Comic. [Sign above four people. A person sits at a desk working on a laptop. A person with ponytail is talking to person with white hat. A person with short hair walks away.] SIGN: It has been [-0.00000000000000044] days since our last floating point error

Day Counter

xkcd.com/3228/

GitHub - numbats/autoAlt Contribute to numbats/autoAlt development by creating an account on GitHub.

Are you interested in adding alt text to your publications? It helps share your data visualisations with vision impaired readers. Try out github.com/numbats/auto... to get a reasonable first draft or maybe complete text. @r-forwards.hachyderm.io.ap.brid.gy @rladies.org @rconsortium.bsky.social

RDM Weekly - Issue 021 A weekly roundup of Research Data Management resources.

RDM Weekly Issue 21 is out! 📬

- Project Structure slides @djnavarro.net
- AI TutoR @emilynordmann.bsky.social
- Data Documentation and Validation @lmu-osc.bsky.social
- Request for Reading Data @jessicatoste.bsky.social @emilyafarris.bsky.social
and more!

rdmweekly.substack.com/p/rdm-weekly...

The value of public R&D

Government has published one of those quiet but important documents that might get overlooked as it is not 'newsy'. The headline finding is that £1 of public R&D investment generates £8 in net economic benefits for the UK over the long term
www.gov.uk/government/p...

There still seems to be a lot of confusion about significance testing in psych. No, p-values *don’t* become useless at large N. This flawed point also used to be framed as "too much power". But power isn't the problem – it's 1) unbalanced error rates and 2) the (lack of a) SESOI. 1/ >

Thanks.

Causal inference interest group, supported by the Centre for Longitudinal Studies Seminar series 20th October 2025, 3pm BST (UTC+1) "Making rigorous causal inference more mainstream" Julia Rohrer, Leipzig University Sign up to attend at tinyurl.com/CIIG-JuliaRohrer

Happy to announce that I'll give a talk on how we can make rigorous causal inference more mainstream 📈

You can sign up for the Zoom link here: tinyurl.com/CIIG-JuliaRo...

Will a recording of this one be made available?

❗️Our next workshop will be on Oct 16th, 6 pm CEST titled Structural Bayesian Techniques for Experimental and Behavioral Economics in R& Stan by @jamesbland.bsky.social
Register or sponsor a student by donating to support Ukraine!
Details: bit.ly/3wBeY4S
Please share!
#AcademicSky #EconSky #RStats

Join us, and invite your siblings, as Quantitude gets Wild tomorrow…

Rookie scientists make research teams more innovative Papers from research teams with a substantial number of beginners are highly disruptive and innovative, study shows.

Beginner's charm 😊
Want to do disruptive #science? Papers from #research teams with a substantial number of beginners are highly disruptive and innovative, a new study shows. www.nature.com/articles/d41... @nature.com #ScienceCareer

Popularity of the first name Bo correlates with Zimmer Biomet Holdings' stock price (ZBH) (r=0.918)

In chess, everyone understands that a new player starts by learning the basics like how the pieces move.

In education, the same is true - but it's much less well understood.

Latest on our Substack - 3 things education can learn from chess.

substack.nomoremarking.com/p/three-thin...

Sample: I'm so random *holds up spork*

Balloon wall art inspired by the ggplot2 hex sticker. The display features a hexagonal frame made of black balloons, filled with white balloons inside and surrounded by a background of light and dark blue balloons. A line graph with black balloon segments and round coloured nodes runs across the centre, and the word “ggplot2” is spelled out in black balloon letters below the chart.

Happy 18th birthday ggplot2! #rstats

From Tool to Teammate: A Randomized Controlled Trial of Clinician-AI Collaborative Workflows for Diagnosis Early studies of large language models (LLMs) in clinical settings have largely treated artificial intelligence (AI) as a tool rather than an active collaborator. As LLMs now demonstrate expert-level ...

www.medrxiv.org/content/10.1...

Our vice-president for education & statistical literacy @sophiebays.bsky.social writes for OCR on why statistics is an essential life skill and why we need the curriculum updated to reflect this

Chaining Bayesian inference with priors constructed from posterior draws
statmodeling.stat.columbia.edu/2025/05/13/c...

#OTD 1918 Frank Anscombe b (d 17 Oct 2001) UK. ASA Fellow 1956. BIL of John Tukey. Best known for Anscombe's quartet, the most compelling argument ever made why data should be plotted before analysis. /3

The ASA has a book club! Follow the group on LinkedIn at www.linkedin.com/sho... and connect with other statisticians who share your love of reading. Upcoming book is "Talking to Strangers" by Malcolm Gladwell. Sign up by May 23. lnkd.in/eh6ey7iQ

Google searches for 'matt levine' correlates with The number of college administrators in Ohio (r=0.952)

This is getting lots of attention - check the thread. I want to emphasize the basic problem: Just because you have randomized (or pseudo-randmized) a treatment, that doesn't mean you can reliably estimate interactions with that treatment. Which means post-strat prediction for population not possible

This is really important. Do NOT use the AI summaries at the top of google searches. Ignore them. This is especially important if you don't have any prior knowledge about the topic, but also a good general rule.

Search sources, scrutinize them carefully and double-check with other sources.

Pencils of varying sizes underneath a fever chart.

The new issue of the "Journal of Statistics and Data Science Education" explores AI in teaching, experiential learning, Bayesian analysis in K–12, and more! Plus, a call for papers on AI in the classroom. www.tandfonline.com/toc/ujse20/c.... #DataScience #StatisticsEducation #AIinEducation

Best Practices for Data Visualisation Insights, advice, and examples (with code) to make data outputs more readable, accessible, and impactful

📊 Best Practices for Data Visualisation

By Andreas Krause, Nicola Rennie & Brian Tarran — A fantastic guide from the Royal Statistical Society on making clear, accessible, and impactful data visuals.

🔗 Read the guide: buff.ly/JEPX0Cb

More R resources 👉 buff.ly/MSQa1kh

#RStats #DataViz

👇 these workshops look great.

Dealing with Duplicate Data in R, April 25th

Smart Extraction: Converting PDF Tables into Usable Data with R, May 1st

Retrieving and Generating Data using LLMs in Python, May 8th

On June 13, we will have a workshop on Using LLMs by @hadley.nz
More info: bit.ly/4jmEAJW
Please share!
#RStats #EconSky #AcademicSky

Rethinking our approach to maths anxiety Farhana Gokhool, Anthea Cowen and Julie Hulme argue that distinguishing typical maths apprehension from clinical anxiety enables more effective support and inclusive teaching

Last week on Wonkhe: Farhana Gokhool, Anthea Cowen and Julie Hulme argue that distinguishing typical maths apprehension from clinical anxiety enables more effective support and inclusive teaching

>The earliest statisticians would spend hours thinking about their assumptions and models because the computations themselves might have taken days.

Today we call those people Bayesians

de Sitter xkcd.com/3077