Or Duek
@orduek.bsky.social
Assistant Prof. at Ben-Gurion Univesity / Adjunct at Yale
#Pych, #Bayes, #Neuro #publichealth
orduek.github.io
#Pych, #Bayes, #Neuro #publichealth
orduek.github.io
Reposted by Or Duek
I am just learning of this 2015 retraction, adding to my "science as amateur software engineering" files. Seems they classified missing values as obs outcome of interest (divorce). Classified 32% of sample divorced, rather than true 5%. retractionwatch.com/2015/07/21/t...
December 18, 2025 at 9:06 AM
I am just learning of this 2015 retraction, adding to my "science as amateur software engineering" files. Seems they classified missing values as obs outcome of interest (divorce). Classified 32% of sample divorced, rather than true 5%. retractionwatch.com/2015/07/21/t...
Reposted by Or Duek
**How do we make long-lasting emotional memories**
Looks very interesting.
#neuroskyence
www.science.org/doi/10.1126/...
Looks very interesting.
#neuroskyence
www.science.org/doi/10.1126/...
December 13, 2025 at 7:06 PM
**How do we make long-lasting emotional memories**
Looks very interesting.
#neuroskyence
www.science.org/doi/10.1126/...
Looks very interesting.
#neuroskyence
www.science.org/doi/10.1126/...
Reposted by Or Duek
I'm teaching Statistical Rethinking again starting Jan 2026. This time with live lectures, divided into Beginner and Experienced sections. Will be a lot more work for me, but I hope much better for students.
I will record lectures & all will be found at this link: github.com/rmcelreath/s...
I will record lectures & all will be found at this link: github.com/rmcelreath/s...
December 9, 2025 at 1:58 PM
I'm teaching Statistical Rethinking again starting Jan 2026. This time with live lectures, divided into Beginner and Experienced sections. Will be a lot more work for me, but I hope much better for students.
I will record lectures & all will be found at this link: github.com/rmcelreath/s...
I will record lectures & all will be found at this link: github.com/rmcelreath/s...
Reposted by Or Duek
Nature Scientific Reports is the third most cited journal in the world smdh
November 27, 2025 at 7:48 AM
Nature Scientific Reports is the third most cited journal in the world smdh
Reposted by Or Duek
This is another example of why I think default priors are generally inappropriate for professional work. They're still great for teaching, though.
The default prior for the intercept in both {rstanarm} and {brms} are very wide.
Counterintuitively - being on the logit scale, this is actually translates to a **strong** prior that p(y=1) is near 1 or near 0.
Always check your priors!
#rstats
Counterintuitively - being on the logit scale, this is actually translates to a **strong** prior that p(y=1) is near 1 or near 0.
Always check your priors!
#rstats
November 18, 2025 at 3:44 PM
This is another example of why I think default priors are generally inappropriate for professional work. They're still great for teaching, though.
Reposted by Or Duek
I wrote something about publication bias at statmodeling.stat.columbia.edu/2025/11/14/t...
November 14, 2025 at 9:17 PM
I wrote something about publication bias at statmodeling.stat.columbia.edu/2025/11/14/t...
Reposted by Or Duek
Many brain imaging “biomarkers” for autism have been proposed. Most aim for balanced accuracy (matching sensivity/specificity) on datasets where cases and controls are split 50/50. 1/🧵
September 8, 2025 at 1:59 PM
Many brain imaging “biomarkers” for autism have been proposed. Most aim for balanced accuracy (matching sensivity/specificity) on datasets where cases and controls are split 50/50. 1/🧵
Reposted by Or Duek
If you read my thread, make sure to read the retracted paper’s last author’s response. As I highlighted on pubpeer & my thread, authors have been very responsive, transparent & collegial all the way through. I was surprised myself seeing a retraction as I had asked for a correction.
Hi I’m the last author of the retracted study; the first author is my PhD student. I don’t disagree with the retraction note. However, it missed out on some important context that I had written in my author’s response, which was not published with the retraction note. Here’s my side of the story
July 18, 2025 at 3:28 PM
If you read my thread, make sure to read the retracted paper’s last author’s response. As I highlighted on pubpeer & my thread, authors have been very responsive, transparent & collegial all the way through. I was surprised myself seeing a retraction as I had asked for a correction.
