October 28, 2025

The R Data Scientist 28-10-2025

R-community news, data skills training, innovative software development, map visualizations and more!

🌐 Community News & Round-ups

rOpenSci News Digest, October 2025 (ropensci​.org). Monthly round-up of rOpenSci activity: software, peer review, coworking, and community notes

Go for Launch! Packages Shipped to the R-Multiverse (ropensci​.org). R-multiverse publishes R packages like riem, geotargets, and weathercan for community testing and production-ready snapshots

Weekly recap (Oct 24, 2025) (blog​.stephenturner​.us). Polyglot data science pipeline (R+Python+Julia) with rixpress; EuroBioC2025/BCN recap; Python packaging for R devs; R/Pharma; DARPA; ASHG; Quarto; AI in universities

Elevate Your Data Skills with Jumping Rivers Training (jumpingrivers​.com). Hands-on training in R, Python, Git, AI, and more from Jumping Rivers, with in-person and online options and bespoke in-house programmes

📄 Quarto & Publishing

An ode to reveal.js (danielroelfs​.com). Why reveal.js excels for design-driven presentations using HTML/CSS/JS, with LaTeX, KaTeX/MathJax, highlight.js, Quarto, and GitHub sharing

I translated my book for $7 using openai (andrewpwheeler​.com). Translating a technical Python crime analysis book with OpenAI, Markdown/Quarto, and promo-boosted multilingual releases

posit::conf(2025) Quarto workshop materials (quarto​.org). Two Quarto workshops at posit::conf(2025): Branded outputs and Extending Quarto with custom tooling

Typst with Pandoc: A Modern, Fast Alternative to (Xe)LaTeX for PDF Generation (slhck​.info). Typst as a fast Pandoc PDF engine alternative to XeLaTeX for Markdown-to-PDF workflows

🛠️ R Development

A pathetic tale of searching for an R function on Google (chainsawriot​.com). R function readODS::read_fods() search experiences on Google, rdocumentation.org, and DuckDuckGo, with critiques of search quality and domain ranking

revdeprun: Rust CLI for R package reverse dependency check automation (nanx​.me). Rust CLI revdeprun automates cloud reverse-dependency checks for R packages, provisioning R environments and running revdep_check()

Switching from Windows to Ubuntu (as an R developer) (rolkra​.github​.io). Switching to Ubuntu for R development with RStudio, CRAN install, Git, and required system libraries on a Dell laptop

Introduction to Julia for R users (sgsong​.blogspot​.com). Introductory guide for R users to Julia, covering Julia basics and transitioning tools and workflows

Tabler 0.1.0 is here! (pacha​.dev). Tabler 0.1.0 for R Shiny introduces a flexible Tabler Dashboard framework with multiple layouts and themes

🗺️ Mapping & Visualization

Age Disparity in Shelter Cost per Room (doodles​.mountainmath​.ca). Shelter cost per room across Canadian metros by age, using PUMF data and inflation-adjusted real terms in R

#IDWeek2025 Posts/Tweets Analysis (kenkoonwong​.com). IDWeek2025 analysis across Bluesky and X: post counts, engagement, top posters, duplicates, and a Shiny app for topic exploration

Mapping Antarctica (dieghernan​.github​.io). Orthographic Antarctica mapping with R, fixing GISCO polygon, ggplot geom_sf, graticules, rmapshaper, giscoR, and custom pole-centered projections

Manhattan Plot of Manhattan (kieranhealy​.org). A playful Manhattan plot of Manhattan’s buildings, mixing noisy x-years with height-based color and alpha encoding

💹 Economics & Policy

Find Something to Do with the Quality of Government (Cross-Section) Data (svmiller​.com). Tutorial using QoG cross-section data with R: QoG, WDI, top 1% income share, worker’s rights, and descriptive modeling

New instantaneous short rates models with their deterministic shift adjustment, for historical and risk-neutral simulation (thierrymoudiki​.github​.io). Three deterministic-shift arbitrage-free short-rate constructions (Nelson–Siegel, ML-guided NS, direct regression) with caplet and swaption pricing in Python and R

Gender Equity in British Literary Prizes: Progress with Persistent Disparities (stevenponce​.netlify​.app). Gender equity in British prizes climbs, yet disparities persist with varied prize outcomes

The World Bank’s Reproducible Research Initiative: Raising the Bar for Transparency in Development Economics (bitss​.org). World Bank requires reproducibility packages for PRWP series; internal verification, open repository, and open data tools

📊 Statistical Methods

Be Mindful of the Time (rworks​.dev). Fitting a 5-state CTMC via EM to incomplete state-table asthma trial data using Q and P(t) computations in R (expm, ctmcd)

Excursion 1 Tour I (3rd stop): The Current State of Play in Statistical Foundations: A View From a Hot-Air Balloon (1.3) (errorstatistics​.com). Explores Bayesian–frequentist debates, ecumenism, and the shift toward eclectic foundations in statistics from a hot-air balloon vantage

Major error in study on Flynn Effect (sebjenseb​.net). Examination of a Flynn Effect WM study: cross-temporal meta-analysis of forward/backward digit span, regression tables, and potential data/code issues

From P-values to Bayes Factors with eJAB (bayesianspectacles​.org). Generalized Jeffreys’s approximate objective Bayes factor (eJAB) links p-values, sample size, and dimensionality for model selection and 71,126 clinical trial results

coupling-based approach to f-divergences diagnostics for MCMC (xianblog​.wordpress​.com). Coupling-based weight harmonization for MCMC f-divergence diagnostics with χ² bounds and convergence guarantees

A parametric survival model for child mortality using complex survey data (by Taylor Okonek, Jon Wakefield, Katie Wilson) (demographic-research​.org). Parametric, survey-weighted survival models for under-5 mortality using complex survey data across LMICs with pseudo-likelihood estimation and validation via nonparametric methods

📚 Academic Research

To MCMC or not to MCMC: Evaluating non-MCMC methods for Bayesian penalized regression (arxiv:stat). Compares MCMC and non‑MCMC (mean‑field VI) for high‑dimensional Bayesian penalized regression, includes R implementations and tutorials—enables huge speedups with quantified prediction trade-offs

Asynchronous Distributed ECME Algorithm for Matrix Variate Non-Gaussian Responses (arxiv:stat). Proposes asynchronous distributed ECME (ADECME) for matrix‑variate skew‑t regression, scales inference for longitudinal, heavy‑tailed data; provides R package enabling practical deployment

Semi-Implicit Approaches for Large-Scale Bayesian Spatial Interpolation (arxiv:stat). Introduces Semi‑Implicit Variational Inference (SIVI) for scalable Bayesian spatial interpolation; matches HMC accuracy but reduces runtimes dramatically—suitable for R spatial practitioners handling massive datasets

hi