That’s why I’m grateful R function names are case sensitive :-) tho I’m sure this would be considered cheating!

I'm trying to find examples of replicable mistakes by Chat GPT. I seem to recall there was a thread on here about common causal inference mistakes made by AI. Does anyone have a tip? #causalsky

Claude R Tidyverse Expert Claude R Tidyverse Expert. GitHub Gist: instantly share code, notes, and snippets.

Just read @sarahjohnson.io tidyverse skill - turns out I needed updating as much as Claude! gist.github.com/sj-io/3828d6...

I don't think there can be any consciousness without time. #randomshowerthoughts

Some of the creators of Claude or other LLMs assign a greater than 0% chance the LLM is conscious. Something as high as 20 to 80%. This would be ethically problematic but I don't think this is right. Claude is non-committal on the topic but it also says it doesn't experience the passage of time.

“A simple comparison of means, with credible random assignment, beats a complex structural model with doubtful exclusion restrictions” - favourite quote so far

Great read tho! Very nice overview

X can cause Y without correlation, but the article only describes 3 ways this can happen. There are more! Eg Y may be multidetermined so X (and W, and Z) causes Y but the correlation isn’t detectable in the presence of other causes (or spontaneous Y occurrences)

Causes can exist without correlation, but they are hard to detect without a true experiment

“Every student learns that correlation does not imply causation. Few learn the converse: absence of correlation does not imply absence of causation. Both mistakes are common in applied work, and understanding why reveals something fundamental about what causal inference requires.”

Optimizing Workplace Digital Mental Health Interventions: Systematic Review and Meta-Analysis Background: Digital mental health interventions (DMHIs) are widely used in workplaces to address common mental health conditions such as depression, anxiety, and stress. Their content and design vary ...

Mental health interventions are now digital but over 50% of the variance in effectiveness for stress is due to differences in design and features. Expert design is needed and throwing everything at the wall is not helpful: www.jmir.org/2025/1/e71253/

We are responding to this call for evidence:
ec.europa.eu/info/law/bet...

Do you have concrete examples of the added value of #Rstats in the public or private sectors?

Include the most important factors (risk, lock-in, security, innovation...) to assess the added value.

Thanks!

I’m in this tweet and I don’t like it

It's coming: bsky.app/profile/hype...

Are young Gen Z men today becoming both more disengaged (not in education, employment or training) and more likely to desire children? How would we square that circle?

tagging @rkwilkins.bsky.social because #HILDA is a great resource for fertility researchers but I don't know where to find them!

Is there something in the water of young men today?

facebook was listening... facebook is always listening

Would you like to look into Medicare claims for mental health support over COVID - I think subsidies were extended for extra psych visits but can’t find records or dates. Other subsidies or State-specific programs might have been provided as well. Could provide nice evidence for treatment efficacy

Rising trend in psychological distress among school-aged youth peaked in 2022, replotted from latest results of Mission Australia Youth Survey (2012-2025)

Latest data from Australia indicates mental ill-health among 15-19 year olds has already peaked. But what caused it to peak? And what caused it to turn around?

Indeed. It seems with sensible immigration policies (skill/education based perhaps) we could trust the market to distribute the population where it will be most productive and avoid most of the ill-effects of rapid decline

Does anyone else just surf LinkedIn hoping to find a job using R, Quarto, or Shiny? #rstats

That seems smart

That makes more sense than the ANCOVA to me. But my thinking is you want the effect of time because that is the only variable in the implicit DAG which is producing the change.

Devils advocate if there is no treatment group ANCOVA is the wrong choice. It answers if pre predicts post. You want if measure changes over time. Second model does that.

That's a tough decision to go through, but getting a PhD can sometimes be an albatross around your neck. It can be hard to know what the good and bad choices are while you are making them - bad luck now can look like a good choice in a few years time and we are all navigating by the rear view mirror

America is great when kids can't play soccer because the secret police may steal their parents

That’s what drove me to always declare the method!

plot provided by @Chris_said

Trend line plot showing major depressive episodes in US teenagers peaked in 2021 and have declined since then (Source data: National Survey on Drug Use and Health)

Major depressive episodes among US teenagers peaked in 2021 and have been declining since. More evidence challenging simplistic theories of teen mental health