Model Selection and Inference

1. Front Matter

   Pages i-xx

   PDF

2. Introduction

   • Kenneth P. Burnham, David R. Anderson

   Pages 1-31

3. Information Theory and Log-Likelihood Models: A Basis for Model Selection and Inference

   • Kenneth P. Burnham, David R. Anderson

   Pages 32-74

4. Practical Use of the Information-Theoretic Approach

   • Kenneth P. Burnham, David R. Anderson

   Pages 75-117

5. Model-Selection Uncertainty with Examples

   • Kenneth P. Burnham, David R. Anderson

   Pages 118-158

6. Monte Carlo and Example-Based Insights

   • Kenneth P. Burnham, David R. Anderson

   Pages 159-229

7. Statistical Theory

   • Kenneth P. Burnham, David R. Anderson

   Pages 230-314

8. Summary

   • Kenneth P. Burnham, David R. Anderson

   Pages 315-328

9. Back Matter

   Pages 329-355

   PDF

We wrote this book to introduce graduate students and research workers in var­ ious scientific disciplines to the use of information-theoretic approaches in the analysis of empirical data. In its fully developed form, the information-theoretic approach allows inference based on more than one model (including estimates of unconditional precision); in its initial form, it is useful in selecting a "best" model and ranking the remaining models. We believe that often the critical issue in data analysis is the selection of a good approximating model that best represents the inference supported by the data (an estimated "best approximating model"). In­ formation theory includes the well-known Kullback-Leibler "distance" between two models (actually, probability distributions), and this represents a fundamental quantity in science. In 1973, Hirotugu Akaike derived an estimator of the (relative) Kullback-Leibler distance based on Fisher's maximized log-likelihood. His mea­ sure, now called Akaike 's information criterion (AIC), provided a new paradigm for model selection in the analysis of empirical data. His approach, with a funda­ mental link to information theory, is relatively simple and easy to use in practice, but little taught in statistics classes and far less understood in the applied sciences than should be the case. We do not accept the notion that there is a simple, "true model" in the biological sciences.

• Inference
• Likelihood
• Model Selection
• data analysis
• information theory
• optimization
• statistics

From the reviews of the second edition:

Burnham and Anderson (eschew) P-values completely and (focus) entirely on how to decide when a model or models adequately fits the data. In essence, this is what an ecologist wants to know-how do predictive models work? This simple categorization, however, belies the conceptual richness that Burnham and Anderson present in their book, and its importance." (Ecology)

"Bolstered by a new chapter and an additional 140 pages, this very specialized book is now quite a sizable affair in its second edition … . Subtitled ‘A Practical Information-Theoretic Approach,’ the book is built on the use of the Kullback-Leibler distance approach for multimodel inference. … The enthusiasm of the authors for their subject is apparent from the effort that they have made to extensively revise what already was a very unique book … ." (Technometrics, Vol. 54 (2), May, 2003)

• Colorado Cooperative Fish and Wildlife Research Unit, Colorado State University, Fort Collins, USA

  Kenneth P. Burnham, David R. Anderson

Policies and ethics