Reposted by Or Duek
🚨 Big News! Our research has been featured in The New York Times @nytimes.com! 🥳
This engagement highlights the real-world impact of science beyond academia and its role in shaping conversations on AI & mental health.
🔗 Link: www.nytimes.com/2025/03/17/science/chatgpt-digital-therapists-anxiety.html
This engagement highlights the real-world impact of science beyond academia and its role in shaping conversations on AI & mental health.
🔗 Link: www.nytimes.com/2025/03/17/science/chatgpt-digital-therapists-anxiety.html
Digital Therapists Get Stressed Too, Study Finds
Chatbots should be built with enough resilience to deal with difficult emotional situations, researchers said.
www.nytimes.com
March 17, 2025 at 5:18 PM
🚨 Big News! Our research has been featured in The New York Times @nytimes.com! 🥳
This engagement highlights the real-world impact of science beyond academia and its role in shaping conversations on AI & mental health.
🔗 Link: www.nytimes.com/2025/03/17/science/chatgpt-digital-therapists-anxiety.html
This engagement highlights the real-world impact of science beyond academia and its role in shaping conversations on AI & mental health.
🔗 Link: www.nytimes.com/2025/03/17/science/chatgpt-digital-therapists-anxiety.html
Reposted by Or Duek
Tenured-research position opened here in Paris : A great opportunity to leverage the full potential of the new 11.7T MRI scanner at Neurospin @inserm.fr @cea.fr @unicog.bsky.social
🧠🟦 / 🧠🤖 / 🧠🩺
#AcademicSky
🧠🟦 / 🧠🤖 / 🧠🩺
#AcademicSky
March 15, 2025 at 9:23 AM
Tenured-research position opened here in Paris : A great opportunity to leverage the full potential of the new 11.7T MRI scanner at Neurospin @inserm.fr @cea.fr @unicog.bsky.social
🧠🟦 / 🧠🤖 / 🧠🩺
#AcademicSky
🧠🟦 / 🧠🤖 / 🧠🩺
#AcademicSky
Reposted by Or Duek
my team at MidJourney is looking to hire an experienced full-stack (but with emphasis on the frontend) developer to work on various personality-related projects. if you're interested, or know someone else who is, DM me a resume and/or a link to some of your previous work!
March 14, 2025 at 12:13 AM
my team at MidJourney is looking to hire an experienced full-stack (but with emphasis on the frontend) developer to work on various personality-related projects. if you're interested, or know someone else who is, DM me a resume and/or a link to some of your previous work!
Reposted by Or Duek
🚨 New Publication Alert! 🚨
1/ Can early brain connectivity predict who will develop PTSD after trauma? 🧠🔍 Check out our new study, published today in JAMA Network Open!
jamanetwork.com/journals/jam...
@orduek.bsky.social @ifatlevy.bsky.social
@harpaz-rotem.bsky.social
🧠🧵👇
1/ Can early brain connectivity predict who will develop PTSD after trauma? 🧠🔍 Check out our new study, published today in JAMA Network Open!
jamanetwork.com/journals/jam...
@orduek.bsky.social @ifatlevy.bsky.social
@harpaz-rotem.bsky.social
🧠🧵👇
March 11, 2025 at 9:40 PM
🚨 New Publication Alert! 🚨
1/ Can early brain connectivity predict who will develop PTSD after trauma? 🧠🔍 Check out our new study, published today in JAMA Network Open!
jamanetwork.com/journals/jam...
@orduek.bsky.social @ifatlevy.bsky.social
@harpaz-rotem.bsky.social
🧠🧵👇
1/ Can early brain connectivity predict who will develop PTSD after trauma? 🧠🔍 Check out our new study, published today in JAMA Network Open!
jamanetwork.com/journals/jam...
