Lightnews — Scholar-powered news

Reposted by Yashvin Seetahul

Eric Hehman @erichehman.bsky.social · Aug 17

I unfortunately think demand characteristics are an underappreciated cause of a lot of effects in the lit

Nicholas A. Coles @nicholascoles.bsky.social · Aug 14

New 📰

Demand characteristics are a fundamental methodological concern in research with humans

Yet little is known about the magnitude and consistency of these effects

In a new paper, I, M. Wyatt, and @mcxfrank.bsky.social take stock of what we’ve learned via meta-analysis

doi.org/10.1525/coll...

A Meta-Analysis of the Impact and Heterogeneity of Explicit Demand Characteristics

Demand characteristics are a fundamental methodological concern in experimental psychology. Yet, little is known about the direction, magnitude, and consistency of their effects. We conducted a three-...

doi.org

2 9

Reposted by Yashvin Seetahul

JD Long @jdlong.cerebralmastication.com · 18d

New code review response just dropped:

2 37 170

Reposted by Yashvin Seetahul

Vilgot Huhn @vilgothuhn.bsky.social · 24d

Anyone familiar with robust regression for heavy-tailed residuals? Seems there are many alternatives. The only method I've learned is Bayesian regression with regularizing priors (from @rmcelreath.bsky.social book) and for the moment I want a frequentist alternative (sorry Bayesians) #stats #rstats

7 3 9

Reposted by Yashvin Seetahul

Lalo Alcaraz @laloalcaraz.bsky.social · 27d

Was it worth it? #massshootings #schoolshootings #charliekirk #guncontrol Please share #laloalcaraz cartoons

43 550 1.4K

Yashvin Seetahul @yashvin.bsky.social · Sep 8

Yes! There are some YT channels where they show the timeseries of blood sugar after eating specific food combinations. It's really interesting to see. I'd be obsessed with checking all the time if I had this. But 150/200 euros a month would feel like an expensive obsession to me 😅

1 1

Yashvin Seetahul @yashvin.bsky.social · Sep 8

The only thing missing in the app is the ability to track time varying confounders 🫣

1 2

Reposted by Yashvin Seetahul

Brett Murphy @brettmurpsych.bsky.social · Sep 7

Want to know what a sample of 200+ editorial board members think about citing practices in psychology? That and much more in this AMPPS article. We had a lot of fun pulling it together. journals.sagepub.com/doi/10.1177/...

2 7 19

Reposted by Yashvin Seetahul

Mary Beth Neff ("Mary-Beth") @mbneff.bsky.social · Sep 3

For those interested, here's our full preprint on the call for more transparent pilot study reporting: osf.io/preprints/ps...

@ihandleyminer.bsky.social #OpenScience #PilotStudies

Mary Beth Neff ("Mary-Beth") @mbneff.bsky.social · Sep 3

"Don't seat the baby near the door" 👶 Thanks to @infantstudies.bsky.social for the chance to discuss our task force work on making pilot study insights more transparent to improve psyc science!

@agataboch.bsky.social #OpenScience #DevPsySky #PilotStudies #PsychScience #Transparency

International Congress of Infant Studies @infantstudies.bsky.social · Sep 2

New on the Baby Blog - Making pilots public and improving developmental science by @agataboch.bsky.social and @mbneff.bsky.social #EarlyYears #DevPsySky #PsychSciSky #science #research #infantstudies infantstudies.org/making-pilot...

3 4

Reposted by Yashvin Seetahul

Hannah Lönneker @hloenneker.bsky.social · Sep 3

Feel free to write us an e-mail at [email protected], join the conversation on here or visit our website for more information: pilotreportingtf.github.io. 2/4

Pilot Reporting Task Force

🚀

pilotreportingtf.github.io

1 1 4

Reposted by Yashvin Seetahul

Hannah Lönneker @hloenneker.bsky.social · Sep 3

As part of the Pilot Reporting Task Force, founded at @improvingpsych.org conference 2023, I would like to share a preprint with you: osf.io/preprints/ps.... We are looking for feedback on our perspective piece, promoting more transparency in the reporting of piloting in psychological science. 1/4

OSF

osf.io

1 9 10

Reposted by Yashvin Seetahul

Eiko Fried @eikofried.bsky.social · Aug 11

New paper by @bsiepe.bsky.social & WARN-D team out now in JoPACS, on the (lack of) relation between EMA selfreport and Garmin passive data.

Guardian @theguardian.com coverage:
www.theguardian.com/technology/2...

Paper:
psycnet.apa.org/doiLanding?d...

🧪 #PsychSciSky #StatsSky #EpiSky

Smartwatches offer little insight into stress levels, researchers find

Academic study suggests devices cannot differentiate between someone being overworked and being excited

www.theguardian.com

3 29 70

Reposted by Yashvin Seetahul

Cameron Brick @cameronbrick.bsky.social · Sep 2

Do I know any experienced wikipedia editors? I'm confused about why a submission is being rejected (without specificity as to what content doesn't meet guidelines).

