Data Scientist (with R): 8th April 2025

Empowering Arctic Researchers with Reproducible Data Science Skills: Key Takeaways from the Arctic Data Center’s February 2025 Virtual Training (arcticdata.io, 2025-04-03). The Arctic Data Center's February 2025 training empowered 14 researchers using R, GitHub, and Quarto, covering reproducible research practices, data management plans, and advanced data visualization techniques like ggplot2 and interactive mapping

第117回R勉強会@東京（#TokyoR） (tokyor.connpass.com, 2025-04-07). 第117回R勉強会@東京（#TokyoR）は初心者向けのオンラインイベントで、R言語の紹介や技術交流を目的としています。事前登録が必要で、ハラスメント防止方針を遵守します。

Synthetic controls and CodeChella: Coming soon workshops (causalinf.substack.com, 2025-04-02). Two upcoming workshops focus on synthetic controls and difference-in-differences, featuring practical applications and coding sessions to enhance understanding of these causal inference methods

R Weekly 2025-W15 Positron, Tidyverse + AI, Observable (rweekly.org, 2025-04-07). Highlights include insights on Positron, learning Tidyverse with AI tools, and support for R users using Observable, along with updates on new packages, R Project news, and upcoming events

Shiny in Production 2024 Videos (jumpingrivers.com, 2025-04-08). Explore Shiny in Production 2024 videos featuring six in-depth talks and additional sessions, including an overview of R package validation with Litmus. Early-bird tickets are available for the upcoming 2025 conference

post-Bayes workshop at UCL [15 & 16 May 2025] (xianblog.wordpress.com, 2025-04-03). UCL's workshop on post-Bayesian inference, on May 15-16, 2025, includes eight invited talks and six contributions covering PAC Bayes, generalized Bayes, and more, with opportunities for early career researchers

Social Coworking and Office Hours - R you joking? Silly R packages for April Fools' day (ropensci.org, 2025-04-01). Join rOpenSci's Social Coworking and Office Hours on April 1, 2025, focusing on 'Silly R packages' for April Fools' Day, hosted by Steffi LaZerte and Yanina Bellini Saibene

sixtyfour: writing robust code against AWS (recology.info, 2025-04-03). sixtyfour introduces a science-focused R interface to AWS, built on the paws package, offering user-friendly functions for AWS tasks while emphasizing security and robust testing strategies to manage sensitive information

Learning the tidyverse with the help of AI tools (tidyverse.org, 2025-04-04). Generative AI tools like ChatGPT facilitate learning R and the tidyverse, demonstrated through practical case studies on data visualization and cleaning tasks while highlighting potential challenges for new learners

R et IA : Comment GitHub Copilot peut vous aider à coder en R ?​ (delladata.fr, 2025-04-01). GitHub Copilot is an AI-powered coding assistant that provides real-time code suggestions for R programming in R Studio, enhancing productivity by minimizing errors and adapting to user coding styles

Visualising R Package Risk Assessments using Litmus (jumpingrivers.com, 2025-04-07). The Litmusverse transforms R package risk assessments with tools like litmus, litmus.score, and litmus.dashboard, enhancing compliance and efficiency in regulated environments for R-based FDA submissions

data.table Count Rows by Group (marsja.se, 2025-04-04). Learn to use data.table in R for counting rows by group, utilizing the built-in .N operator, and explore techniques for grouping across multiple categorical variables with concise code examples

Static Code Analysis for R (joss.theoj.org, 2025-04-03). Static Code Analysis for R focuses on tools and techniques for analyzing R code quality using a linter, particularly within the Tidyverse ecosystem, contributing to enhanced software development practices

shapr: Explaining Machine Learning Models with Conditional Shapley Values in R and Python (arxiv:cs, 2025-04-02). shapr is a package for generating conditional Shapley value explanations in R and Python, emphasizing feature dependencies, with tools for time series, parallel computations, and causal values for enhanced model interpretability

How to Make a Heatmap in R (marsja.se, 2025-04-06). Create a clean heatmap in R using ggplot2 by visualizing correlation among BFI personality traits. Learn to preprocess data, compute correlation matrices, and customize visual appearance without borders or grid lines

Calculating the United State’s ‘reciprocal’ tariffs (gilesd-j.com, 2025-04-04). Giles Dickenson-Jones analyzes US reciprocal tariffs through R and UN Comtrade data, revealing their similarity to the trade balance-to-imports ratio using data manipulation techniques and visualizations

Visualizing the Global Fight Against LGBTI Rights: A Data Visualization Collaboration (nicolarighetti.net, 2025-04-01). Data visualizations created using R and ggplot2 illustrate transnational conservative networks targeting LGBTI rights, focusing on actor roles and relationships during the World Congress of Families through heatmaps and geographic mappings

rsample 1.3.0 (tidyverse.org, 2025-04-03). The release of rsample 1.3.0 introduces flexible grouping for bootstrap confidence intervals, enhancing model performance assessment within the tidymodels framework of R, aiding in statistical analysis with various estimation options

When Pearson’s r Fools You: Why Caution is Necessary When Working with Time Series (nicolarighetti.net, 2025-04-07). Caution is needed when using Pearson’s r with time series data, as common trends, seasonality, and regime-switching can produce misleading correlations that do not reflect true relationships between variables

Bayesian Superiority Estimation with R2D2 Priors: A Practical Guide for Protein Screening (ericmjl.github.io, 2025-04-03). Explore Bayesian methods for protein screening using R2D2 priors to decompose variance, quantify protein superiority, and tackle experimental noise with practical examples and PyMC implementation

Addressing common inferential mistakes when failing to reject the null-hypothesis [version 3; peer review: 2 approved] (f1000research.com, 2025-04-01). Common mistakes in failing to reject null-hypothesis discussed, including misinterpretation of statistical power, reliance on p-values, and the need for estimation accuracy in clinical research

Ensembles of Models (datageeek.com, 2025-04-07). An analysis of the BIST Technology Index utilizing ensemble modeling techniques including Auto ARIMA, Prophet, and Elastic Net, with code demonstrating the use of R packages like tidymodels and modeltime

Scalable Fitting Methods for Multivariate Gaussian Additive Models with Covariate-dependent Covariance Matrices (arxiv:stat, 2025-04-04). Efficient computational methods are proposed for multivariate Gaussian additive models with covariate-dependent covariance matrices, using modified Cholesky decomposition and block-oriented methods, implemented in the SCM R package

evalprob4cast: An R-package for evaluation of ensembles as probabilistic forecasts or event forecasts (arxiv:stat, 2025-04-04). evalprob4cast is an R-package designed for evaluating probabilistic and event forecasts, offering metrics and visualization tools for ensemble forecasts, suitable for applications like renewable energy and beyond