Daniel Lakens
@lakens.bsky.social
Metascience, statistics, psychology, philosophy of science. Eindhoven University of Technology, The Netherlands. Omnia probate. 🇪🇺
Pinned
Daniel Lakens
@lakens.bsky.social
· Apr 14
OSF
osf.io
My paper on concerns about replicability, theorizing, relevance, generalizability, and methodology across 2 crises is now in press at the International Review of Social Psychology. After revisions it was 17500 words, so it is split in 2 parts: osf.io/dtvs7_v2 and osf.io/g6kja_v1
It makes me happy to see that a scientific book that looks interesting is available for free, open access. It also raises my expectation that it will be a good book, as the authors really wanted it to be read (unlike authors who merely want to have a book published).
January 4, 2026 at 7:21 AM
It makes me happy to see that a scientific book that looks interesting is available for free, open access. It also raises my expectation that it will be a good book, as the authors really wanted it to be read (unlike authors who merely want to have a book published).
Reposted by Daniel Lakens
To bring in the New Year, here's a proposal for external regulation of academic publishing, through a voluntary system of journal certification to the ISO 9001 quality management standard. 🧪 #ResearchIntegrity (1/2) www.nature.com/articles/d41...
www.nature.com
December 30, 2025 at 11:28 PM
To bring in the New Year, here's a proposal for external regulation of academic publishing, through a voluntary system of journal certification to the ISO 9001 quality management standard. 🧪 #ResearchIntegrity (1/2) www.nature.com/articles/d41...
Reposted by Daniel Lakens
2025 seems to be the end of p-curve. This preprint shares what we have learned from 10 years of p-curve results.
replicationindex.com/2026/01/03/w...
replicationindex.com/2026/01/03/w...
What a Decade of P-Curve Tells Us About False-Positive Psychology - Replicability-Index
The File-Drawer Problem A single study is rarely enough to provide sufficient evidence for a theoretically derived hypothesis. To make sense of inconsistent results across multiple studies, psychologi...
replicationindex.com
January 3, 2026 at 4:27 PM
2025 seems to be the end of p-curve. This preprint shares what we have learned from 10 years of p-curve results.
replicationindex.com/2026/01/03/w...
replicationindex.com/2026/01/03/w...
Reposted by Daniel Lakens
After this, the EU should absolutely proceed on the assumption that Trump meant what he said about Greenland. Nothing is off the table anymore.
January 3, 2026 at 10:41 AM
After this, the EU should absolutely proceed on the assumption that Trump meant what he said about Greenland. Nothing is off the table anymore.
Reposted by Daniel Lakens
Reports of widespread protests at universities and beyond across Iran. Thinking of students and scholars there, and wishing them safety and a brighter future.
January 2, 2026 at 5:31 PM
Reports of widespread protests at universities and beyond across Iran. Thinking of students and scholars there, and wishing them safety and a brighter future.
What the USA has done is absolutely disgraceful. Time for a boycot of US products, especially tech, and for the population in the USA to instigate a change in leadership in their own country.
January 3, 2026 at 10:25 AM
What the USA has done is absolutely disgraceful. Time for a boycot of US products, especially tech, and for the population in the USA to instigate a change in leadership in their own country.
Reposted by Daniel Lakens
well it’s one way to move attention from the Epstein files
President Trump ordered strikes on sites inside Venezuela, including military facilities, U.S. officials told CBS News, as the administration early Saturday ratcheted up its campaign against the regime of Venezuelan President Nicolás Maduro.
January 3, 2026 at 8:05 AM
well it’s one way to move attention from the Epstein files
Starting the new year with a new podcast episode of Nullius In Verba on 'Scientism' nulliusinverba.podbean.com/e/episode-72...
In the first of two parts, we ask if it is ok to think that science is the best way to generate knowledge, or if this is too dismissing of 'other ways of knowing'.
In the first of two parts, we ask if it is ok to think that science is the best way to generate knowledge, or if this is too dismissing of 'other ways of knowing'.
Episode 72: Scientismus - I | Nullius in Verba
In this two-part episode, we delve into the topic of scientism. Is science the best way to generate knowledge? Or are we giving too much deference to science if we believe this? In this first part,…
nulliusinverba.podbean.com
January 2, 2026 at 5:25 PM
Starting the new year with a new podcast episode of Nullius In Verba on 'Scientism' nulliusinverba.podbean.com/e/episode-72...
In the first of two parts, we ask if it is ok to think that science is the best way to generate knowledge, or if this is too dismissing of 'other ways of knowing'.
In the first of two parts, we ask if it is ok to think that science is the best way to generate knowledge, or if this is too dismissing of 'other ways of knowing'.
A highlight of my year has breaking through the 6b+ barrier in bouldering, managing some of my first 6c routes. Meeting up with a lovely crowd of friends once or twice a week is such a pleasant way to stay in shape.