1 1 2

Reposted by Yashvin Seetahul

Bryan Culbertson 🥄 @bryanculbertson.com · Apr 26

Reminder to donate to Wikipedia every time the Trump regime tries to censor them

donate.wikimedia.org/wiki/Ways_to...

1 16 41

Reposted by Yashvin Seetahul

Greg Priest @gregpriest.bsky.social · Aug 29

New study on #BlueSky for #SciComm.

“Bluesky posts demonstrate substantially higher levels of interaction (likes, reposts, replies, and quotes) and greater textual originality than previously reported for X, suggesting both stronger interactive and more interpretive engagement.”

🦋🦫🌱🐋🧪 #philsci

Research posts on Bluesky are more original — and get better engagement

Bluesky posts about science garner more likes and reposts than similar ones on X.

www.nature.com

4 61 190

Reposted by Yashvin Seetahul

Brian Nosek @briannosek.bsky.social · Aug 27

10 years ago?! Holy smokes.

5 14 62

Reposted by Yashvin Seetahul

Ian Hussey @ianhussey.mmmdata.io · Aug 27

It’s fascinating to argue that LLMs mimic humans when they’re producing effects that aren’t replicated in humans.

1 1 11

Reposted by Yashvin Seetahul

Jamie Cummins @jamiecummins.bsky.social · Aug 27

So, as evidence of "mimicry", we have the LLM exhibiting effect sizes in the 90th-98th percentile of effects seen in studies of human beings in a paradigm where humans do not replicably show the effect. Not very compelling IMO.

mmmdata.io/posts/2025/0...

If researchers find Cohen's *d* = 8, no they didn't

I’ve spent a lot of time thinking about the plausibility of standardized effect sizes in the last year. From a trustworthiness assessment perspective, (standardized) effect sizes have a great combinat...

mmmdata.io

2 1 8

Reposted by Yashvin Seetahul

Cameron Patrick @cameronpat.bsky.social · Aug 28

not at all surprising: arstechnica.com/science/2025...

Bluesky now platform of choice for science community

It’s not just you. Survey says: “Twitter sucks now and all the cool kids are moving to Bluesky”…

arstechnica.com

3 47 270

Yashvin Seetahul @yashvin.bsky.social · Aug 28

Failure of imagination of alternative interpretations in itself is not an issue, but it's the taboo of admitting a mistake...

If these same concerns had been brought up prior to publication (e.g., colleagues, reviewers, editor), I'm sure authors would be more open to considering alternative views.

2

Reposted by Yashvin Seetahul

Carl Zimmer @carlzimmer.com · Aug 19

How to recognize shoddy studies that claim to link vaccines and autism. Essay by @unbiasedscipod.bsky.social Gift link: nyti.ms/3UUNrIp

Opinion | The Playbook Used to ‘Prove’ Vaccines Cause Autism (Gift Article)

Data can easily be manipulated to show causation that doesn’t exist.

nyti.ms

1 35 83

Reposted by Yashvin Seetahul

Jamie Cummins @jamiecummins.bsky.social · Aug 27

This has now been published in PNAS!

www.pnas.org/doi/10.1073/...

The original authors also posted a reply:

www.pnas.org/doi/10.1073/...

Quick thread on some additional thoughts and then I'm probably done talking about this one 🧵

2 17 50

Reposted by Yashvin Seetahul

Lisa Spantig @lisaspantig.com · Aug 24

Why LLMs are not a substitute for humans in research on human behavior:

Human participants were responsive to semantic nuances that LLMs didn't pick up.

Example: Cut their beard to shame someone vs cut their beard to shave someone.

#Econsky

Benjamin Paaßen @bpaassen.bsky.social · Aug 12

Large Language models (LLMs) do not simulate human psychology. That's the title of our new paper, available as preprint today (1/12):

arxiv.org/abs/2508.06950

Large Language Models Do Not Simulate Human Psychology

Large Language Models (LLMs),such as ChatGPT, are increasingly used in research, ranging from simple writing assistance to complex data annotation tasks. Recently, some research has suggested that LLM...

arxiv.org

2 11

Reposted by Yashvin Seetahul

Daniel Lakens @lakens.bsky.social · Aug 25

If you are preparing your bachelor statistics course and would like to add optional material for students to better understand statistics on a conceptual level (see topics in the screenshot) my free textbook provides a state of the art overview. lakens.github.io/statistical_...

4 68 210

Yashvin Seetahul @yashvin.bsky.social · Aug 25

Never ever declaw cats.

www.nature.com/articles/s41...

Declawing in Cat is associated with neuroplastic sensitization and long-term painful afflictions - Scientific Reports

Scientific Reports - Declawing in Cat is associated with neuroplastic sensitization and long-term painful afflictions

www.nature.com

Reposted by Yashvin Seetahul

Thom Volker @thomvolker.bsky.social · Aug 21

Been working on a tutorial on synthetic data for open science for @lmu-osc.bsky.social
A draft version is now up: lmu-osc.github.io/synthetic-da...

It covers model building, evaluating synthetic data utility with density ratio estimation, and disclosure risk.

Feedback is very welcome!

3 13 38