Lightnews — Scholar-powered news

Richard D. Morey

@richarddmorey.bsky.social

5.4K followers 810 following 500 posts

Statistics, cognitive modelling, and other sundry things. Mastodon: @[email protected] [I deleted my twitter account]

Posts Media Videos Starter Packs

Pinned

Richard D. Morey @richarddmorey.bsky.social · Aug 8

Paper drop, for anyone interested in #metascience, #statistics, or #metaanalysis! @clintin.bsky.social and I show in a new paper in JASA that the P-curve, a popular forensic meta-analysis method, has deeply undesirable statistical properties. www.tandfonline.com/doi/full/10.... 1/?

Cover page for the manuscript: Morey, R. D., & Davis-Stober, C. P. (2025). On the poor statistical properties of the P-curve meta-analytic procedure. Journal of the American Statistical Association, 1–19. https://doi.org/10.1080/01621459.2025.2544397

Abstract for the paper: The P-curve (Simonsohn, Nelson, & Simmons, 2014; Simonsohn, Simmons, & Nelson, 2015) is a widely-used suite of meta-analytic tests advertised for detecting problems in sets of studies. They are based on nonparametric combinations of p values (e.g., Marden, 1985) across significant (p < .05) studies and are variously claimed to detect “evidential value”, “lack of evidential value”, and “left skew” in p values. We show that these tests do not have the properties ascribed to them. Moreover, they fail basic desiderata for tests, including admissibility and monotonicity. In light of these serious problems, we recommend against the use of the P-curve tests.

17 120 290

Reposted by Richard D. Morey

Grem, of 𝐆𝐑𝐄𝐌𝐂𝐎𝐑𝐏 🔜 MCAtlanta! @gremlin.world · 2d

I will never not repost this

(Sound on for maximum effect)

31 2.2K 4.6K

Reposted by Richard D. Morey

Steve Horton is writing a graphic novel @stevehorton.mst3k.fan · 1d

fuck the moon @fuckthem00n
FUCK THE MOON
fly me to the moon let me kick it's fucking ass let me show it what i learned
in my moon jujitsu class
3:05 PM • 10/17/19 • Twitter for Android
28K Retweets 111K Likes
FUCK THE MOON
fuck the moon @fuckthem00n • 1d wow this blew up. wish the moon would.
29
LX238
4,182
V

1 12 95

Reposted by Richard D. Morey

Olivia Guest · Ολίβια Γκεστ @olivia.science · 4d

yup! if anybody reading or otherwise needs a primer Guest, O. & Martin, A. E. (2021). How Computational Modeling Can Force Theory Building in Psychological Science. Perspectives on Psychological Science. doi.org/10.1177/1745...

bsky.app/profile/oliv...

Olivia Guest · Ολίβια Γκεστ @olivia.science · Apr 7

I'm looking back at this paper written 2019 & published 2021 with @andreaeyleen.bsky.social: How Computational Modeling Can Force Theory Building in Psychological Science (pdf: oliviaguest.com/doc/guest_ma...) We presented a positive view and kind, if I do say so myself, compatibilist stance. 1/

fig 2 in Guest, O., & Martin, A. E. (2021). How Computational Modeling Can Force Theory Building in Psychological Science. Perspectives on Psychological Science, 16(4), 789-802. https://doi.org/10.1177/1745691620970585

1 3 11

Richard D. Morey @richarddmorey.bsky.social · 4d

My argument has always been that the “skills” needed to use it without being fooled are critical thinking and research which is supposed to be what we already teach anyway. But people are advocating for it’s use in thinking and research so obviously something is off.

6 40

Richard D. Morey @richarddmorey.bsky.social · 4d

Also - contrast b/w the response when I advocate teaching R instead of SPSS -- "No hurry, let's not rush into it" (still waiting) -- & others re: use of LLMs -- "It's inevitable, we're behind; need it implement it ASAP!" -- is telling. Learning to code is freeing. Overhyped LLMs create dependency.

Excerpt from Guest & van Rooij, 2025:

As Danielle Navarro (2015) says about shortcuts through us-
ing inappropriate technology, which chatbots are, we end up dig-
ging ourselves into “a very deep hole.” She goes on to explain:

"The business model here is to suck you in during
your student days, and then leave you dependent on
their tools when you go out into the real world. [...]
And you can avoid it: if you make use of packages
like R that are open source and free, you never get
trapped having to pay exorbitant licensing fees." (pp.
37–38)

3 32 110

Richard D. Morey @richarddmorey.bsky.social · 4d

Mathematical psychology uses simulation as well, to understand models that are too complex to understand completely without it. It can help uncover surprising behaviour or predictions. Crucially, the sims are helping understand models, not people. The *psychological* knowledge is gained elsewhere.

1 1 7

Richard D. Morey @richarddmorey.bsky.social · 4d

For me this is a hard red line in psychological science. If you advocate the use of "silicon samples" you do not understand what it is we're supposed to be doing (and likely don't understand LLMs, or are a grifter). Luckily I haven't seen much of this among people I'd consider my peer group.

Except from Table 1 of Guest & van Rooij, 2025:

3) Displacement of Participants

“I can use AI instead of participants to perform tasks and generate data.”

The providence of the data used in these models indicates it is not ethically sourced, falling below standards for our discipline, involving sweatshop labour and no consent for private data used in experiments. The output can contain direct original input data (i.e. double dipping), but smoothed to remove outliers, conform to our pre-existing ideas of what it should look like (data fabrication), and all-round irreplicable. Psychology is meant to study humans, not patterns at the output of biased statistical models.

