Generalized linear models and the exponential family of distributions · Advanced reference treatise · Introduction

Introduction

What this guide covers

The classical general linear model (OLS or ordinary least squares regression) has been the core of empirical analysis for decades. However, its formulation rests on restrictive mathematical assumptions that are often unsustainable given the intrinsic nature of observational and experimental empirical data.

Overview

Topics covered

Introduction
Introduction Generalized Linear Models
Deficiencies of the Classical Linear Model and Beginnings of the GLM
Critical Limitations of the Classical Approach
The Unification of Nelder and Wedderburn
The Exponential Family of Distributions: Unified Formulation

Related concepts

Main connections

Compatible notation

Mathematical sample in LaTeX

The expression is rendered accessibly, with its LaTeX source preserved below.

Y = \mathbf{X}\boldsymbol{\beta} + \boldsymbol{\varepsilon}

View LaTeX source

Y = \mathbf{X}\boldsymbol{\beta} + \boldsymbol{\varepsilon}