Francisco Rodriguez-Sanchez

3/ If using AI, I want people to learn from it. So I'm increasingly asking questions like

What is the code doing here?
How do you know it's correct?
How have you checked it?
How could it fail?
And how could you make it more robust to failure?

2/ Many people use AI to just get things done, without really understanding the output. I'm seeing this a lot around (not only students). It's fast but you learn nothing. It's somewhat risky. And it's a problem if you then have to debug

How AI assistance impacts coding speed and skill formation

This is quite interesting, with implications for #teaching.

AI can make you work faster or slower, learn nothing or a lot, depending on how you use it

www.anthropic.com/research/AI-...

1/

Rare, dangerous side effects of some COVID-19 vaccines explained “Groundbreaking” study uncovers why adenovirus-based shots caused life-threatening blood clots and bleeding in some people

Five years after the rollout of Covid-19 vaccines started, it seems the mystery of why the Astra-Zeneca and J&J vaccines led to a rare but deadly side effect of unusual blood clots and bleeding has finally been solved. 

It's a fascinating case of molecular mimicry that may help make vaccine safer.🧪

Simulated null distribution for data with a sample size of 100, difference in group means of 5, and a p-value of 0.142

Simulated null distribution of a slope of 0.8 and p-value of 0.002

Finally, we have to decide if the p-value meets an evidentiary standard or threshold that would provide us with enough evidence that we aren’t in the null world (or, in more statsy terms, enough evidence to reject the null hypothesis). There are lots of possible thresholds. By convention, most people use a threshold (often shortened to α) of 0.05, or 5%. But that’s not required! You could have a lower standard with an α of 0.1 (10%), or a higher standard with an α of 0.01 (1%). Statistically significant The p-value is < 0.001 and our threshold for α is 0.05 In a world where there is no relationship between x and y, the probability of seeing a slope of at least 0.901 is < 0.1% Since < 0.001 is less than 0.05, we have enough evidence to say that the slope is statistically significant.

Evidentiary standards When thinking about p-values and thresholds, I like to imagine myself as a judge or a member of a jury. Many legal systems around the world have formal evidentiary thresholds or standards of proof. If prosecutors provide evidence that meets a threshold (i.e. goes beyond a reasonable doubt, or shows evidence on a balance of probabilities), the judge or jury can rule guilty. If there’s not enough evidence to clear the standard or threshold, the judge or jury has to rule not guilty. With p-values: If the probability of seeing an effect or difference (or δ) in a null world is less than 5% (or whatever the threshold is), we rule it statistically significant and say that the difference does not fit in that world. We’re pretty confident that it’s not zero. If the p-value is larger than the threshold, we do not have enough evidence to claim that δ doesn’t come from a world of where there’s no difference. We don’t know if it’s not zero. Importantly, if the difference is not significant, that does not mean that there is no difference. It just means that we can’t detect one if there is. If a prosecutor doesn’t provide sufficient evidence to clear a standard or threshold, it does not mean that the defendant didn’t do whatever they’re charged with†—it means that the judge or jury can’t detect guilt.

I just whipped up this little #QuartoPub site last week that demonstrates how I teach p-values/hyp-testing through simulation both with live OJS and with #rstats, and I think it's super neat! It has examples for diff-in-means, diff-in-props, and regression slopes nullworlds.andrewheiss.com #statsky

Although the next conference is still a way off, we’ve created this account to share updates on venue and dates, as well as news and publications on FRUGIVORES & SEED DISPERSAL

Artwork: María León Ilustración

🎉 ¡Vuelven los encuentros!
Jueves, 12 de marzo (18:30-20:00), para compartir conocimientos sobre R, estadística, ciencia de datos y programación.

📍 Lugar: Instituto de Matemáticas de la Universidad de Sevilla (IMUS) Av. de la Reina Mercedes, s/n · Sevilla
Meetup: www.meetup.com/sevilla-r-us...
1/2

Great advice there! Thanks

Perhaps it might be useful to mention quarto-live in addition to learnr for making interactive tutorials with exercises?

r-wasm.github.io/quarto-live/...

Ten simple rules for teaching data science Teaching data science presents unique challenges and opportunities that cannot be fully addressed by simply borrowing pedagogical strategies from its parent disciplines of statistics and computer scie...

"Ten simple rules for teaching data science": arxiv.org/abs/2602.02874

A new preprint by @minecr.bsky.social and myself. We'd love any feedback!

dplyr 1.2.0 dplyr 1.2.0 fills in some important gaps in dplyr's API: we've added a new complement to `filter()` focused on dropping rows, and we've expanded the `case_when()` family with three new recoding and re...

dplyr 1.2.0 is out now and we are SO excited!

- `filter_out()` for dropping rows

- `recode_values()`, `replace_values()`, and `replace_when()` that join `case_when()` as a complete family of recoding/replacing tools

These are huge quality of life wins for #rstats!

tidyverse.org/blog/2026/02...

