Data Scientist (with R): 9th September 2025

CBIO’s EuroBioc2025 posters and talks (lgatto​.github​.io). CBIO presents EuroBioc2025 posters and talks on PSMatch, RforMassSpectrometry, QFeatures, e-OMIX, and benchmarking in single-cell proteomics

第119回R勉強会@東京（#TokyoR） (tokyor​.connpass​.com). 第119回R勉強会@東京（#TokyoR）オンライン開催、発表者登録・LT申告、BeginneR Special! の開催案内とコードオブコンダクト

Speaking at posit::conf 2025 (tshafer​.com). In Atlanta, Tom Shafer discusses R development practices that bolster model governance post-deployment for MLOps using packaging, tests, S3 methods, and modular code

Boka höstens kurser nu (statistikakademin​.se). Höstenbjuder onlinekurser i SPSS och R: regression, logistisk regression, överlevnadsanalys, PCA, cluster och SEM

Closing my tabs (Sep 5 2025) (blog​.stephenturner​.us). A weekly recap of AI, R, genomics, and biotech topics including NIH budget news, Bluesky & Science, tidymodels, SV calling, CRAN packages, and Python documentation

A postdoctoral position in ecological statistics at the University of Helsinki (bayesian​.org). Postdoctoral researcher sought to develop hierarchical Bayesian methods for joint species distribution models, phenology from censored data, and climate-extreme effects on ecosystems at University of Helsinki

Driving more efficient and reproducible workflows with Posit Academy (posit​.co). Posit Academy trains R and Python users with hands-on workflows, Quarto, purrr, Shiny, and reproducible pipelines

Creating and managing Canvas quizzes with R/exams and vvcanvas (R-exams​.org). Using R/exams and vvcanvas to create and manage Canvas quizzes via QTI imports and API interactions

Talking to LLMs: From Prompt to Response (shiny​.posit​.co). Practical workflow for programmatic LLM interaction in Python and R using ChatAnthropic/ellmer, system prompts, and environment-key management

bidux 0.3.1: Modern Telemetry Integration in the BID Framework (jrwinget​.com). bidux 0.3.1 adds hybrid telemetry objects and tidy bid_telemetry workflow for BID framework

mirai 2.5.0 (tidyverse​.org). Mirai 2.5.0 brings production-grade async computing to R with OpenTelemetry observability, reproducible parallel RNG, and UI improvements

Version 3.0.1 of neonUtilities R package released (neonscience​.org). Version 3.0.1 of neonUtilities R package updates: bug fixes, token handling, stacking for mobile sites, and timestamp casting improvements

How to use R to dig for story ideas (storybench​.org). Using two R packages, tidyverse and readxl, to load Boston salaries data and explore by department, title, and metrics like TOTAL_GROSS, OVERTIME, and INJURED

Some Papua New Guinea data doodles (freerangestats​.info). Explores PNG GDP, population, employment and vaccination data with R code from ANU PNG Economic Database

10 ChatGPT Prompts for ggplot2 Boxplots: Complete Guide with Working R Code (datavizpyr​.com). 10 ChatGPT prompts with complete R code for ggplot2 boxplots, including notched, jitter, violin overlays, and annotated variants

Proximity-centred accessibility (urbandemographics​.blogspot​.com). Proximity-centred accessibility using R-based spatial analysis, agent-based modeling, and space syntax concepts for urban mobility and transport policy

Time Series Modeling: Why ARIMA Models Beat Linear Regression for Temporal Data (statisticalhorizons​.com). ARIMA (p,d,q)(P,D,Q)s vs linear regression; AirPassengers data; auto.arima; ARIMA(1,1,0)(0,1,0)[12]; Ljung-Box; residuals; forecasts; MAPE ~2.88%

I’m supposed to present ‘Conformal Predictive Simulations for Univariate Time Series’ at COPA CONFERENCE 2025 in London… (thierrymoudiki​.github​.io). Conformal predictive simulations for univariate time series; COPA 2025 poster, MLR Proceedings, conformal prediction, nnetsauce, ahead, Ridge2, Python/R/Ridge2f, conformalize, prob. forecasting

Transfer Learning using ahead::ridge2f on synthetic stocks returns (thierrymoudiki​.github​.io). Pretrains ahead::ridge2f on 1000 synthetic stock returns with Bayesian Optimization and tests on European indices

Your noise is my signal (argmin​.net). Actuarial prediction from samples without features; Brier score; online vs batch prediction; variance irreducible error; sequential evaluation

GAMLSS, NHANES, and my own personal hell (blog​.djnavarro​.net). GAMLSS, NHANES data preprocessing, and modeling joint height–weight distributions using smoothing functions in R

How Bonferroni goes wrong (tamino​.wordpress​.com). Bonferroni pitfalls illustrated with multiple tests,Benjamini-Hochberg contrast, and a dice-loading example

New Publication: Treatment Effect Bounds under Left-censoring in Journal of Applied Statistics: Environmental Statistics and Data Science (herbsusmann​.com). Non-parametric bounds for treatment effects under left-censoring with causal inference for environmental data using R

Why are Normal Distributions Normal (bruceediger​.com). Explores normal vs. log-normal distributions, CLT critiques, tolerances, machining, and a practical PRNG volume experiment

The Actuary's Final Word (argmin​.net). Statistical decision rules vs. clinical judgment; Meehlian critiques; actuarial methods; Bureaucratic Theory of Statistics; arXiv preprint

A nutritionally informed model for Bayesian variable selection with metabolite response variables (arxiv:stat). Bayesian variable selection for metabolite responses using skew-normal censored mixture models with Markov random field priors on diet variables

TumorPred: A Computational Framework Implemented via an R/Shiny Web Application for Parameter Estimation and Sensitivity Analysis in Compartmental Brain Modeling (arxiv:q-bio). TumorPred: An R/Shiny web app for four-compartment brain PK modeling, sensitivity analysis, and parameter estimation

Comparative study of Bayesian and Frequentist methods for epidemic forecasting: Insights from simulated and historical data (arxiv:q-bio). Comparative Bayesian and Frequentist epidemic forecasting with deterministic SIR models, MCMC (Stan), and error metrics across simulated and historical data

Optimizing Prognostic Biomarker Discovery in Pancreatic Cancer Through Hybrid Ensemble Feature Selection and Multi-Omics Data (arxiv:q-bio). Hybrid ensemble feature selection (hEFS) with multi-omics data for pancreatic cancer survival prediction using subsampling, ensemble models, Pareto optimization, and mlr3fselect

The super learner for time-to-event outcomes: A tutorial (arxiv:stat). Practical tutorial on time-to-event super learner: discrete/continuous-time, ensemble methods, R implementations, and open data examples

I've got a big favor to ask - keeping Blaze running isn't expensive, but it does all add up, so I'm asking readers like you to help, if you can.
That's why I'm launching a Patreon page!. Nothing flashy, just a way for folks who find value in these newsletters to chip in a little each month. In return, you'll get:

• Real say in how Blaze evolves — vote on new topics, features, topic curation ideas
• First dibs on merch (details still cooking)
• That warm fuzzy feeling knowing you're supporting something that saves you time and keeps you plugged into great tech writing

If you are getting value from blaze, checking this out would mean the world. And if you can't contribute, no worries—the newsletters keep coming either way, and you can follow along on patreon for free.
Thanks for reading and being part of this nerdy corner of the internet. All the best - Alastair.