1 13 58

Richard D. Morey @richarddmorey.bsky.social · 4d

"Ultimately, contemporary AI is research misconduct"

I like it already :)

1 3 16

Reposted by Richard D. Morey

Derek Gottlieb @derekgottlieb.bsky.social · 5d

The most important and clarifying thing here is a literal definition of “loser shit”: "the dysfunctions that bad leadership is prone to, particularly an obsession with rules and norms: 'If I follow the rules, at least I can't be blamed when we lose.’"

Democrats Must Embrace War Mindset

We have exited a long period of peace and entered into a struggle not unlike war, in which all the old certainties have gone malleable and the future of the republic is at stake.

www.liberalcurrents.com

1 20 67

Richard D. Morey @richarddmorey.bsky.social · 5d

see lots of folks talking up Scylla and the Sirens, but the real stuff is the crazy flute solo while fighting Polyphemus

Reposted by Richard D. Morey

Olivia Guest · Ολίβια Γκεστ @olivia.science · 5d

"People don't necessarily realize this because if you try to explain to someone how AT Proto works, they immediately go to sleep, but let's try anyway."

🥲

azhdarchid.com/delusions-of...

Delusions of a Protocol

On vaporware as an ideological product.

azhdarchid.com

1 35 130

Reposted by Richard D. Morey

Natalia Jagielska @nataliajagielska.bsky.social · 5d

Ptero

9 120 530

Reposted by Richard D. Morey

Gary Lupyan @glupyan.bsky.social · 7d

A wild exchange with Gemini Pro 2.5. In preparing some examples for my seminar (cogsci-llms.netlify.app) I remembered @randomwalker.bsky.social old tweet about playing Rock paper scissors with LLMs. Decided to see what it's like now ....

1 8 22

Reposted by Richard D. Morey

Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 7d

My first attempt to dispel concern with this kind of naive correlation filtering: It can arise from different causes and vanish in a properly specified model. Example: Data generated by this DAG

X –> Z –> Y

can have highly correlated X and Z. But in model Y ~ X + Z it won't show any "collinearity"

1 1 9

Reposted by Richard D. Morey

Andy Zax @andyzax.bsky.social · 8d

While going through text messages from Kaleb—insert an image of Charlie Brown saying “sigh” here—I found this, from about a year ago. The point he was making applies to all of us.

I occasionally check in with Al, not just because there's filthy gig money in Al training but also to see where the tech is at, and ask it to write an essay about California by me and the results are always so bad, so unfixable, so obviously counterfeit, that it gives me motivation to write again. It just reminds me l'm the only entity that does what I do. Never mind getting more validation than that, it tells me l'm not a statistic.

2 120 770

Richard D. Morey @richarddmorey.bsky.social · 8d

thank you for saying what we’re all thinking

Richard D. Morey @richarddmorey.bsky.social · 10d

Another awesome video from Numberphile. I’m not going to spoil it, but I will say it is very relevant if you teach research methods (it not just statistical in a narrow sense) youtu.be/VwIKKBL4ldQ?...

We have statistical evidence that people are mildly psychic

YouTube video by Stand-up Maths

youtu.be

10 34

Reposted by Richard D. Morey

Danielle Navarro @djnavarro.net · 10d

A few words on survey weights, why I'm embarrassed to have forgotten to take them into account in the past, and how I got lucky because I personally didn't get burned. Not a mistake I intend to repeat in the future

blog.djnavarro.net/posts/2025-0...

Some notes on survey weights – Notes from a data witch

An area of statistics in which the author is not strong, and really needs to up her game

blog.djnavarro.net

8 16 71

Reposted by Richard D. Morey

Mark Rubin @markrubin.bsky.social · 10d

Report on Australian Higher Education finds:

🔹️ Council members have no lived experience of universities

🔹️ Council members have COIs with consultancy firms

🔹️ Council meetings are closed affairs that lack transparency

🔹️ Leaders' exorbitant salaries could not be justified

One submission said leaders’ salaries could not be “justified by the quality of executive decision-making, nor by the scope of executive duties. The core business of a university – teaching and research – is co-ordinated virtually entirely by ordinary non-executive staff”.

3 25 53

Reposted by Richard D. Morey

Jo Wood @jwolondon.bsky.social · 10d

A great post from @djnavarro.net, providing an accessible explanation of why statistics that can appear to reveal our ignorance may actually do the opposite. Makes excellent use of #datavis to provide visual support for the argument.

blog.djnavarro.net/posts/2025-0...

Some notes on probability judgement – Notes from a data witch

For the love of fuck, literally nobody thinks that 20% of the population is transgender. Please stop sharing that ridiculous YouGov statistic

blog.djnavarro.net

2 18 47

Reposted by Richard D. Morey

Iris van Rooij 💭 @irisvanrooij.bsky.social · 11d

There is absolutely no good faith reason to use the term “AI” for any technology one is selling.

It serves only for dazzling people into thinking the technology has capabilities that it doesn’t.

If one wants a technology to be trustworthy, just use a transparent, informative term without hype.

75 230 1.2K

Reposted by Richard D. Morey

Kit Yates @kityates.bsky.social · 11d

If I was a tutoring company and I wanted to convince you that I could teach your kids maths, I would probably not have an advert that said “3=2” on it!

That’s just me though.

58 290 1.7K

Richard D. Morey @richarddmorey.bsky.social · 11d

“Going through the motions”

1 2

Reposted by Richard D. Morey

The Museum of English Rural Life (MERL) @themerl.bsky.social · 11d

yeah we're into LLMs (Large Lamb-bridge Models)

A herd of sheep move across a marshy bridge.

13 300 1.3K

Richard D. Morey @richarddmorey.bsky.social · 11d

Ha, I'm way to deep in this stats hole to crawl out, but a class is still a good idea! There must be something in SE Wales.