Jim Grange

This could be done by (1) embedding open outputs in promotion criteria, valuing rigour & transparency over "high-impact" publications; (2) recognising data sets, pre-prints, and replication reports as valuable; (3) highlighting exemplars of researchers publishing negative results

It's also interesting the piece calls for "a couple of high-profile funders or institutions" to provide momentum for a tipping point in promoting the publishing of negative results. This seems something an agile University could look to implement to lead the way.

Research funders urged to drive culture shift on negative results - Research Professional News Reform needed to improve trust in science, patient care and training of AI, advocates say

"Research funders urged to drive culture shift on negative results". Interesting perspective at Research Professional. Of course, Registered Reports offer a valuable solution not mentioned here. www.researchprofessionalnews.com/rr-news-worl...

A Chess Scandal Revisited – Why Nakamura is Right About Cherry-Picking Recently I was attended to a paper by Maharaj, Polson, and Sokolov, in which they provided a statistical analysis of a chess cheating allegation. Their abstract: We provide a statistical analysis o…

A chess scandal revisited -- and why Nakamura was right
www.bayesianspectacles.org/a-chess-scan...

Fancy being a journal Section Editor?

Exciting Opportunity: Two new Section Editors needed for Cogent Psychology.

One for 'Personality & Individual Differences' & one for 'Social Psychology'.

Why not submit an application.

Details below. D/l 7th Nov.
think.taylorandfrancis.com/editor_recru...

Multiverse simulation to explore the impact of analytical choices on type I and type II errors in a reaction time study - Behavior Research Methods Researcher degrees of freedom in data analysis present significant challenges in social sciences, where different analytical decisions can lead to varying conclusions. In this work, we propose an exam...

I am happy to announce the publication of our new work on the impact of arbitrary analytical choices on type I and type II error rates. We simulated reaction time data in a conflict task and analyzed the notable CSE effect in a multiverse manner. Worrying results:
link.springer.com/article/10.3...

Multiverse simulation to explore the impact of analytical choices on type I and type II errors in a reaction time study - Behavior Research Methods Researcher degrees of freedom in data analysis present significant challenges in social sciences, where different analytical decisions can lead to varying conclusions. In this work, we propose an exam...

New paper, now out in Behavior Research Methods. "Multiverse simulation to explore the impact of analytical choices on type I and type II errors in a reaction time study"

link.springer.com/article/10.3...

I often see papers using GPower for power analysis in repeated measures factorial ANOVA designs. I don’t know what it’s doing, but it’s definitely giving wrong answers: substantially underestimates required sample size. MorePower seems like a much better alternative github.com/LewisPeacock...

I've spent the past weeks publishing my flankr package on CRAN for R. Users who've only installed the first version will notice SIGNIFICANT improvements in model fit speed.

Plus, I made a hex sticker for it.

CRAN: cran.r-project.org/web/packages...
Github (dev version): github.com/JimGrange/fl...

Well this is a delightfully clever study. Check it out.

Book Review | BPS - British Psychological Society BPS Explore is our easy-to-access central location for you to read and download a wide range of psychological content from practitioners, researchers and working groups.

Does anyone have access to this book review I wrote for the BPS in 2011, please? explore.bps.org.uk/content/bpsp...

Ah massive congratulations, Professor Holmboe!

So go for it. I'm looking forward to reading it!

Write for yourself, first & foremost. Use writing as a tool for thinking. I find t's not until I start writing that I realise my thoughts on a matter. Not just that, the process of writing helps sharpen my thoughts and signals where my thinking is not yet developed enough.

The reason it's been on my mind is I feel a similar way: I used to write a lot a few years ago and feel strong hesitation in starting again. But a feel a piece of me is missing by not doing it. Maybe that's how you feel; maybe it's not. But I think—whether you publish it or not—you should write.

Your post has been at the back of my mind for the past couple of days. I 100% think you should start writing again. I've certainly valued your writing.

I only started running properly around my 40th. I've just turned 44, and training now for my 5th marathon. A half mara is a gateway drug to the full mara, so see you on the start line of a full marathon soon :)

Mixed signals: stimulus‐response compatibility and car indicator light configuration The amber indicator lights on cars are designed to enable road users to efficiently predict the driver's next manoeuvre. Among other factors (e.g. luminance), the spatial configuration of these light...

Reminds me of this paper from Andrew Bayliss (now UEA):

onlinelibrary.wiley.com/doi/abs/10.1...

Can I ask what the format of the (half) day was? Always interested in how other departments approach research away days. (Currently planning our research week here for early Sept.)

Unlike standard publishing you absolutely CAN send the same proposal to multiple publishers to try and get the best deal. We had 3 publishers on board for our book proposal and were therefore able to choose the one we preferred.

Not only is this a *superb* paper, I'm learning so much from the code posted online. Thank you @gidon-frischkorn.bsky.social!

Paper: psycnet.apa.org/record/2026-...
Code: github.com/GidonFrischk...

Ahhh the good old days on Twitter seeing people post these blogs.

I use this format in all my documents & spreadsheets much to the dismay of my colleagues. (I'm in the UK.)

Leadership A short (let’s see!) blog post about leadership, which has been on my mind lately. But first, a digression. Regular readers will have noticed I’ve not been posting much. This is because…

Remember that I used to write blog posts?? It's been an eternity, but I finally wrote another on. This time on leadership

gavinbuckingham.wordpress.com/2025/07/07/l...

Didn't realise he's on BlueSky! Here's the first author: @sbmoore.bsky.social

New pre-print: The impact of dimension switching on visual short-term memory. This is some of the PhD work of Stuart Moore.

osf.io/preprints/ps...

Hot take: Some computational modellers don't share readable, complete code—or offer help when asked—because gatekeeping methods gives them a professional edge. It's bad for science and worse for collaboration.

I'm therefore committed to only sharing usable software and readable model code. And if there's something that's not clear to someone, I will do everything I can to help.

What is "obvious" to some is a month's work (more?) for me.

I don't think it's (necessarily) intentional—the "curse of knowledge" likely means some people don't realise just how much better their understanding is, and just how much I struggle to understand some aspects of modelling.