The lme4u Project, Handbook of Regression Modeling in People Analytics, New Courses

This week's agenda:

• Open Source of the Week -

• New learning resources - building game simulation agents, matplotlib and pandas course, probability, and MLflow courses

• Book of the week - Handbook of Regression Modeling in People Analytics by Keith McNulty

I share daily updates on Substack, Facebook, Telegram, WhatsApp, and Viber.

---

Are you interested in learning how to set up automation using GitHub Actions? If so, please check out my course on LinkedIn Learning:

---

Open Source of the Week

Here are some open-source updates I came across this week.

The lme4u Project

The lme4u project is a new R library by Holly Cui that provides an interpretation and diagnostic tool for linear mixed-effects models fitted with the lme4 package.

The library comes with a set of functions for:

• Tools for interpretation of a fitted lmer model's fixed and random effects.

• Likelihood ratio test for linear mixed-effects model

• Assumption checks for residuals

• Student-teacher achievement ratio data

You can find more details in the project documentation.

Project repo: https://github.com/hollyyfc/lme4u/

License: GPL-3

Quarto 1.7

Quarto is one of my favorite open-source projects, and it is great to see the constant improvement and new features in the project. Version 1.7 was released recently with improvements to the dark mode functionality. More details are available in the release notes.

The CopilotKit Project Supports MCP Chat

The CopilotKit project now supports an MCP-compatible chat client in any React application. The following post, from Atai Barkai , provides more details.

You can find more details about the CopilotKit project in this edition.

---

New Learning Resources

Here are some new learning resources that I came across this week.

Building Game Simulation Agents - New Course

The AI hands-on course by

Miguel Otero Pedrido

and

Paul Iusztin

focuses on building a production-level AI agent using tools such as Groq, LangGraph, MongoDB, Opik, and FastAPI. This five-chapter course covers the following topics:

• PhiloAgents architecture

• LangGraph workflow

• Agent memory system

• FastAPI + websockets

• LLMOps

Introduction to matplotlib and pandas Libraries

A great intro to matplotlib and pandas Python libraries by Prof. Patrick Georges from the University of Ottawa. This tutorial was designed for children and it is a beginner level.

Probability, Measure and Martingales - Oxford Course

The University of Oxford released a new mini stats course that focuses on math beyond core probability topics such as conditional expectation, martingales, martingale transforms, and changes of measure. The course is taught by Professor of Mathematics Jan Obloj.

MLflow Crash Course

The following tutorial by Karndeep Singh provides an introduction to the MLflow framework. This five-video series covers the foundation of experimentation with MLflow, and it covers the following topics:

• Experiment tracking

• Machine learning experiment

• Hyperparameter tuning with MLflow and HyperOpt

• Model versioning

• Model registry

• Setting up an MLflow server

---

Book of the Week

This week's focus is on a classical stats book. Keith McNulty's Handbook of Regression Modeling in People Analytics is a practical guide that bridges statistical theory with real-world applications in people analytics. It offers a comprehensive approach to regression techniques, complemented by hands-on examples in R, Python, and Julia.

Topics Covered:

• Fundamentals of the R programming language

• Statistical foundations for regression analysis

• Linear regression for continuous outcomes

• Binomial logistic regression for binary outcomes

• Multinomial logistic regression for nominal categories

• Ordinal logistic regression for ordered categories

• Modeling hierarchical data structures

• Survival analysis for time-to-event data

• Alternative technical approaches in R, Python, and Julia

• Power analysis for determining sample sizes

• Practical exercises with 16 diverse datasets

The book is ideal for analysts, students, and researchers in both the public and private sectors. The book provides the tools to apply regression modeling effectively in various contexts. The book, thanks to the author, has a free online version.

A printed version of the book is available for purchase from the book publisher's website at a 20% discount (via the online version) using code HRM20.

---

Have any questions? Please comment below!

See you next Saturday!

Thanks,

Rami