E. David Klonsky, PhD
@klonskylab.bsky.social
Professor of Psychology at the University of British Columbia. Suicide, emotion, and personality research. Advocate for robust science. Also jiu-jitsu and combat sports 🤟🏼
Pinned
How to Produce, Identify, and Motivate Robust Psychological Science: A Roadmap and a Response to Vize et al
Some wish to mandate preregistration as a response to the replication crisis, while I and others caution that such mandates inadvertently cause harm and distract from more critical reforms. In this article, after briefly critiquing a recently ...
pmc.ncbi.nlm.nih.gov
Apropos of nothing, here's a brief paper of mine about how to make Psychological Science a robust and cumulative science. How to: 1) Produce findings likely to be robust, 2) Distinguish robust vs fragile findings, and 3) Motivate the field to use this knowledge.
pmc.ncbi.nlm.nih.gov/articles/PMC...
pmc.ncbi.nlm.nih.gov/articles/PMC...
Reposted by E. David Klonsky, PhD
Yeah...what René said!
Why aren't some of the strongest personality neuroscience papers getting widely cited?
November 5, 2025 at 8:46 PM
Yeah...what René said!
Reposted by E. David Klonsky, PhD
Once more, with feeling:
Jew hatred antedates modern constructions of wh*teness by literally thousands of years. It's cannot be understood or effectively countered solely in terms of contemporary racial politics.
Jew hatred antedates modern constructions of wh*teness by literally thousands of years. It's cannot be understood or effectively countered solely in terms of contemporary racial politics.
It seems like it may have been a mistake to conceptualize antisemitism as a subset of white supremacy, when there is consensus among many people who are *and aren't* white supremacists that Jews are the cause of all problems.
November 3, 2025 at 8:48 PM
Once more, with feeling:
Jew hatred antedates modern constructions of wh*teness by literally thousands of years. It's cannot be understood or effectively countered solely in terms of contemporary racial politics.
Jew hatred antedates modern constructions of wh*teness by literally thousands of years. It's cannot be understood or effectively countered solely in terms of contemporary racial politics.
Not sure where this is from, but assuming it’s right, there are clear implications for countering the replication crisis and “false positive” psychology: Insufficient sample sizes are a primary culprit, and should be a primary target of reforms.
lol; as statistical power goes up, effect sizes go down
November 4, 2025 at 3:21 AM
Not sure where this is from, but assuming it’s right, there are clear implications for countering the replication crisis and “false positive” psychology: Insufficient sample sizes are a primary culprit, and should be a primary target of reforms.
I really didn’t like the decision to sacrifice bunt Guerrero to 3rd. And it’s still bothering me. When you’re 3 outs from losing the Series, I don’t think you can give an out away.
November 2, 2025 at 4:37 AM
I really didn’t like the decision to sacrifice bunt Guerrero to 3rd. And it’s still bothering me. When you’re 3 outs from losing the Series, I don’t think you can give an out away.
1/2 Really appreciate this issue being centered. I prefer a reframe. NOT: Initial studies need replication. RATHER: Confidence in a conclusion increases to the extent it is supported by converging findings from multiple studies by multiple investigators across multiple samples and measures/methods.
I love asking the question: how much should be spent on scientific replication? When asked, I have suggested that 1-2% of a funding budget felt right. "Felt right" meaning no evidence basis other than intuition.
@jdworkin.bsky.social offers a much more thoughtful approach.
@jdworkin.bsky.social offers a much more thoughtful approach.
How Much Should We Spend on Scientific Replication? | IFP
A data-driven framework for targeting replication funding where it matters most
ifp.org
October 31, 2025 at 8:18 PM
1/2 Really appreciate this issue being centered. I prefer a reframe. NOT: Initial studies need replication. RATHER: Confidence in a conclusion increases to the extent it is supported by converging findings from multiple studies by multiple investigators across multiple samples and measures/methods.
Apropos of nothing, here's a brief paper of mine about how to make Psychological Science a robust and cumulative science. How to: 1) Produce findings likely to be robust, 2) Distinguish robust vs fragile findings, and 3) Motivate the field to use this knowledge.
pmc.ncbi.nlm.nih.gov/articles/PMC...
pmc.ncbi.nlm.nih.gov/articles/PMC...
How to Produce, Identify, and Motivate Robust Psychological Science: A Roadmap and a Response to Vize et al
Some wish to mandate preregistration as a response to the replication crisis, while I and others caution that such mandates inadvertently cause harm and distract from more critical reforms. In this article, after briefly critiquing a recently ...
pmc.ncbi.nlm.nih.gov
October 29, 2025 at 3:16 AM
Apropos of nothing, here's a brief paper of mine about how to make Psychological Science a robust and cumulative science. How to: 1) Produce findings likely to be robust, 2) Distinguish robust vs fragile findings, and 3) Motivate the field to use this knowledge.
pmc.ncbi.nlm.nih.gov/articles/PMC...
pmc.ncbi.nlm.nih.gov/articles/PMC...
