We're living in a #distopy.

I’d like to share that my book, Multilevel Thinking: Discovering Variation, Universals, and Particulars in Cross-Cultural Research is available for pre-order at Oxford University Press: https://global.oup.com/academic/product/multilevel-thinking-9780197806463?cc=us&lang=en&#

* This book explains multilevel modeling building upon my 15 years of teaching this topic.
* The book contains appendices for estimating multilevel models in #Stata, #Rstats, and #Julialang.

Are you in SoCal? Come join me on April 24 for a behind-the-scenes talk on the origin of Tidier.jl for #julialang, and why #rstats users should give it a look. More details will be posted here: www.meetup.com/socal-rug/

We are hiring a researcher to work on dispersion modeling in #JuliaLang. The location is #Brussels, job starts in August.

#academicjobs #FediHire

https://www.linkedin.com/jobs/view/4200104658

https://DSLC.io welcomes you to week 13 of #TidyTuesday! We're exploring Pokemon!

https://tidytues.day/2025/2025-04-01
https://medium.com/@hanahshih46/pokemon-data-visualization-and-analysis-with-r-60970c8e37f4

Submit a dataset! https://github.com/rfordatascience/tidytuesday/blob/main/.github/CONTRIBUTING.md

Interesting write-up regarding the reason behind the speed in #JuliaLang. Author argues that speed isn't solely from the JIT (both #Python and #R have JIT implementations). Instead, the speedup is from type stability + multiple dispatch for specialization, which allows for easier compiler optimizations.

Why Does Julia Work So Well?
https://ucidatascienceinitiative.github.io/IntroToJulia/Html/WhyJulia

https://DSLC.io welcomes you to week 12 of #TidyTuesday! We're exploring Text Data From Amazon's Annual Reports!

https://tidytues.day/2025/2025-03-25
https://gregoryvdvinne.github.io/Text-Mining-Amazon-Budgets.html

Submit a dataset! https://github.com/rfordatascience/tidytuesday/blob/main/.github/CONTRIBUTING.md

If you're an power user / dev interested in putting R in production please join my discord :) https://discord.gg/YS8JKTrm

Its probably the best way to get a hold of me these days!

users welcome too—I want to learn more about y'all

Anyone know what #atproto API call to get basic user info like # followed, # following, # of posts? (preferably using an #rstats package like {atrrr} or {bskyr} or other, or #julialang) I can fetch the actual posts — typically 100 at a time paginated — but I just want total count estimate.

PSA to the 5 people who might find this useful: you can now fit #julialang MixedModels from #rstats in Google Colab :D

https://github.com/yjunechoe/jlme/

OH MY GOD?!?!?!?

Not only does Google Colab support #julialang runtime now but the #rstats runtime can access the Julia executable too!?!?!

With #JuliaLang now part of #GoogleColab, I've created a notebook showcasing Colab-specific Julia features and data wrangling.

Perfect for #rstats & #python users wanting to experience Julia's speed and elegance.

Colab: https://colab.research.google.com/github/coatless-r-n-d/colab-notes/blob/main/10a-julia-colab-demo.ipynb

GitHub: https://github.com/coatless-r-n-d/colab-notes/blob/main/10a-julia-colab-demo.ipynb

Introducing multi-root workspace support: the Quarto Wizard now casts its spell across multiple realms!
(Currently as pre-release: 0.15.0)

https://github.com/mcanouil/quarto-wizard

Julia has joined Python and R as a native kernel in Google Colab for a complete JuPyteR experience! Now you can use Julia with a free T4 GPU and leverage packages like Reactant without complex setup.

Details: https://github.com/googlecolab/colabtools/issues/5151

Cubic smoothing splines be like.

#Julialang #opensource #GeometryProcessing

Code: https://github.com/COMODO-research/Comodo.jl/blob/main/examples/demo_smoothing_spline.jl

Made possible by: https://github.com/jipolanco/BSplineKit.jl

Google colab now has native support for #rstats and #JuliaLang

Simply change the runtime kernel.

Thanks to Miles Cranmer for the tip.

Just delivered a talk on algorithmic differentiation in our #dftk density-functional theory code at the #cecam workshop on #dft and #ai

Slides: https://michael-herbst.com/talks/2025.03.04_DFT_AI_Learning_each_other.pdf
#julialang demo: https://michael-herbst.com/talks/2025.03.04_DFT_AI_Learning_each_other_design.html

I spent yesterday trying to find the best way to plot this very detailed image. Due to its many overlapping lines, regular paper didn't hold up to repeated passes unless I used a ballpoint, which shed ink in a way that I found distracting.

In the end, the best result came from a 0.1mm Rotring Isograph with Black DeAtramentis Document ink on Yupo paper. Amazing detail and tonal gradation.