| |
| |
Preface | |
| |
| |
Introduction to Bayesian Statistics | |
| |
| |
The Frequentist Approach to Statistics | |
| |
| |
The Bayesian Approach to Statistics | |
| |
| |
Comparing Likelihood and Bayesian Approaches to Statistics | |
| |
| |
Computational Bayesian Statistics | |
| |
| |
Purpose and Organization of This Book | |
| |
| |
Monte Carlo Sampling from the Posterior | |
| |
| |
Acceptance-Rejection-Sampling | |
| |
| |
Sampling-Importance-Resampling | |
| |
| |
Adaptive-Rejection-Sampling from a Log-Concave Distribution | |
| |
| |
Why Direct Methods Are Inefficient for High-Dimension Parameter Space | |
| |
| |
Bayesian Inference | |
| |
| |
Bayesian Inference from the Numerical Posterior | |
| |
| |
Bayesian Inference from Posterior Random Sample | |
| |
| |
Bayesian Statistics Using Conjugate Priors | |
| |
| |
One-Dimensional Exponential Family of Densities | |
| |
| |
Distributions for Count Data | |
| |
| |
Distributions for Waiting Times | |
| |
| |
Normally Distributed Observations with Known Variance | |
| |
| |
Normally Distributed Observations with Known Mean | |
| |
| |
Normally Distributed Observations with Unknown Mean and Variance | |
| |
| |
Multivariate Normal Observations with Known Covariance Matrix | |
| |
| |
Observations from Normal Linear Regression Model | |
| |
| |
Appendix: Proof of Poisson Process Theorem | |
| |
| |
Markov Chains | |
| |
| |
Stochastic Processes | |
| |
| |
Markov Chains | |
| |
| |
Time-Invariant Markov Chains with Finite State Space | |
| |
| |
Classification of States of a Markov Chain | |
| |
| |
Sampling from a Markov Chain | |
| |
| |
Time-Reversible Markov Chains and Detailed-Balance | |
| |
| |
Markov Chains with Continuous State Space | |
| |
| |
Markov Chain Monte Carlo Sampling from Posterior | |
| |
| |
Metropolis-Hastings Algorithm for a Single Parameter | |
| |
| |
Metropolis-Hastings Algorithm for Multiple Parameters | |
| |
| |
Blockwise Metropolis Hastings Algorithm | |
| |
| |
Gibbs Sampling | |
| |
| |
Summary | |
| |
| |
Statistical Inference from a Markov Chain Monte Carlo Sample | |
| |
| |
Mixing Properties of the Chain | |
| |
| |
Finding a Heavy-Tailed Matched Curvature Candidate Density | |
| |
| |
Obtaining An Approximate Random Sample For Inference | |
| |
| |
Appendix: Procedure for Finding the Matched Curvature Candidate Density for a Multivariate Parameter | |
| |
| |
Logistic Regression | |
| |
| |
Logistic Regression Model | |
| |
| |
Computational Bayesian Approach to the Logistic Regression Model | |
| |
| |
Modelling with the Multiple Logistic Regression Model | |
| |
| |
Poisson Regression and Proportional Hazards Model | |
| |
| |
Poisson Regression Model | |
| |
| |
Computational Approach to Poisson Regression Model | |
| |
| |
The Proportional Hazards Model | |
| |
| |
Computational Bayesian Approach to Proportional Hazards Model | |
| |
| |
Gibbs Sampling and Hierarchical Models | |
| |
| |
Gibbs Sampling Procedure | |
| |
| |
The Gibbs Sampler for the Normal Distribution | |
| |
| |
Hierarchical Models and Gibbs Sampling | |
| |
| |
Modelling Related Populations with Hierarchical Models | |
| |
| |
Appendix: Proof That Improper Jeffrey's Prior Distribution for the Hypervariance Can Lead to an Improper Posterior | |
| |
| |
Going Forward with Markov Chain Monte Carlo | |
| |
| |
Using the Included Minitab Macros | |
| |
| |
Using the Included R Functions | |
| |
| |
References | |
| |
| |
Topic Index | |