December 31, 2025 at 7:13 PM
A highlight of my year has breaking through the 6b+ barrier in bouldering, managing some of my first 6c routes. Meeting up with a lovely crowd of friends once or twice a week is such a pleasant way to stay in shape.
Reposted by Daniel Lakens
Once again, John Ioannidis should just shut the fuck up.
December 24, 2025 at 1:25 AM
Once again, John Ioannidis should just shut the fuck up.
Reposted by Daniel Lakens
Our Spotify Wrapped tells us that collectively you have listened a total of 181 days to our podcast - and that's just for those of you using Spotify to listen to @nulliusinverba.bsky.social
Thank you all so much for listening!
Thank you all so much for listening!
December 23, 2025 at 5:31 AM
Our Spotify Wrapped tells us that collectively you have listened a total of 181 days to our podcast - and that's just for those of you using Spotify to listen to @nulliusinverba.bsky.social
Thank you all so much for listening!
Thank you all so much for listening!
It is not just that 'ideally' criteria for publication should be the same for significant and non-significant results - it is literally in the code of conduct for research integrity. If you do not act in line with this, you are violating the code of conduct for research integrity.
December 20, 2025 at 5:02 AM
It is not just that 'ideally' criteria for publication should be the same for significant and non-significant results - it is literally in the code of conduct for research integrity. If you do not act in line with this, you are violating the code of conduct for research integrity.
Reposted by Daniel Lakens
I sometime wonder how bad is the replication crisis in top AI conferences. I bet >50% of results cannot be reproduced and >80% will not withstand the slightest change in input data.
People give psychologists the shit about their shitty research, but at least they cared enough to actually check.
People give psychologists the shit about their shitty research, but at least they cared enough to actually check.
December 19, 2025 at 10:16 PM
I sometime wonder how bad is the replication crisis in top AI conferences. I bet >50% of results cannot be reproduced and >80% will not withstand the slightest change in input data.
People give psychologists the shit about their shitty research, but at least they cared enough to actually check.
People give psychologists the shit about their shitty research, but at least they cared enough to actually check.
There are many dubious papers on correcting for multiple comparisons. And the issue is so simple:
1) You need to control error rates of claims. If multiple tests inflate error rates, you must lower alpha.
2) you adjust on the level of a claim.
lakens.github.io/statistical_....
1) You need to control error rates of claims. If multiple tests inflate error rates, you must lower alpha.
2) you adjust on the level of a claim.
lakens.github.io/statistical_....
2 Error control – Improving Your Statistical Inferences
This open educational resource contains information to improve statistical inferences, design better experiments, and report scientific research more transparently.
lakens.github.io
December 19, 2025 at 6:22 AM
There are many dubious papers on correcting for multiple comparisons. And the issue is so simple:
1) You need to control error rates of claims. If multiple tests inflate error rates, you must lower alpha.
2) you adjust on the level of a claim.
lakens.github.io/statistical_....
1) You need to control error rates of claims. If multiple tests inflate error rates, you must lower alpha.
2) you adjust on the level of a claim.
lakens.github.io/statistical_....
"The replication crisis in Psychology has undermined both intra-scientific and public trust. This review shows–using Wilholt's notion of epistemic trust–that replicability is fundamental for epistemic reliability" #metascience
www.sciencedirect.com/science/arti...
www.sciencedirect.com/science/arti...
December 19, 2025 at 6:07 AM
"The replication crisis in Psychology has undermined both intra-scientific and public trust. This review shows–using Wilholt's notion of epistemic trust–that replicability is fundamental for epistemic reliability" #metascience
www.sciencedirect.com/science/arti...
www.sciencedirect.com/science/arti...
Reposted by Daniel Lakens
Finally, @bjoernhommel.bsky.social's and my paper introducing the SurveyBot3000 is officially out in AMPPS. It's a fine-tuned language model that guesstimates correlations between survey items from text alone. Not perfectly, but useful for search, for example.
journals.sagepub.com/doi/10.1177/...
journals.sagepub.com/doi/10.1177/...
December 18, 2025 at 8:21 PM
Finally, @bjoernhommel.bsky.social's and my paper introducing the SurveyBot3000 is officially out in AMPPS. It's a fine-tuned language model that guesstimates correlations between survey items from text alone. Not perfectly, but useful for search, for example.
journals.sagepub.com/doi/10.1177/...
journals.sagepub.com/doi/10.1177/...
It reminds me of the question 'who will replicate the replicators?' that people used to ask during the replication crisis. Turns out the answer is: the replicators themselves, after they have gained a decade of expertise on a topic :)
Very happy to have received a replication grant from NWO! We will be reproducing power analyses of large scale replication projects, to learn how to improve power analyses, and increase quality control in large team Science projects! www.openscience.nl/en/news/27-s...