@orduek.bsky.social @ifatlevy.bsky.social
@harpaz-rotem.bsky.social
🧠🧵👇
Reposted by Or Duek
🚀 Just 5 days since publication, our paper is already the #1 trending article on @natureportfolio.nature.com npj Digital Medicine! 🥳
🤖 Check out how we induced anxiety in Chat-GPT using traumatic narratives - then calmed it down with mindfulness & meditation: www.nature.com/articles/s41... 📝
🤖 Check out how we induced anxiety in Chat-GPT using traumatic narratives - then calmed it down with mindfulness & meditation: www.nature.com/articles/s41... 📝
March 8, 2025 at 1:45 PM
🚀 Just 5 days since publication, our paper is already the #1 trending article on @natureportfolio.nature.com npj Digital Medicine! 🥳
🤖 Check out how we induced anxiety in Chat-GPT using traumatic narratives - then calmed it down with mindfulness & meditation: www.nature.com/articles/s41... 📝
🤖 Check out how we induced anxiety in Chat-GPT using traumatic narratives - then calmed it down with mindfulness & meditation: www.nature.com/articles/s41... 📝
Reposted by Or Duek
🚨New Paper Alert! Our latest research in npj Digital Medicine explores two unusual questions:
1⃣ Can Chat-GPT experience state anxiety?💥🤖
2⃣ If so, can we reduce it? 📉
A thread on how we "took Chat-GPT to therapy" 🧵👇
Full text available here: rdcu.be/ebZ9v
1⃣ Can Chat-GPT experience state anxiety?💥🤖
2⃣ If so, can we reduce it? 📉
A thread on how we "took Chat-GPT to therapy" 🧵👇
Full text available here: rdcu.be/ebZ9v
March 3, 2025 at 8:38 PM
🚨New Paper Alert! Our latest research in npj Digital Medicine explores two unusual questions:
1⃣ Can Chat-GPT experience state anxiety?💥🤖
2⃣ If so, can we reduce it? 📉
A thread on how we "took Chat-GPT to therapy" 🧵👇
Full text available here: rdcu.be/ebZ9v
1⃣ Can Chat-GPT experience state anxiety?💥🤖
2⃣ If so, can we reduce it? 📉
A thread on how we "took Chat-GPT to therapy" 🧵👇
Full text available here: rdcu.be/ebZ9v
Reposted by Or Duek
Here are some cool animations I made a couple years ago for teaching DAG-based causal inference
Confounding!
Confounding!
February 20, 2025 at 9:40 PM
Here are some cool animations I made a couple years ago for teaching DAG-based causal inference
Confounding!
Confounding!
Reposted by Or Duek
Week 6 in my Bayes stats course, we finally arrive at multilevel models. For those who know the basics, there is also a BONUS lesson on group confounding and Mundlak Machines, incl a latent Bayesian variety. Lecture link set to start of BONUS content: www.youtube.com/watch?v=iwVq...
February 13, 2025 at 8:16 AM
Week 6 in my Bayes stats course, we finally arrive at multilevel models. For those who know the basics, there is also a BONUS lesson on group confounding and Mundlak Machines, incl a latent Bayesian variety. Lecture link set to start of BONUS content: www.youtube.com/watch?v=iwVq...
Reposted by Or Duek
Interesting point - disorders allow many combinations of symptoms, but many combinations of symptoms don't tend to show up at all: jamanetwork.com/journals/jam...
Unveiling the Structure in Mental Disorder Presentations
This cross-sectional study examines 4 preexisting datasets to determine how symptom-based definitions and assessments contribute to a distinct probability pattern for the occurrence of symptom combina...
jamanetwork.com
November 18, 2024 at 8:31 PM
Interesting point - disorders allow many combinations of symptoms, but many combinations of symptoms don't tend to show up at all: jamanetwork.com/journals/jam...
Reposted by Or Duek
Since it is inefficient to attempt to educate every reviewer individually, I am yeeting into your feed this clear paper from Gelman, Hill, and Yajima on how Bayesians can do even better than correcting for multiple comparisons. arxiv.org/abs/0907.2478
Why we (usually) don't have to worry about multiple comparisons
Applied researchers often find themselves making statistical inferences in settings that would seem to require multiple comparisons adjustments. We challenge the Type I error paradigm that underlies t...
