳 I may have finally worked out a way to put a Seinfeld quote into a paper title. S05 The Hamptons.
130
Matti Vuorre @matti.vuorre.com · 23/09/2026
I liked this episode too. Even on this brief interview it's clear he's great at explaining things so I'm now reading his 1990 paper
111
Matti Vuorre @matti.vuorre.com · 23/09/2026
Super thread on science comms and how a study can 'evolve' over time. As she says "be careful with PRs"
030
Reposted by Matti Vuorre
moin syed @syeducation.bsky.social · 22/09/2026
New paper! Despite qualitative researchers claiming that generalizability is not a goal, their published work does indeed contain generalizable claims. We document this and provide recommendations for how all researchers can better calibrate their generalizability claims. doi.org/10.1177/2515...
article header for, "Qualitative Researchers Can and Do Generalize: Generalizability Claims in Qualitative Psychological Research". Metascience!
619258
Matti Vuorre @matti.vuorre.com · 22/09/2026
I happened to take a look at that paper and its quite frustrating. I wanted to do some analyses on the data they present but its not open (nor open in the cited papers). Is sharing not common in the field? Good luck with the comment!
110
Matti Vuorre @matti.vuorre.com · 21/09/2026
This is what concerns me too, but yeah maybe they are technical problems that a good model / prompt / etc can help with. I'll stick with Zotero though :)
010
Matti Vuorre @matti.vuorre.com · 21/09/2026
I have heard from a bunch of people that they use llms to - move bibliographies between files and software - copy & format citations between papers - write bibtex entries for references So basically using chatGPT as a supercharged copypaste that will sink your credibility when a mistake is caught.
150
Matti Vuorre @matti.vuorre.com · 21/09/2026
100% this, numbers and such easily convey a sense of false certainty
010
Matti Vuorre @matti.vuorre.com · 17/09/2026
Against "Against Method": Would Feyrabend preregister his hypotheses in 2026?
020
Matti Vuorre @matti.vuorre.com · 17/09/2026
Consistency between (or even within) these three papers not guaranteed. :)
130
Matti Vuorre @matti.vuorre.com · 17/09/2026
Papers I would like to explore: - Against SESOI: More arbitrary thresholds = More arbitrary science - Against value-driven science: open, team, or interdisciplinary science doesn't make your study more valid - Abandon "best practices" and explain your reasoning instead
3151
Matti Vuorre @matti.vuorre.com · 15/09/2026
Ohh... Lame. Even more reason to write a commentary!
020
Matti Vuorre @matti.vuorre.com · 15/09/2026
The same one?
100
Matti Vuorre @matti.vuorre.com · 15/09/2026
Methods dev can and sometimes should be field/application-specific. Why dont these methodologists then review for applied journals.
000
Reposted by Matti Vuorre
Bastian Jaeger @bxjaeger.bsky.social · 15/09/2026
1. We used a multidimensional cultural distance measure to quantify how culturally different the 41 groups were to the US where the typical hierarchy was first documented. The closer a sample was to the US culturally, the more similar its hierarchy of moral concern.
101
Matti Vuorre @matti.vuorre.com · 15/09/2026
I don't justify the use of mcmc anymore and push back when requested to do so. It's silly. I'm all for justifying methods but this is an odd one as the other one apparently needs no justification.
040
Reposted by Matti Vuorre
Gabor Csardi @gaborcsardi.org · 14/09/2026
New beta of #Rstats rig: LOTS of EXCITING stuff: - new: web site: rig.r-lib.org - new: user-mode R installation: rig.r-lib.org/admin-vs-use... - new: manage R packages (CRAN + git): rig.r-lib.org/pkg-guide.html - new: manage R projects and virtual environments: rig.r-lib.org/proj-guide.h...
rig.r-lib.org
rig – the R Installation Manager – rig
34919
Reposted by Matti Vuorre
Veli-Matti Karhulahti @mkarhulahti.bsky.social · 12/09/2026
If there's something positive in the ai/science discourse it has made more ppl reflect on why humanity keeps doing science beyond instrumental accounts-- for some, not only is the pursuit of knowledge inherently valuable but also defines collective curiosity & shapes our other values
042
Matti Vuorre @matti.vuorre.com · 08/09/2026
Season 8 of Quantitude off to a strong start. Loved the true crime framing here -- especially since we all know who's guilty!
111
Matti Vuorre @matti.vuorre.com · 01/09/2026
Yup, would be reasonable for a paper on reproducibility to be accessible -- a minimal requirement to reproducibility. Extremely meh
020
Matti Vuorre @matti.vuorre.com · 01/09/2026
Utrecht (and some other Dutch unis) are showing some leadership/bravery here www.uu.nl/en/news/remi... sciencebusiness.net/news/univers...
010
Matti Vuorre @matti.vuorre.com · 31/08/2026
static.klipy.com
Robocop Comply
ALT: Robocop Comply
010
Reposted by Matti Vuorre
Robert (Bob) Kubinec @rmkubinec.bsky.social · 25/08/2026
My ordered beta regression paper has now reached over 5k downloads on OSF: osf.io/preprints/so... I'd like to thank all of the readers 🫶 and also academic publishing companies by making it so darn hard to access the published version. As an FYI, the OSF version is *exactly* the same.
osf.io
OSF
3364
Matti Vuorre @matti.vuorre.com · 26/08/2026
Fear and anger sell; love and courage, sadly, do not. This is fucking awful.
010
Matti Vuorre @matti.vuorre.com · 26/08/2026
This is relevant, again: "Preprints—scholarly manuscripts not yet captured by the publication industry—are widely read and circulated, yet the ‘intellectual perestroika‘ they could facilitate hasn’t been uniformly realized..."
050
Reposted by Matti Vuorre
Jacob T. Levy @jacobtlevy.bsky.social · 24/08/2026
On this day in 2018. Kieran @kjhealy.co ‘s obituary will include the MacArthur essay and “Fuck Nuance,” but for a particular niche audience of connoisseurs, this is his masterpiece.
1035985
Matti Vuorre @matti.vuorre.com · 20/08/2026
Thanks, I will send any notes I encounter trying it out (will do shortly.) And as usual thanks so much for your work on all things jsPsych.
020
Matti Vuorre @matti.vuorre.com · 20/08/2026
jsPsych can now automatically document your data using the Psych-DS metadata standard: metadata.jspsych.org
2152
Matti Vuorre @matti.vuorre.com · 18/08/2026
This is great, thanks for developing it. I've used datapipe with OSF a couple times and it worked perfectly.
000
Reposted by Matti Vuorre
Josh de Leeuw @joshdeleeuw.bsky.social · 11/08/2026
With the upcoming changes to OSF, DataPipe (pipe.jspsych.org) is migrating to a multi-backend model. We're currently developing support for Zenodo, Dataverse, and Google Drive. If there are other providers that you'd like to see as options please get in touch.
pipe.jspsych.org
DataPipe
23017