| |
| |
Foreword | |
| |
| |
Preface | |
| |
| |
| |
Introduction | |
| |
| |
| |
Advantages of the Bayesian Approach to Statistics | |
| |
| |
| |
So Why Then Isn't Everyone a Bayesian? | |
| |
| |
| |
WinBUGS | |
| |
| |
| |
Why This Book? | |
| |
| |
| |
What This Book Is Not About: Theory of Bayesian Statistics and Computation | |
| |
| |
| |
Further Reading | |
| |
| |
| |
Summary | |
| |
| |
| |
Introduction to the Bayesian Analysis of a Statistical Model | |
| |
| |
| |
Probability Theory and Statistics | |
| |
| |
| |
Two Views of Statistics: Classical and Bayesian | |
| |
| |
| |
The Importance of Modem Algorithms and Computers for Bayesian Statistics | |
| |
| |
| |
Markov chain Monte Carlo (MCMC) and Gibbs Sampling | |
| |
| |
| |
What Comes after MCMC? | |
| |
| |
| |
Some Shared Challenges in the Bayesian and the Classical Analysis of a Statistical Model | |
| |
| |
| |
Pointer to Special Topics in This Book | |
| |
| |
| |
Summary | |
| |
| |
| |
WinBUGS | |
| |
| |
| |
What Is WinBUGS? | |
| |
| |
| |
Running WinBUGS from R | |
| |
| |
| |
WinBUGS Frees the Modeler in You | |
| |
| |
| |
Some Technicalities and Conventions | |
| |
| |
| |
A First Session in WinBUGS: The �Model of the Mean� | |
| |
| |
| |
Introduction | |
| |
| |
| |
Setting Up the Analysis | |
| |
| |
| |
Starting the MCMC blackbox | |
| |
| |
| |
Summarizing the Results | |
| |
| |
| |
Summary | |
| |
| |
| |
Running WinBUGS from R via R2WinBUGS | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Using R | |
| |
| |
| |
Analysis Using WinBUGS | |
| |
| |
| |
Summary | |
| |
| |
| |
Key Components of (Generalized) Linear Models: Statistical Distributions and the Linear Predictor | |
| |
| |
| |
Introduction | |
| |
| |
| |
Stochastic Part of Linear Models: Statistical Distributions | |
| |
| |
| |
Deterministic Part of Linear Models: Linear Predictor and Design Matrices | |
| |
| |
| |
Summary | |
| |
| |
| |
t-Test: Equal and Unequal Variances | |
| |
| |
| |
t-Test with Equal Variances | |
| |
| |
| |
t-Test with Unequal Variances | |
| |
| |
| |
Summary and a Comment on the Modeling of Variances | |
| |
| |
| |
Normal Linear Regression | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Using R | |
| |
| |
| |
Analysis Using WinBUGS | |
| |
| |
| |
Summary | |
| |
| |
| |
Normal One-Way ANOVA | |
| |
| |
| |
Introduction: Fixed and Random Effects | |
| |
| |
| |
Fixed-Effects ANOVA | |
| |
| |
| |
Random-Effects ANOVA | |
| |
| |
| |
Summary | |
| |
| |
| |
Normal Two-Way ANOVA | |
| |
| |
| |
Introduction: Main and Interaction Effects | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Aside: Using Simulation to Assess Bias and Precision of an Estimator | |
| |
| |
| |
Analysis Using R | |
| |
| |
| |
Analysis Using WinBUGS | |
| |
| |
| |
Summary | |
| |
| |
| |
General Linear Model (ANCOVA) | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Using R | |
| |
| |
| |
Analysis Using WinBUGS (and a Cautionary Tale About the Importance of Covaviate Standardization) | |
| |
| |
| |
Summary | |
| |
| |
| |
Linear Mixed-Effects Model | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Under a Random-Intercepts Model | |
| |
| |
| |
Analysis Under a Random-Coefficients Model without Correlation between Intercept and Slope | |
| |
| |
| |
The Random-Coefficients Model with Correlation between Intercept and Slope | |
| |
| |
| |
Summary | |
| |
| |
| |
Introduction to the Generalized Linear Model: Poisson �t-test� | |
| |
| |
| |
Introduction | |
| |
| |
| |
An Important but Often Forgotten Issue with Count Data | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Using R | |
| |
| |
| |
Analysis Using WinBUGS | |
| |
| |
| |
Summary | |
| |
| |
| |
Overdispersion, Zero-Inflation, and Offsets in the GLM | |
| |
| |
| |
Overdispersion | |
| |
| |
| |
Zero-Inflation | |
| |
| |
| |
Offsets | |
| |
| |
| |
Summary | |
| |
| |
| |
Poisson ANCOVA | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Using R | |
| |
| |
| |
Analysis Using WinBUGS | |
| |
| |
| |
Summary | |
| |
| |
| |
Poisson Mixed-Effects Model (Poisson GLMM) | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Under a Random-Coefficients Model | |
| |
| |
| |
Summary | |
| |
| |
| |
Binomial �t-Test� | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Using R | |
| |
| |
| |
Analysis Using WinBUGS | |
| |
| |
| |
Summary | |
| |
| |
| |
Binomial Analysis of Covariance | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Using R | |
| |
| |
| |
Analysis Using WinBUGS | |
| |
| |
| |
Summary | |
| |
| |
| |
Binomial Mixed-Effects Model (Binomial GLMM) | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Under a Random-Coefficients Model | |
| |
| |
| |
Summary | |
| |
| |
| |
Nonstandard GLMMs 1: Site-Occupancy Species Distribution Model | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Using WinBUGS | |
| |
| |
| |
Summary | |
| |
| |
| |
Nonstandard GLMMs 2: Binomial Mixture Model to Model Abundance | |
| |
| |
| |
Introduction | |
| |
| |
| |
Data Generation | |
| |
| |
| |
Analysis Using WinBUGS | |
| |
| |
| |
Summary | |
| |
| |
| |
Conclusions | |
| |
| |
Appendix | |
| |
| |
References | |
| |
| |
Index | |