Eiko Fried
@eikofried.bsky.social
Professor of Mental Health & Data Science at Leiden University. Studying mental health problems as systems (http://eiko-fried.com). Building an early warning system for depression (http://WARN-D.com).
Probably Illustrator or Indesign or so
February 4, 2026 at 8:56 PM
Probably Illustrator or Indesign or so
Does anyone know why some fancy journals redraw your figures for you (no matter how much you object) — must be some copyright ($) thingie?
Below from the proofs I just got. Looks like they placed all numbers by hand (and definitely not in the node center, see e.g. "4") 🫣
Below from the proofs I just got. Looks like they placed all numbers by hand (and definitely not in the node center, see e.g. "4") 🫣
February 4, 2026 at 8:49 PM
Does anyone know why some fancy journals redraw your figures for you (no matter how much you object) — must be some copyright ($) thingie?
Below from the proofs I just got. Looks like they placed all numbers by hand (and definitely not in the node center, see e.g. "4") 🫣
Below from the proofs I just got. Looks like they placed all numbers by hand (and definitely not in the node center, see e.g. "4") 🫣
Again, it also just accepts defeat rather than engaging with the issue at hand: that we need to legislate these apps. It’s ridiculous I get ads for a product after a voice msg to my partner in another.
February 4, 2026 at 5:44 PM
Again, it also just accepts defeat rather than engaging with the issue at hand: that we need to legislate these apps. It’s ridiculous I get ads for a product after a voice msg to my partner in another.
Or we look at evidence first, then make rationale decisions. I haven’t seen convincing evidence to warrant blanket bans.
Bans will also be ineffective. I can stop my 14 yr old from driving and when they do I’ll know. Good luck doing that w a phone w/o taking away all your kids autonomy.
Bans will also be ineffective. I can stop my 14 yr old from driving and when they do I’ll know. Good luck doing that w a phone w/o taking away all your kids autonomy.
February 4, 2026 at 5:42 PM
Or we look at evidence first, then make rationale decisions. I haven’t seen convincing evidence to warrant blanket bans.
Bans will also be ineffective. I can stop my 14 yr old from driving and when they do I’ll know. Good luck doing that w a phone w/o taking away all your kids autonomy.
Bans will also be ineffective. I can stop my 14 yr old from driving and when they do I’ll know. Good luck doing that w a phone w/o taking away all your kids autonomy.
Please also keep in mind that bans do not change kids’ access to misinformation or nonsense, which is readily available anywhere else on the internet (blogs, podcasts. Fox “news” etc) or in everyday life (classrooms etc)
February 4, 2026 at 5:38 PM
Please also keep in mind that bans do not change kids’ access to misinformation or nonsense, which is readily available anywhere else on the internet (blogs, podcasts. Fox “news” etc) or in everyday life (classrooms etc)
Thanks André I’ll talk to my collaborators
February 4, 2026 at 5:35 PM
Thanks André I’ll talk to my collaborators
That’s just not true. Banning social media does nothing in that regard because the exactly same stuff is available on newspapers, magazines, school classes, blogs, podcasts etc kids can legally access after bans.
February 4, 2026 at 5:34 PM
That’s just not true. Banning social media does nothing in that regard because the exactly same stuff is available on newspapers, magazines, school classes, blogs, podcasts etc kids can legally access after bans.
You’re the best thanks
February 4, 2026 at 5:31 PM
You’re the best thanks
Drawing a parallel between social media and weapons / drugs seems problematic to me.
For cars, we legislated the hell out of car companies, with eg seatbelts and airbags for everybody, not just vulnerable people.
For cars, we legislated the hell out of car companies, with eg seatbelts and airbags for everybody, not just vulnerable people.
February 4, 2026 at 5:31 PM
Drawing a parallel between social media and weapons / drugs seems problematic to me.
For cars, we legislated the hell out of car companies, with eg seatbelts and airbags for everybody, not just vulnerable people.
For cars, we legislated the hell out of car companies, with eg seatbelts and airbags for everybody, not just vulnerable people.
Awesome! Any idea which of the scales could be a candidate for extracting qualitatively different classes (rather than your typical LCA situation where you get 'parallel' classes cutting categories into a dimension of severity).
February 4, 2026 at 11:06 AM
Awesome! Any idea which of the scales could be a candidate for extracting qualitatively different classes (rather than your typical LCA situation where you get 'parallel' classes cutting categories into a dimension of severity).
But other people are vulnerable too, not just young people. And I don't think I've seen serious efforts regulating social media in countries that introduced bans now (e.g. Australia) or are considering it (Spain, UK).
February 4, 2026 at 11:03 AM
But other people are vulnerable too, not just young people. And I don't think I've seen serious efforts regulating social media in countries that introduced bans now (e.g. Australia) or are considering it (Spain, UK).
Thanks for sharing — I'm not a parent so not feeling comfortable making this argument myself, but good to hear from folks w kids (and FWIW of course I agree)
February 4, 2026 at 11:02 AM
Thanks for sharing — I'm not a parent so not feeling comfortable making this argument myself, but good to hear from folks w kids (and FWIW of course I agree)
Thanks a ton. I have access to equally large mental health data I think, I'm just not sure I'd necessarily expect clustering of responses (e.g. "parents tend to answer in 3 different categories"). Any intuition on this?
February 4, 2026 at 11:01 AM
Thanks a ton. I have access to equally large mental health data I think, I'm just not sure I'd necessarily expect clustering of responses (e.g. "parents tend to answer in 3 different categories"). Any intuition on this?
If you truly believe that social media platforms are harmful places, the idea that the government now makes a list of vulnerable people and bans them from these platforms, e.g. based on age, is not a sensible or good faith solution.
