PyMC で学ぶ ベイズ統計モデリング 【基礎編】

Learn the fundamentals of Bayesian statistics modeling and probabilistic programming with PyMC, a powerful Python package. This course takes you from basic examples like distribution fitting to understanding more complex models such as Generalized Linear Models (GLMs) and Generalized Linear Mixed Models (GLMMs).

PyMC is known for its user-friendly interface, allowing you to express a wide variety of models with simple syntax. Our goal is to provide a concise and efficient introduction to the workflow of Bayesian modeling with minimal learning overhead.

Important Notes:

• While we cover both theoretical and practical aspects, some prior knowledge of probability distributions is beneficial for a deeper understanding. We provide a review of necessary background information at the beginning of the course.
• The examples used are largely the same as those in "NumPyro で学ぶベイズ統計モデリング【基礎編】" but utilize PyMC.
• This course prioritizes implementation and code. Conceptual explanations are included but considered supplementary. For a rigorous statistical foundation, we recommend consulting dedicated statistics textbooks.

Course Updates:

This course is an update of the original "PyMC3 で学ぶ統計モデリングの基礎" and has been revised to align with the latest version of PyMC. While the sample code is updated for PyMC version 5, some video content may still reflect older PyMC3 versions.

Setting up the environment is simplified! Unlike previous versions requiring Anaconda, PyMC now runs seamlessly in Google Colaboratory. We offer free resources for environment setup, which we recommend reviewing.

Key topics covered:

• Bayesian Statistics
• Probabilistic Programming
• PyMC
• Generalized Linear Models (GLMs)
• Generalized Linear Mixed Models (GLMMs)
• Distribution Fitting
• Statistical Modeling
• Python Packages