Reposted by E. David Klonsky, PhD
From this new post by OpenAI: 0.15% of users (something like 9M people given public numbers) show signs of suicidal intent in their ChatGPT chats each week
But there seems to be progress in making ChatGPT respond appropriately to mental health issues. openai.com/index/streng...
But there seems to be progress in making ChatGPT respond appropriately to mental health issues. openai.com/index/streng...
October 28, 2025 at 4:40 AM
From this new post by OpenAI: 0.15% of users (something like 9M people given public numbers) show signs of suicidal intent in their ChatGPT chats each week
But there seems to be progress in making ChatGPT respond appropriately to mental health issues. openai.com/index/streng...
But there seems to be progress in making ChatGPT respond appropriately to mental health issues. openai.com/index/streng...
Very cool issue on intensive longitudinal data, including a piece by @aidangcw.bsky.social and others on minimum sample size for estimating various parameters. Sometimes when we move beyond traditional self-report we neglect psychometrics and publish lots of noise. This work can help prevent that.
Interesting new special issue in Psychological Assessment.
Edited by Kristin Naragon-Gainey and @kstanton.bsky.social
Here's their overview paper: psycnet.apa.org/record/2026-...
And here's our contribution, which will win us no friends:
psycnet.apa.org/record/2026-...
Edited by Kristin Naragon-Gainey and @kstanton.bsky.social
Here's their overview paper: psycnet.apa.org/record/2026-...
And here's our contribution, which will win us no friends:
psycnet.apa.org/record/2026-...
October 25, 2025 at 3:00 AM
Very cool issue on intensive longitudinal data, including a piece by @aidangcw.bsky.social and others on minimum sample size for estimating various parameters. Sometimes when we move beyond traditional self-report we neglect psychometrics and publish lots of noise. This work can help prevent that.
I think robustness checks should be a standard part of every Results section. I also agree they should be 'thoughtful', not 'brute force' multiverse. But it shouldn't only be authors who choose the robustness checks -- also the reviewers pre-publication, and the field post-publication.
October 23, 2025 at 8:36 PM
I think robustness checks should be a standard part of every Results section. I also agree they should be 'thoughtful', not 'brute force' multiverse. But it shouldn't only be authors who choose the robustness checks -- also the reviewers pre-publication, and the field post-publication.
Things are scary.
October 23, 2025 at 4:18 AM
Things are scary.
I think it’s underappreciated in psychology that we establish generalizability of an effect not through some near-perfect ‘representative’ sample — but to the extent it consistently occurs across many different unrepresentative samples that vary demographically/culturally/etc.
"Representative sample" is a flawed, ambiguous concept and it does not have a precise definition in the technical literature of survey sampling, so you should avoid using it at all costs.
/TheEnd
/TheEnd
October 22, 2025 at 3:06 PM
I think it’s underappreciated in psychology that we establish generalizability of an effect not through some near-perfect ‘representative’ sample — but to the extent it consistently occurs across many different unrepresentative samples that vary demographically/culturally/etc.
There really are a ton of fascinating pieces in this issue! Topics include metascience, constructs & measurement, and LLMs. Particularly intrigued by the one on using LLMs for psych assessment — for curiosity I periodically have an LLM assess me in various psych domains, and it’s surprisingly good 😳
Papers from July to Sept 2025 at AMPPS are killer. We don't have formal print issues, but we have this-- journals.sagepub.com/toc/ampa/8/3
Advances in Methods and Practices in Psychological Science - Volume 8, Number 3
Table of contents for Advances in Methods and Practices in Psychological Science, 8, 3
journals.sagepub.com
October 21, 2025 at 9:30 PM
There really are a ton of fascinating pieces in this issue! Topics include metascience, constructs & measurement, and LLMs. Particularly intrigued by the one on using LLMs for psych assessment — for curiosity I periodically have an LLM assess me in various psych domains, and it’s surprisingly good 😳
As Trump et al. try to destroy democracy, this is one of the most important movements in American history. 🙏❤️ #NoKings
The is literally nothing more American and patriotic than declaring: No Kings.
October 17, 2025 at 7:38 PM
As Trump et al. try to destroy democracy, this is one of the most important movements in American history. 🙏❤️ #NoKings
Reposted by E. David Klonsky, PhD
In 2018, Charles Murray challenged me to a bet: "We will understand IQ genetically—I think most of the picture will have been filled in by 2025—there will still be blanks—but we’ll know basically what’s going on." It's now 2025, and I claim a win. I write about it in The Atlantic.
Your Genes Are Simply Not Enough to Explain How Smart You Are
Seven years ago, I took a bet with Charles Murray about whether we’d basically understand the genetics of intelligence by now.
www.theatlantic.com
October 13, 2025 at 1:33 PM
In 2018, Charles Murray challenged me to a bet: "We will understand IQ genetically—I think most of the picture will have been filled in by 2025—there will still be blanks—but we’ll know basically what’s going on." It's now 2025, and I claim a win. I write about it in The Atlantic.
