Model Selection and Inference

This book is unique in that it covers the philosophy of model-based data analysis and a strategy for the analysis of empirical data. Model selection, under the information theoretic approach presented here, attempts to identify the (likely) best model, orders the models from best to worst, and measures the plausibility (“calibration”) that each model is really the best as an inference. Model selection methods are extended to allow inference from more than a single “best” model. Several methods are given that allow the uncertainty as to which model is "best" to be incorporated into estimates of precision. An array of examples are given to illustrate various technical issues. This is an applied book written primarily for biologists and statisticians using models for making inferences from empirical data. Research biologists working either in the field or in the laboratory will find simple methods that are likely to be useful in their investigations. Applied statisticians will find the information theoretic methods presented here quite useful and a superior alternative, especially for observational studies. People interested in the empirical sciences will find this material useful as it offers an alternative to hypothesis testing and Bayesian approaches.

Table of contents

Preface
Chapter 1: Introduction
Chapter 2: Information Theory and Log-Likelihood Models - A Basis for Model Selection and Inference
Chapter 3: Practical Use of the Information Theoretic Approach
Chapter 4: Model Selection Uncertainty with Examples
Chapter 5: Monte Carlo Insights and Extended Examples
Chapter 6: Statistical Theory
Chapter 7: Summary
Chapter 8: References
Chapter 9: Index