arxiv.org
November 26, 2024 at 9:11 AM
Since it is inefficient to attempt to educate every reviewer individually, I am yeeting into your feed this clear paper from Gelman, Hill, and Yajima on how Bayesians can do even better than correcting for multiple comparisons. arxiv.org/abs/0907.2478
Reposted by Or Duek
New large study (n ~ 6 million) in @JAMApsych tracking mental disorder trends in Denmark showing increases in mood disorders in recent birth cohorts tinyurl.com/c5nyfd8k
November 27, 2024 at 9:08 PM
New large study (n ~ 6 million) in @JAMApsych tracking mental disorder trends in Denmark showing increases in mood disorders in recent birth cohorts tinyurl.com/c5nyfd8k
Reposted by Or Duek
Causal methods peeps. Can you point me to a good intro reading on DAGs? Something more easily digestible than Pearl's primary papers but more technical than the kinds of 30,000-ft summaries you get from a Google search.
November 24, 2024 at 7:42 PM
Causal methods peeps. Can you point me to a good intro reading on DAGs? Something more easily digestible than Pearl's primary papers but more technical than the kinds of 30,000-ft summaries you get from a Google search.
Reposted by Or Duek
Anscombe's quartet illustrates how datasets can have nearly identical descrptv stats but different distributions
@lucystats.bsky.social proposed the "Causal Quartet" datasets all with the same statistical summaries & dataviz but different true causal effects livefreeordichotomize.com/posts/2023-0...
@lucystats.bsky.social proposed the "Causal Quartet" datasets all with the same statistical summaries & dataviz but different true causal effects livefreeordichotomize.com/posts/2023-0...
October 2, 2023 at 1:27 PM
Anscombe's quartet illustrates how datasets can have nearly identical descrptv stats but different distributions
@lucystats.bsky.social proposed the "Causal Quartet" datasets all with the same statistical summaries & dataviz but different true causal effects livefreeordichotomize.com/posts/2023-0...
@lucystats.bsky.social proposed the "Causal Quartet" datasets all with the same statistical summaries & dataviz but different true causal effects livefreeordichotomize.com/posts/2023-0...
Reposted by Or Duek
Very excited about this new preprint in which we solve one of the main issues in network psychometrics: estimating symptom networks in clinically severe populations. This solution is now available in the bootnet, IsingFit, IsingSampler and psychonetrics #Rstats packages! osf.io/xq8ur/
October 6, 2023 at 6:56 AM
Very excited about this new preprint in which we solve one of the main issues in network psychometrics: estimating symptom networks in clinically severe populations. This solution is now available in the bootnet, IsingFit, IsingSampler and psychonetrics #Rstats packages! osf.io/xq8ur/
Reposted by Or Duek
The Journal of Psychopathology and Clinical Science is looking for 4 Editorial Fellows (EFs) for the 2024 calendar year. EFs are a PAID mentored position intended to give individuals from underrepresented backgrounds frontline editorial experience. Ad attached
www.apa.org/pubs/journal...
1/3
www.apa.org/pubs/journal...
1/3
October 5, 2023 at 12:21 AM
The Journal of Psychopathology and Clinical Science is looking for 4 Editorial Fellows (EFs) for the 2024 calendar year. EFs are a PAID mentored position intended to give individuals from underrepresented backgrounds frontline editorial experience. Ad attached
www.apa.org/pubs/journal...
1/3
www.apa.org/pubs/journal...
1/3
Reposted by Or Duek
We are hiring at the University of Michigan Depression Denter.
The goal is clear. Move the needle on improving mental health. But the task is hard. So we are building a multidisciplinary team. Positions are open at all ranks and in any relevant discipline.
depressioncenter.org/about/facult...
The goal is clear. Move the needle on improving mental health. But the task is hard. So we are building a multidisciplinary team. Positions are open at all ranks and in any relevant discipline.
depressioncenter.org/about/facult...
October 3, 2023 at 11:52 PM
We are hiring at the University of Michigan Depression Denter.
The goal is clear. Move the needle on improving mental health. But the task is hard. So we are building a multidisciplinary team. Positions are open at all ranks and in any relevant discipline.
depressioncenter.org/about/facult...
The goal is clear. Move the needle on improving mental health. But the task is hard. So we are building a multidisciplinary team. Positions are open at all ranks and in any relevant discipline.
depressioncenter.org/about/facult...