Bayesian Inference

Klappentext Statistical theory is primarily a product of the twentieth century. The prevailing school of thought builds on the frequentist philosophy developed by R.A. Fisher, the eminent biological theorist and experimentalist. Fisher's philosophy has been so thoroughly embraced that it has been labeled the "classical" approach, even though the alternative Bayesian philosophy antedates it by more than a century. Frequentist thinking has prevailed over Bayesian primarily because of the practical difficulty of fitting all but the simplest Bayesian models. Wildlife statistics has been almost entirely conducted in the frequentist mode. However, wildlife data are most naturally described in terms of hierarchical models, and these models are best analyzed using Bayesian tools. The advent of fast personal computers and easily available software has nearly removed the difficulties in fitting Bayesian models, and hierarchical models in particular. Hierarchical models describe stochastic population processes governing data and these processes are the real focus of scientific inquiry. This book takes the reader into the domain of Bayesian inference where complex hierarchical modelling is made possible. Zusammenfassung Written to provide a mathematically sound but accessible introduction to Bayesian inference specifically for environmental scientists! ecologists and wildlife biologists! this title emphasizes the power and usefulness of Bayesian methods in an ecological context. It also includes examples drawn from ecology and wildlife research. Inhaltsverzeichnis Chapter 1. Bayesian InferenceChapter 2. ProbabilityChapter 3. Statistical InferenceChapter 4. Posterior CalculationsChapter 5. Bayesian PredictionChapter 6. PriorsChapter 7. Multimodel InferenceChapter 8. Hidden Data ModelsChapter 9. Closed-Population Mark-Recapture ModelsChapter 10. Latent MultinomialsChapter 11. Open Population ModelsChapter 12. Individual FitnessChapter 13. Autoregressive Smoothing...

Zusammenfassung
Written to provide a mathematically sound but accessible introduction to Bayesian inference specifically for environmental scientists, ecologists and wildlife biologists, this title emphasizes the power and usefulness of Bayesian methods in an ecological context. It also includes examples drawn from ecology and wildlife research.

Inhalt

Chapter 1. Bayesian InferenceChapter 2. ProbabilityChapter 3. Statistical InferenceChapter 4. Posterior CalculationsChapter 5. Bayesian PredictionChapter 6. PriorsChapter 7. Multimodel InferenceChapter 8. Hidden Data ModelsChapter 9. Closed-Population Mark-Recapture ModelsChapter 10. Latent MultinomialsChapter 11. Open Population ModelsChapter 12. Individual FitnessChapter 13. Autoregressive Smoothing