2026
Introducing flownet: Efficient Transport Modeling in R
I am excited to introduce a new R package called flownet providing high-performance tools for transport modeling—network processing, route enumeration, and traffic assignment in R. As of now, the package implements the Path-Sized Logit (PSL) model (Ben-Akiva and Bierlaire, 1999)—a powerful and well-established method for stochastic traffic assignment accounting ...
Visualising income inequality social tables by @ellis2013nz
I recently read Branko Milanovic’s 2023 book, Visions of Inequality: from the French Revolution to the Cold War and gave it five stars. The bulk of the book is an excellent critical look at the views of six major economic thinkers—Quesnay, Smith, Ricar...
How to Predict Sports in R: Elo, Monte Carlo, and Real Simulations
R • Sports Analytics • Ratings • Monte Carlo • Forecasting Sports are noisy. Teams change. Injuries happen. Upsets happen. But uncertainty is not the enemy—it’s the input. In this hands-on guide you’ll build a practical sports prediction workflow in R using tidyverse, PlayerRatings, and NFLSimulatoR, then connect ratings to Monte ... [Read more...]
Getting to the bottom of TMLE: influence functions and perturbations
I first encountered TMLE—sometimes spelled out as targeted maximum likelihood estimation or targeted minimum-loss estimate—about twelve or so years ago when Mark var der Laan, one of the original developers who literally wrote the book, gave a talk ... [Read more...]
Getting to the bottom of TMLE: influence functions and perturbations
I first encountered TMLE—sometimes spelled out as targeted maximum likelihood estimation or targeted minimum-loss estimate—about twelve or so years ago when Mark var der Laan, one of the original developers who literally wrote the book, gave a talk ... [Read more...]
Paleontology R Packages to Benefit from Software Sustainability Institute Grant
Palaeoverse, a grassroots organization that develops R packages for paleontology, has been awarded a Large Grant from the Software Sustainability Institute, via the Research Software Maintenance Fund, for the project ‘Converting Users to Contrib... [Read more...]
Repost: OpenAI Codex App: Vibe-updating my old qqman R package to ggplot2 with plan+execute.
Reposted from the original at https://blog.stephenturner.us/p/openai-codex-app-qqman.Earlier this week I reposted a Bluesky post from Ethan Mollick.
I’m on the same page here — there are problems for sure, but these
tools have irreversibly changed th...
Presenting Lightweight Transfer Learning for Financial Forecasting (Risk 2026)
Presenting Lightweight Transfer Learning for Financial Forecasting (Risk 2026) [Read more...]
When Targeting Gets Too Narrow: A Break-Even Lens for selecting Audience Segments
Short practical advise on media targeting decisions:
Calculate the “Break-Even Multiplier” Before Spending
Instead of asking if a targeting segment will perform better than a broad audience, calculate exactly how much better it needs to be to ... [Read more...]
Announcing New Statistical Software Peer Review Editors: Natalia da Silva and Andrew Heiss
At rOpenSci we’re continually grateful for the support and engagement of our community who help make our open-source ecosystem stronger, more inclusive, and more collaborative. The software peer review program is one of the best examples of this: brin... [Read more...]
December 2025 Top 40 New CRAN Packages
In December, one hundred ninety-six new packages made it to CRAN. Here are my Top 40 picks in nineteen categories: Agriculture, Artificial Intelligence, Audio Analysis, Causal Inference, Computational Methods, Ecology, Econometrics, Epidemiology...
Designing Sports Betting Systems in R: Bayesian Probabilities, Expected Value, and Kelly Logic
A good sports betting system is not a “pick-winners” machine. It’s an uncertainty engine: it turns data into probabilities, probabilities into expected value, and expected value into position sizes that survive variance. If you can do those three steps consistently, you can build a robust process— even if individual ... [Read more...]
Option pricing using time series models as market price of risk
Enhancing Time Series Forecasting (ahead::ridge2f) with Attention-Based Context Vectors (ahead::contextridge2f)
Explain the new ahead::contextridge2f function [Read more...]
Do Loyalty Programs Actually Create Loyalty?
Today’s paper is Byron Sharp’s 1997 “Loyalty Programs and their Impact on Repeat-Purchase Loyalty Patterns” – a classic that remains surprisingly relevant.
Takeaways for marketing practitioners?
Loyalty programs don’t create “excess loyalty”:... [Read more...]
Releasing dfms 1.0: Fast and Feature-Rich Estimation of Dynamic Factor Models in R
I am very happy to announce the release of dfms version 1.0 (and 0.4.0 just a week earlier, see news), implementing major features such as support for dynamic factor models (DFMs) with autoregressive errors, mixed-frequency (monthly-quarterly) DFMs, including with autoregressive errors, and decomposition of forecast revisions into news releases (updates to time ...
rOpenSci News Digest, January 2026
Dear rOpenSci friends, it’s time for our monthly news roundup! You can read this post on our blog. Now let’s dive into the activity at and around rOpenSci!
rOpenSci HQ
Open call for the rOpenSci Champions Program 2026!
We are pleased t... [Read more...]
Book Recommendations
There was a very long time without a blog post from me.
I will start now again with a very short blog post with some book and blog recommendations.
I think two still very hot topics currently are AI and Causal Modelling.
AI
For a theoretical A... [Read more...]
How to Recruit a New Maintainer for Your Package
Read it in: Español. Maintaining an open source package is rewarding work, but it’s also a lot of work.
Life and careers change, interests shift, and sometimes you simply don’t have the time or energy to keep working on your R package (and that’s okay!1).
When ... [Read more...]
Copyright © 2026 | MH Corporate basic by MH Themes