27 studies re-examined | Open Science NL
Open Science NL has awarded funding to 27 applicants to replicate earlier studies. They will reanalyse original data, repeat experiments, and replicate studies with slight variations to the original…
www.openscience.nl
December 17, 2025 at 3:07 PM
It reminds me of the question 'who will replicate the replicators?' that people used to ask during the replication crisis. Turns out the answer is: the replicators themselves, after they have gained a decade of expertise on a topic :)
Very happy to have received a replication grant from NWO! We will be reproducing power analyses of large scale replication projects, to learn how to improve power analyses, and increase quality control in large team Science projects! www.openscience.nl/en/news/27-s...
27 studies re-examined | Open Science NL
Open Science NL has awarded funding to 27 applicants to replicate earlier studies. They will reanalyse original data, repeat experiments, and replicate studies with slight variations to the original…
www.openscience.nl
December 17, 2025 at 3:05 PM
Very happy to have received a replication grant from NWO! We will be reproducing power analyses of large scale replication projects, to learn how to improve power analyses, and increase quality control in large team Science projects! www.openscience.nl/en/news/27-s...
I'm very happy to continue my work at the Human-Technology Interaction group as a Full Professor of Metascience.
Working at this department has been a great source of joy over the last 15 years.
Working at this department has been a great source of joy over the last 15 years.
December 15, 2025 at 5:27 PM
I'm very happy to continue my work at the Human-Technology Interaction group as a Full Professor of Metascience.
Working at this department has been a great source of joy over the last 15 years.
Working at this department has been a great source of joy over the last 15 years.
Reposted by Daniel Lakens
New #NIH prize competition to identify areas of biomedical science that can benefit from replication and to recognize past replication efforts to further promote the importance of research replication:
www.challenge.gov?challenge=re...
Submission deadline is in one month!
www.challenge.gov?challenge=re...
Submission deadline is in one month!
Challenge.gov
Challenge.gov is the official government website supporting prize challenges and prize competitions that are sponsored by the US federal government. Here federal agencies provide prize awards to publi...
www.challenge.gov
December 11, 2025 at 2:21 PM
Reposted by Daniel Lakens
“Dutch people cycle an average of 2.6km each per day. If this pattern was replicated worldwide, annual carbon emissions would drop by 686 million tonnes.
This mammoth figure exceeds the entire carbon footprint of most countries, including the UK, Canada, Saudi Arabia and Australia.” @euronews.com
This mammoth figure exceeds the entire carbon footprint of most countries, including the UK, Canada, Saudi Arabia and Australia.” @euronews.com
Cycling like the Dutch would slash the world’s carbon footprint
If everybody cycled like the Dutch, we could offset the UK or Australia’s entire carbon footprint.
www.euronews.com
December 13, 2025 at 10:01 PM
“Dutch people cycle an average of 2.6km each per day. If this pattern was replicated worldwide, annual carbon emissions would drop by 686 million tonnes.
This mammoth figure exceeds the entire carbon footprint of most countries, including the UK, Canada, Saudi Arabia and Australia.” @euronews.com
This mammoth figure exceeds the entire carbon footprint of most countries, including the UK, Canada, Saudi Arabia and Australia.” @euronews.com
Reposted by Daniel Lakens
Just feeding "slow uptake of diamond OA journals" with numbers from Germany: According to OA Monitor (open-access-monitor.de/open-access), which uses WoS, Scopus, and OpenAlex, we are talking about less than 5% (!) of articles being published as Diamond OA.
December 10, 2025 at 12:30 PM
Just feeding "slow uptake of diamond OA journals" with numbers from Germany: According to OA Monitor (open-access-monitor.de/open-access), which uses WoS, Scopus, and OpenAlex, we are talking about less than 5% (!) of articles being published as Diamond OA.
Reposted by Daniel Lakens
Reposted by Daniel Lakens
New blog post: Dogmatic Bayesianism Disorder
daniellakens.blogspot.com/2025/12/dogm...
daniellakens.blogspot.com/2025/12/dogm...
December 6, 2025 at 7:23 AM
New blog post: Dogmatic Bayesianism Disorder
daniellakens.blogspot.com/2025/12/dogm...
daniellakens.blogspot.com/2025/12/dogm...
In my paper Sample Size Justification I discuss 6 approaches to justifying sample sizes. The focus of the paper is to teach people the tools they need to be honest when they explain where their sample size comes from. I know, so radical ;) online.ucpress.edu/collabra/art...
December 7, 2025 at 10:12 AM
In my paper Sample Size Justification I discuss 6 approaches to justifying sample sizes. The focus of the paper is to teach people the tools they need to be honest when they explain where their sample size comes from. I know, so radical ;) online.ucpress.edu/collabra/art...