Excited to share my recent first-author publication! Does EMA impact the use of alcohol and sexual assault protective behaviors among college women? Click below to find out! psycnet.apa.org/doiLanding?d...

Can you guess what happened when Denmark doubled the amount of parental leave parents could take? ... ... ... Intimate partner violence declined as a direct result.

so no one wanted to tell me this is what it feels like to be a doc candidate ????

I’ve watched Sam give two talks about this topic (once as a first year grad student which was extremely formative for my research trajectory). Very excited to see this in print!

In a new paper, my colleagues and I set out to demonstrate how method biases can create spurious findings in relationship science, by using a seemingly meaningless scale (e.g., "My relationship has very good Saturn") to predict relationship outcomes. journals.sagepub.com/doi/10.1177/...

Sure, why not

For those interested in reading my article: pubmed.ncbi.nlm.nih.gov/36736052/

🚨New Paper Alert🚨 Just published in AJCP - one of my students and I (along with an awesome team of collaborators) explored the ostensible impact of historic redlining practices on contemporary violence exposure risk of adolescents living in those communities. Data and code here: osf.io/ekxmf/

Pachinko is a fantastic book and this clap black is delicious.

In much better news: after our fury, HHS says “We are now working to fully restore funding to” the Women's Health Initiative. Sharing the gift article. Reminding us all that we're in 'announcements about announcements' territory, but let's keep close eye on this. www.nytimes.com/2025/04/24/h...

Biggest commitment to a 3 second joke I've ever seen

Speaking up takes many forms. I’m mindful that people do so offline and we may not alway see the work people do behind the scene. Not everyone is comfortable with public social media platforms. But we must all resist the growing fascism in this country however we can.

BREAKING: Kim Davis, the Kentucky clerk who refused to issue same-sex couples' marriage licenses, loses her appeal at the Sixth Circuit of a lawsuit she lost at trial that was brought by same-sex couples whose constitutional right to marry she violated. storage.courtlistener.com/recap/gov.us...

Congratulations to Rich Sutton and Andrew Barto on receiving the Turing Award in recognition of their significant contributions to ML. I also stand with them: Releasing models to the public without the right technical and societal safeguards is irresponsible. www.ft.com/content/d8f8...

Mental health misinformation is rampant on social media. In our new study, 33% of top viewed TikTok videos that offered advice and information were misleading. These videos were watched over 1 billion times. journals.sagepub.com/doi/epub/10.... @srmarcon.bsky.social @marcozenone.bsky.social

I included these slides in a talk recently. I think it went well? #SPSP2025 #spspcloserels

Easily popped up at my 3:15 alarm … what was that all about …

BREAKING On Monday, Popular Information broke the news that the NIH had frozen virtually all grant funding in violation of 2 federal court orders On Wednesday, NIH leadership distributed a memo, acknowledging that its funding freeze was illegal and directing staff to resume issuing grants.

The absolute whiplash of meeting with grad school applicants to attending a protest to sitting in a statistics class is A Lot to handle on this fine Wednesday …

This isn't mine at all, but the Magic School Bus TV cartoon, which inspired untold millennials including myself, originated as an NSF grant 🧪 www.nsf.gov/awardsearch/...

Bad news: my Deep Learning homework takes so long to run Good news: I found several new songs that I really like

Many great points in this piece about PTSD disinformation Misrepresenting research in a way that discourages ppl from seeking effective care is extremely harmful Existing evidence-based options for PTSD aren’t perfect & often require flexing to meet individual needs. But they _do_ work

my least favorite part of grad school is 100% the graphic design portion

www.bostonglobe.com/2024/11/20/m...

CU Boulder must pay 386 women faculty back pay for gender discrimination.

Blog on our new JoPACS viewpoint led by @molthof.bsky.social, highlighting problems of ignoring socio-environmental causes for psychopathology, using the example of the p-factor for which all dominant theories position liability *within* the person. eiko-fried.com/causes-of-me...

Does anyone have any advice for overcoming a writer’s block? Asking for a friend, of course….

No meta-analytic link between heart-rate variability and aggression. onlinelibrary.wiley.com/doi/10.1002/...

slowly dragging myself out of a bit of a slump and getting back to writing and designing studies … YAYYYY

As part of an undergrad’s development in our lab, I’ve been having individual meetings with her to teach intro grad-level stats (think “what is the general linear model, why do we use it, and when should we not use it”). seeing someone “get it” in real-time is one of the coolest feelings ever

If you’re going to SSSP next weekend, I’ll be sitting on the Graduate Student Panel. I would love to see you there!

in any other medical context, results like this would qualify as a miracle - you just don't see this level of satisfaction even with completely uncontroversial, common medical treatments there is simply no serious good faith argument that gender-affirming care hurts people - the opposite is true

A survey of more than 200 transgender and nonbinary youth who received gender-affirming medical care shows they were largely satisfied with the treatments they received, according to a study published Monday in JAMA Pediatrics.

Preregistration Deviations Psychologists are more likely to identify deviations in psychology preregistrations than are open science experts. doi.org/10.1002/pra2... #MetaSci 🧪

The only thing more difficult than submitting a F31 is revising the application for resubmission and I’ll die on that hill

Lancet Commission on Self-Harm: No significant link between social media and youth mental illness. Broader issues like poverty and inequality have impact. A call to action address root causes—not just blame social media or hide it from kids. We should harness it! www.thelancet.com/journals/lan...

Deceiving Only Ourselves? The Assessment and Exclusion of 'Suspicion' is Linked to Lower Quality of Psychological Evidence: http://osf.io/aupbd/

New pre-print with my advisor @davidchester.bsky.social !! In this quasi-experimental meta-analysis, we assessed the evidentiary value of studies that employed a ‘suspicion’ probe and studies that did not! Thread below :-)

A study measured the performance of 800 developers before and after getting GitHub's Copilot. It found: - No change in productivity - No change in burnout levels - A 41% increase in the bug rate!?? Aren't you thrilled we're burning the world to power these AI models?

Is the retraction a win and final proof of the effectiveness of preregistration? Or proof, once and for all, that open science is all bullshit? Neither. It's just a hugely disappointing error.

I'm a huge fan of most open science reforms, but it's always disturbing to see members of that community engaging in many of the same shenanigans and practices they disavow. For starters, they need to be more open to criticism. They mistreated 3 critics who were spot on here.

I just wrote 51 pages in 48 hours … comps are halfway over!

All three books I've co-authored are freely available online for non-commercial use: - #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/ - #Regression and Other Stories at avehtari.github.io/ROS-Examples/ - Active Statistics at avehtari.github.io/ActiveStatis...

My students in Research Methods can submit memes for extra credit and there have been some real bangers so far.

We had subjects complete a task in which they had to choose whether a positive vs. negative trait word better described themselves or a close friend. We then used hierarchical Bayesian drift diffusion modeling to decompose the decision processes.

📊When teaching or giving a talk, do you like presenting plots step by step, revealing e.g. one group at a time? This is often useful for walking through complex results. I made a R package that makes it extremely easy to do this! ggreveal: Reveal a ggplot incrementally #rstats #dataviz #ggplot2