Statistical Modelling: Theory and Practice

Here are posts so far on statistical modelling, now arranged by section/grouping for easier navigation.

Core material: Principles of Statistical Inference and Simulation

Section 1: Introduction

A reintroduction to statistics from the perspective of generalised linear modelling.

Section 2: Likelihood and simulation theory

A deep dive into the core principles and concepts underlying statistical modelling using likelihood, and how to use models for honest prediction and simulation

Section 3: A complete example

The application of the above material to a specific dataset, starting with model fitting and simple prediction functions, and ending with Bayesian modelling

Notes on core section

I consider the production of this material something of a public service. More on the background to the series, which includes my own background, is available in this post here.

Additional Materials

Deep dives into specific topic areas. These sections can be approached in any order, so long as the core section has been read and understood first.

Causal Inference

An opinionated discussion of the topic and challenges of causal inference.

Time Series

An introduction to time series, focused around the ARIMA modelling framework.

Resampling Methods/Hacker Stats

An introduction to resampling methods (AKA ‘Hacker Stats’), including bootstrapping and permutation testing.