Reposted by E. David Klonsky, PhD
Portland is so good at trolling these fascists.
I ❤️ Portland
I ❤️ Portland
October 9, 2025 at 4:52 AM
Portland is so good at trolling these fascists.
I ❤️ Portland
I ❤️ Portland
Reposted by E. David Klonsky, PhD
Pritzker: "He wants to militarize major cities because he wants us to get used to the idea of troops on the streets. I believe he's gonna post people outside of polling places and if he needs to in order to control those elections, he'll assume control of the ballot boxes & count the votes himself"
October 8, 2025 at 5:41 PM
Pritzker: "He wants to militarize major cities because he wants us to get used to the idea of troops on the streets. I believe he's gonna post people outside of polling places and if he needs to in order to control those elections, he'll assume control of the ballot boxes & count the votes himself"
Reposted by E. David Klonsky, PhD
My blog has moved! It’s now at sometimesimwrongblog.wordpress.com If you have links to posts in your syllabus, let me know if you have any trouble finding the corresponding post!
October 7, 2025 at 7:49 PM
My blog has moved! It’s now at sometimesimwrongblog.wordpress.com If you have links to posts in your syllabus, let me know if you have any trouble finding the corresponding post!
In lighter news, the game between the 49ers and Rams was incredible. Mac Jones is physically and mentally tough as nails. And Kyle Shanahan is a special kind of quarterback whisperer.
October 3, 2025 at 6:06 AM
In lighter news, the game between the 49ers and Rams was incredible. Mac Jones is physically and mentally tough as nails. And Kyle Shanahan is a special kind of quarterback whisperer.
Reposted by E. David Klonsky, PhD
Donald Trump's militarization of our city streets isn't about fighting crime or public safety — it's about consolidating power in his hands.
What he plans to do with that, now or during the 2026 elections, should worry all of us.
What he plans to do with that, now or during the 2026 elections, should worry all of us.
September 30, 2025 at 1:35 AM
Donald Trump's militarization of our city streets isn't about fighting crime or public safety — it's about consolidating power in his hands.
What he plans to do with that, now or during the 2026 elections, should worry all of us.
What he plans to do with that, now or during the 2026 elections, should worry all of us.
Sarah is a great person in addition to a superb scholar. Apply to her lab!
I am barely on this app, because of *gestures wildly* life, the universe, and everything, but I should announce that I plan to review apps for clinical psychology PhD admissions this cycle! Please read my website for more info! www.sarahevictor.com/contact
Contact & Apply | Sarah Victor, PhD | United States
Information on how to reach TRTL and how to join the lab.
www.sarahevictor.com
September 25, 2025 at 7:18 PM
Sarah is a great person in addition to a superb scholar. Apply to her lab!
Agree. Odds ratios are a great effect size when you want to: make a small effect look meaningful, report a metric that defies intuitive understanding, or use a metric that will be hard to integrate with other effect sizes in a metanalysis. In short, they are stupid.
September 25, 2025 at 1:28 AM
Agree. Odds ratios are a great effect size when you want to: make a small effect look meaningful, report a metric that defies intuitive understanding, or use a metric that will be hard to integrate with other effect sizes in a metanalysis. In short, they are stupid.
I thought I had built in plenty of time to submit my finalized grant application to @sshrc-crsh.canada.ca, but now it's my third consecutive day trying to upload my documents and the site still won't let me. When do we panic?
September 24, 2025 at 10:42 PM
I thought I had built in plenty of time to submit my finalized grant application to @sshrc-crsh.canada.ca, but now it's my third consecutive day trying to upload my documents and the site still won't let me. When do we panic?
Reposted by E. David Klonsky, PhD
It’s actually very sad to see that risk prediction has never gone away, despite so much evidence demonstrating how awful we are at predicting suicide and its related outcomes. This is an incredibly important piece of work that we should all read.
Extremely important work by Matt Spittal, @oliviajkirtley.bsky.social and other colleagues published this week!
journals.plos.org/plosmedicine...
journals.plos.org/plosmedicine...
September 20, 2025 at 3:18 PM
It’s actually very sad to see that risk prediction has never gone away, despite so much evidence demonstrating how awful we are at predicting suicide and its related outcomes. This is an incredibly important piece of work that we should all read.
The FCC getting Jimmy Kimmel taken off the air is chilling — especially so soon after Trump said Kimmel was a target. Another step further from ‘land of the free’. The US we knew is ending. Or ended.
September 17, 2025 at 11:27 PM
The FCC getting Jimmy Kimmel taken off the air is chilling — especially so soon after Trump said Kimmel was a target. Another step further from ‘land of the free’. The US we knew is ending. Or ended.