GitHub - Conan9133/Bayesian_Inference_PyMC: These notebooks demonstrate my hands-on work in probabilistic modeling and Bayesian inference using PyMC, including MCMC sampling, posterior estimation, and model comparison.

Bayesian Modelling with PyMC and Bambi

This repository contains selected implementations of Bayesian statistical models using PyMC and Bambi. The notebooks demonstrate hands-on experience with probabilistic modelling, hierarchical models, regression techniques, and uncertainty quantification.

Topics Covered

Regression Models (PyMC)

Simple Linear Regression
Logistic Regression
Robust Regression
Hierarchical Linear Regression
Variable Variance Models

Structured Modelling (Bambi)

Polynomial regression and splines
Categorical predictors and interactions
Distributional models
Variable selection

Technical Focus

MCMC sampling
Posterior inference
Convergence diagnostics (R-hat, ESS)
Posterior predictive checks
Model comparison and interpretation
Hierarchical modelling and shrinkage effects

Motivation

While my primary research focuses on hybrid quantum–classical optimization algorithms, Bayesian modelling provides a principled framework for uncertainty-aware inference and model evaluation.

These notebooks were implemented while studying: Osvaldo Martin, Bayesian Analysis with Python (Chapters 4 and 6), and include my own extensions, parameter experiments, and diagnostics.

Tools Used

Python
PyMC
Bambi
ArviZ
NumPy / SciPy / Matplotlib