Regulate the platforms instead, for everybody.
Regulate the platforms instead, for everybody.
February 4, 2026 at 8:32 AM
If you truly believe that social media platforms are harmful places, the idea that the government now makes a list of vulnerable people and bans them from these platforms, e.g. based on age, is not a sensible or good faith solution.
Regulate the platforms instead, for everybody.
Regulate the platforms instead, for everybody.
Thanks, good idea using large age ranges
February 2, 2026 at 9:34 PM
Thanks, good idea using large age ranges
... components/factors/dimensions I would find in a given sample and questionnaire compared to projection of the same data into person space. Clustering I've seen (mood & anxiety) are usually also just severity rather than qualitatively different, and we'd love qualitatively diff subgroups.
February 2, 2026 at 7:03 PM
... components/factors/dimensions I would find in a given sample and questionnaire compared to projection of the same data into person space. Clustering I've seen (mood & anxiety) are usually also just severity rather than qualitatively different, and we'd love qualitatively diff subgroups.
Thanks Hannah. I know some of these datasets (my 4 years postdoc were reanalyzing those data), but I wonder if anyone has a neat idea on a questionnaire where we expected fairly clear person-clustering (e.g. into 3 groups). I feel like I have a much better intuition on how many ...
February 2, 2026 at 7:02 PM
Thanks Hannah. I know some of these datasets (my 4 years postdoc were reanalyzing those data), but I wonder if anyone has a neat idea on a questionnaire where we expected fairly clear person-clustering (e.g. into 3 groups). I feel like I have a much better intuition on how many ...
Hi folks! For a methods validation paper, we're looking for a large, cross-sectional, psychometric dataset that will show considerable heterogeneity in item responses, preferably, based on different classes/clusters/groups of people. Open access optimal, but if you have one you'd share w me ...
February 2, 2026 at 6:28 PM
Hi folks! For a methods validation paper, we're looking for a large, cross-sectional, psychometric dataset that will show considerable heterogeneity in item responses, preferably, based on different classes/clusters/groups of people. Open access optimal, but if you have one you'd share w me ...
Breaking news: New Dutch cabinet reversing €1.5 billion in cuts to education and science
www.scienceguide.nl/2026/01/kabi...
www.scienceguide.nl/2026/01/kabi...
Kabinet-Jetten gaat met 1,5 miljard bezuinigingen op onderwijs en wetenschap terugdraaien - ScienceGuide
Voor investeringen in het onderwijs is door de nieuwe coalitie een envelop van structureel 1,5 miljard euro beschikbaar gesteld. Dit geld wordt onder andere besteed aan terugdraaien van de bezuiniging...
www.scienceguide.nl
January 30, 2026 at 12:59 PM
Breaking news: New Dutch cabinet reversing €1.5 billion in cuts to education and science
www.scienceguide.nl/2026/01/kabi...
www.scienceguide.nl/2026/01/kabi...
One month left for our ML competition to predict depression onset, in a massive dataset we collected over 5 years, including EMA and passive sensing data.
We have nearly 200 signups already, very excited to share our data and see who can fit the best models!
www.codabench.org/competitions...
We have nearly 200 signups already, very excited to share our data and see who can fit the best models!
www.codabench.org/competitions...
January 30, 2026 at 11:08 AM
One month left for our ML competition to predict depression onset, in a massive dataset we collected over 5 years, including EMA and passive sensing data.
We have nearly 200 signups already, very excited to share our data and see who can fit the best models!
www.codabench.org/competitions...
We have nearly 200 signups already, very excited to share our data and see who can fit the best models!
www.codabench.org/competitions...
Editorial by @astridchevance.bsky.social on censorship in academia.
Worth your time.
#AcademicSky #PsychSciSky 🧪
www.cambridge.org/core/journal...
Worth your time.
#AcademicSky #PsychSciSky 🧪
www.cambridge.org/core/journal...
Contemporary censors at work: targeting medical science to shape social reality | The British Journal of Psychiatry | Cambridge Core
Contemporary censors at work: targeting medical science to shape social reality - Volume 228 Issue 1
www.cambridge.org
January 30, 2026 at 9:30 AM
Editorial by @astridchevance.bsky.social on censorship in academia.
Worth your time.
#AcademicSky #PsychSciSky 🧪
www.cambridge.org/core/journal...
Worth your time.
#AcademicSky #PsychSciSky 🧪
www.cambridge.org/core/journal...
Reposted by Eiko Fried
New blog post introducing Causion - a web app for causal inference teaching and learning: pedermisager.org/blog/causion....
Introducing Causion: A web app for playing with DAGs | Peder M. Isager
Personal website of Dr. Peder M. Isager
pedermisager.org
January 28, 2026 at 9:23 AM
New blog post introducing Causion - a web app for causal inference teaching and learning: pedermisager.org/blog/causion....
Reposted by Eiko Fried
Comparing registrations to published papers is essential to research integrity - and almost no one does it routinely because it's slow, messy, and time-demanding.
RegCheck was built to help make this process easier.
Today, we launch RegCheck V2.
🧵
regcheck.app
RegCheck was built to help make this process easier.
Today, we launch RegCheck V2.
🧵
regcheck.app
RegCheck
RegCheck is an AI tool to compare preregistrations with papers instantly.
regcheck.app
January 22, 2026 at 11:05 AM
Comparing registrations to published papers is essential to research integrity - and almost no one does it routinely because it's slow, messy, and time-demanding.
RegCheck was built to help make this process easier.
Today, we launch RegCheck V2.
🧵
regcheck.app
RegCheck was built to help make this process easier.
Today, we launch RegCheck V2.
🧵
regcheck.app