AIC model selection and multimodel inference in behavioral ecology: some background, observations, and comparisons

@article{Burnham2010AICMS,
  title={AIC model selection and multimodel inference in behavioral ecology: some background, observations, and comparisons},
  author={Kenneth P. Burnham and David R. Anderson and Kathryn P. Huyvaert},
  journal={Behavioral Ecology and Sociobiology},
  year={2010},
  volume={65},
  pages={23-35}
}
We briefly outline the information-theoretic (I-T) approaches to valid inference including a review of some simple methods for making formal inference from all the hypotheses in the model set (multimodel inference). The I-T approaches can replace the usual t tests and ANOVA tables that are so inferentially limited, but still commonly used. The I-T methods are easy to compute and understand and provide formal measures of the strength of evidence for both the null and alternative hypotheses… 

A brief guide to model selection, multimodel inference and model averaging in behavioural ecology using Akaike’s information criterion

TLDR
Akaike’s information criterion is provided, using recent examples from the behavioural ecology literature, a simple introductory guide to AIC: what it is, how and when to apply it and what it achieves.

Model selection and model averaging in behavioural ecology: the utility of the IT-AIC framework

TLDR
It is found that, for simple analyses, the advantages of switching to an IT-AIC approach are likely to be slight, especially given recent emphasis on biological rather than statistical significance, and the model selection approach embodied by IT approaches offers significant advantages when applied to problems of more complex causality.

Multimodel-inference in comparative analyses

TLDR
A conceptual framework of model selection for phylogenetic comparative analyses is presented, where the goal is to generalize across models that involve different combinations of predictors, phylogenetic hypotheses, parameters describing the mode of evolution, and error structures.

Using information theory as a substitute for stepwise regression in ecology and behavior

TLDR
This work examines three shortcomings of stepwise regression, subjective critical values, model uncertainty, and parameter estimation bias, and argues that, in certain circumstances, the IT approach may be sensitive to these issues as well.

A brief introduction to mixed effects modelling and multi-model inference in ecology

TLDR
This overview should serve as a widely accessible code of best practice for applying LMMs to complex biological problems and model structures, and in doing so improve the robustness of conclusions drawn from studies investigating ecological and evolutionary questions.

APPENDIX Projections in Model Space: Multi-model Inference Beyond Model Averaging

TLDR
This work discusses information criteria differences as a natural extension of the likelihood ratio that overcomes many of the complexities of real data analysis and extends the information criterion model comparison framework to much more effectively utilize the information in multiple models.

Model averaging in ecology: a review of Bayesian, information-theoretic, and tactical approaches for predictive inference

TLDR
It is shown that model averaging is particularly useful if the predictive error of contributing model predictions is dominated by variance, and if the covariance between models is low, and for noisy data, which predominate in ecology, these conditions will often be met.

A modern method of multiple working hypotheses to improve inference in ecology

TLDR
This work presents a framework for explicitly modelling systems in which relevant processes are commonly omitted, overlooked or not considered and provides a formal workflow for a pre-data collection analysis of multiple candidate hypotheses.

Information criteria on multimodel selection of parametric regression: Biological applications

TLDR
This paper is intended to evaluate in 40 datasets from various ecological published studies the effectiveness of the linear regression model designated by the authors by contrasting with six regression models using the Akaike and Bayesian information criteria, and furthermore to discuss its implications on subsequent interpretations made.

An Information Theoretic Approach to Model Selection: A Tutorial with Monte Carlo Confirmation

TLDR
This article examines claims made by advocates of the Information-Theoretic (I-T) Model Selection approach using Monte Carlo simulations in which 10,000 different data sets are generated and analyzed and showed that the probabilities associated with each model returned by the single virtual experiment approximated those that resulted from the simulations.
...

References

SHOWING 1-10 OF 93 REFERENCES

A brief guide to model selection, multimodel inference and model averaging in behavioural ecology using Akaike’s information criterion

TLDR
Akaike’s information criterion is provided, using recent examples from the behavioural ecology literature, a simple introductory guide to AIC: what it is, how and when to apply it and what it achieves.

Kullback-Leibler information as a basis for strong inference in ecological studies

We describe an information-theoretic paradigm for analysis of ecological data, based on Kullback–Leibler information, that is an extension of likelihood theory and avoids the pitfalls of null

Stepwise Model Fitting and Statistical Inference: Turning Noise into Signal Pollution

TLDR
This study amplifies previous warnings about using stepwise procedures and recommends that biologists refrain from applying these methods, by using a simple simulation design.

Information-theoretic approaches to statistical analysis in behavioural ecology: an introduction

TLDR
This special issue examines the suitability of the IT method for analysing data with multiple predictors, which researchers encounter in the authors' field and brings together different viewpoints to aid behavioural ecologists in understanding the method.

Model selection and multimodel inference : a practical information-theoretic approach

The second edition of this book is unique in that it focuses on methods for making formal statistical inference from all the models in an a priori set (Multi-Model Inference). A philosophy is

Dealing with collinearity in behavioural and ecological data: model averaging and the problems of measurement error

  • R. Freckleton
  • Environmental Science
    Behavioral Ecology and Sociobiology
  • 2010
TLDR
It is shown that automated model selection techniques should not be relied on in the analysis of complex multivariable datasets, as this can lead to extreme biases when predictors are collinear, have strong effects but differ in their degree of measurement error.

Data-Based Selection of an Appropriate Biological Model: The Key to Modern Data Analysis

TLDR
A proper model is fully supported by the data, and has enough parameters to avoid bias, but not too many that precision is lost (the Principle of Parsimony).

Why do we still use stepwise modelling in ecology and behaviour?

TLDR
It is shown that stepwise regression allows models containing significant predictors to be obtained from each year's data, and that the significance of the selected models vary substantially between years and suggest patterns that are at odds with those determined by analysing the full, 4-year data set.

Information Criteria and Statistical Modeling

TLDR
A generalized information criterion (GIC) and a bootstrap information criterion are presented, which provide unified tools for modeling and model evaluation for a diverse range of models, including various types of nonlinear models and model estimation procedures such as robust estimation, the maximum penalized likelihood method and a Bayesian approach.

A new look at the statistical model identification

The history of the development of statistical hypothesis testing in time series analysis is reviewed briefly and it is pointed out that the hypothesis testing procedure is not adequately defined as
...