Thank you @zeileis.org, makes sense

To give credit in publications, I think I'll keep using whatever package authors chose in their CITATION file. But I can see how the CRAN DOI can be very useful in many circumstances

What's new in the world of Generalized Additive Models YouTube video by Bottom of the Heap

🚨 GAMs have moved on—so it’s time for an update.

On March 3, 2026 (17:00–19:00 CET) I’ll be livestreaming an updated introduction to Generalized Additive Models in R

📺 YouTube livestream link: youtube.com/live/A9U8e1K...

#RStats #mgcv #GAMs #gratia #statistics 🧪

I don't know if it's feasible that even though the DOI redirects to the CRAN page, the citation metadata (deposited at Crossref) reflect those of the CITATION file

@tjmahr.com yeah my point is that if we use CRAN DOI to cite packages, we are not citing them the way package authors have stated explicitly in the CITATION file. It'd be nice to respect that?

I recall reading @zeileis.org that CRAN DOI metadata are independent of the CITATION file, even if the latter exists. Which sometimes might be unfortunate if package authors are not cited the way they would prefer...

So if the package has a CITATION file, the CRAN DOI metadata should reflect what is stated in CITATION? That's not what I get. See example with lme4 too. What am I doing wrong?

CRAN DOI-generated citation of ggplot2 package: Wickham, H., Chang, W., Henry, L., Pedersen, T. L., Takahashi, K., Wilke, C., Woo, K., Yutani, H., Dunnington, D., Brand, T. van den, Posit, & Pbc. (2025). ggplot2: Create elegant data visualisations using the grammar of graphics (Versión 4.0.1) [Software]. https://cran.r-project.org/web/packages/ggplot2/index.html

ggplot2 preferred citation as stated in the CITATION file: To cite ggplot2 in publications, please use Wickham H (2016). ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York. ISBN 978-3-319-24277-4, https://ggplot2.tidyverse.org.

Yes. But I'm still confused it overrides authors' preferred citation as stated in the CITATION file?

Compare CRAN DOI citation (left) vs CITATION file (right) #rstats

Screenshot of Prism - I asked it to create a methods, participants, results, and discussion seconds. It did so within 54 seconds...

OpenAI just released Prism, a LaTeX editor with embedded ChatGPT for free.
Writing a paper has never been easier.
Clogging the scientific publishing pipeline has never been easier.
It took me 54 seconds to write up an experiment I did not actually conduct.

prism.openai.com

igure 1: Overview of results: (Left) We find a significant decrease in library-specific skills (conceptual understanding, code reading, and debugging) among workers using AI assistance for completing tasks with a new python library. (Right) We categorize AI usage patterns and found three high skill development patterns where participants stay cognitively engaged when using AI assistance.

"How AI Impacts Skill Formation", by Judy Hanwen Shen and Alex Tamkin, both working at Anthropic: arxiv.org/abs/2601.20245

I'd say yes, in general. But beware of external dependencies beyond R packages. Tools like rix or Docker help you capture (and recreate) the full computational environment required for your project

raps-with-r.dev

¡Muchas gracias! Totalmente de acuerdo en la importancia de la defensa y, probablemente, la conveniencia de un comité externo con reuniones anuales. IMO ayuda a encaminar la tesis desde el principio y si todo va bien, el requisito de publicación sería casi innecesario...

Interesado en escuchar opiniones sobre esto 👆🏼. ¿Cuál es la postura de @fpuinvestiga.bsky.social @redpredoctoralcsic.bsky.social @fjiprecarios.bsky.social ? Gracias

We are hiring a postdoctoral researcher!🌲 🌳 🌍

📍Interested in boreal and temperate forest productivity and respiration?
💻 Like to work with large datasets, remote sensing and models?
🏔️ Love an alpine setting in a small town?

Come and join us at KIT!

Application details: t1p.de/qctj7

🫂

Last term I tried an experiment: I walked into my Tech and Design Ethics class, admitted that I had *no idea* what to do about ChatGPT - so I would let them figure it out.

As in: their first project was to decide and write the ChatGPT policy for the class.

Here's what happened:

Examples of how to use the new futurize package

Oooh love this. Easiest way to parallelise anything in #rstats. Just add futurize() to your favourite function call

www.jottr.org/2026/01/22/f...

Thanks @henrikbengtsson.bsky.social HT @rstats.blaze.email

Zotero 8 is out in stable: www.zotero.org/blog/zotero-8/
A bunch of new stuff -- the new citation dialog especially is a huge (and long overdue) improvement; massively speeds up anything I do in Word/GDocs with Zotero

Thanks Luis. Very helpful resource

Nice initiative! I've just added it to the directory of journals publishing software papers in ecology, evolution and biogeography

pakillo.github.io/journals-sof...

Back from holiday and it's finally time to post about this. I am taking on a section editor role for the new diamond open access journal Biogeography, put together by @biogeographyjfab.bsky.social. That means that it's free to publish and free to read. (thread)

biog.journals.sup.org/index.php/bi...