It's not just p-values that get hacked. We added a 3rd large dataset to our preprint: APA PsycTests. 67512 Cronbach's alphas from 60491 scales again show excesses at the .70 rule of thumb threshold. osf.io/preprints/psya… Malte Elson Ruben C. Arslan Taym Alsalti Frank Bosco

I'm very excited to share a preprint from a passion project I've been working on this past year! This came out of trying to work through two puzzles that have been bothering me for a while, and which are at the core of almost everything most of us study. osf.io/preprints/psya…

Interesting work in progress from Höfler et al. : A falsification assessment form (FAF) docs.google.com/presentation/d…

We estimate that ~48,000 articles from 2017-2022 and indexed in PubMed Central or PubMed used G*Power. Two assessors were able to reproduce 2% (2 out of 95) sample size calculations without making any assumptions and 28% (27/95) after making assumptions. medrxiv.org/content/10.110…

🚨Calling all EXERCISE SCIENCE/NUTRITION researchers: Bad science & questionable research practices are harming the discipline. Help elucidate the extent of the problem by completing our anonymous questionnaire. #Science #Research ➡️t.ly/CcWmC Please share!

What should researchers replicate? Anna van 't Veer, Daniël Lakens & Peder M Isager proposed the Replication Value as a metric. In a commentary, Bert Bakker, Delaney Peterson & I reflect on it and propose a revision to better differentiate between studies with large samples. t.ly/av_Kv

New paper: The benefits of preregistration and Registered Reports, with Cristian Mesquida, sajedeh and former lab visitor Max Ditroilo. We provide a state-of-the-art overview of the metascience on preregistration and Registered Reports. tandfonline.com/doi/full/10.10… >

That means we also do not expect people who have different epistemological philosophies to preregister – nor is it a logical solution for exploratory research, or certain types of secondary data analysis. >

I am very proud of this paper, which proposes a systematic method for testing whether theories putatively explain empirical phenomena. Congrats to the whole team, thanks to Noah van Dongen for pulling it over the finish line. psycnet.apa.org/fulltext/2025-…

New preprint: "The value of replications goes beyond replicability and is tied to the value of the research it replicates: Commentary on Isager et al. (2024)" My very quick take on the Isager and team's work on value of replications. Read: researchgate.net/publication/38…

Even then I agree with Gilad Feldman that RV is primarily about resource optimization to support replicators *before study is run*. Once a replication is done, there is nothing to optimize. Not publishing the replication study is the only way we can waste resources at that point.

“The people who work in research integrity ... call it HARKing, p-hacking, selection bias, and so on,... but ... the answer is staring us in the face. We are asking people to do things [statistical analysis] they are not trained for.” bit.ly/3YBF2wd

Daniël Lakens Gilad Feldman The two talks at our upcoming hackathon, featuring amazing speakers Daniël Lakens & Gilad Feldman, will be held online & are open to everyone. To prevent issues during the Zoom meeting, we will send Zoom ID via email, scanning the QR code or wjx.cn/vm/QQImR2g.asp… to fill out the form

nature.com/articles/s4156…

"𝑰𝒇 𝒚𝒐𝒖 𝒅𝒐𝒏'𝒕 𝒕𝒆𝒍𝒍 𝒚𝒐𝒖𝒓 𝒐𝒘𝒏 𝒔𝒕𝒐𝒓𝒚, 𝒔𝒐𝒎𝒆𝒐𝒏𝒆 𝒆𝒍𝒔𝒆 𝒘𝒊𝒍𝒍 𝒕𝒆𝒍𝒍 𝒊𝒕 𝒇𝒐𝒓 𝒚𝒐𝒖. 𝑨𝒏𝒅 𝒚𝒐𝒖 𝒎𝒊𝒈𝒉𝒕 𝒏𝒐𝒕 𝒍𝒊𝒌𝒆 𝒉𝒐𝒘 𝒕𝒉𝒆𝒚 𝒅𝒐 𝒊𝒕." - 𝑆ℎ𝑖𝑟𝑙𝑒𝑦 𝑀𝑎𝑙𝑐𝑜𝑙𝑚 We're excited to launch a new initiative at the

We're looking for a PhD student (75% position, in Leipzig with me and Björn) and a postdoc (in Bern, with Malte) to work with us starting sometime in early 2025. Get in touch here or via email to my handle at gmail.

New blog post: Why I don’t expect to be convinced by evidence that scientific reform is improving science (and why that is not a problem) daniellakens.blogspot.com/2024/09/why-i-…

The Replication Database: Documenting the Replicability of Psychological Science Data paper is out! doi.org/10.5334/jopd.1… “... the Replication Database (forrt-replications.shinyapps.io/fred_explorer), a novel platform hosting 1,239 original findings paired with replication findings.”

I have been writing a German textbook on Open Science that summarizes a plethora of problems and solutions in a simple way. It is available online for free (because everything else would be *closed* science) and the WIP version is accessible here: lukasroeseler.github.io/opensciencebuc…

New blog post: The distinction between logical justifications and empirical justifications: A reply to Prof. Hullman daniellakens.blogspot.com/2024/09/the-di… I respond to her blog post here (statmodeling.stat.columbia.edu/2024/09/19/get…) to answer some of the questions she had after reading my blog.