| Introduction: basic notions about Bayesian inference | p. 1 |
| Basic notions | p. 2 |
| Simple dependence structures | p. 5 |
| Synthesis of conditional distributions | p. 11 |
| Choice of the prior distribution | p. 14 |
| Bayesian inference in the linear regression model | p. 18 |
| Markov chain Monte Carlo methods | p. 22 |
| Gibbs sampler | p. 24 |
| Metropolis-Hastings algorithm | p. 24 |
| Adaptive rejection Metropolis sampling | p. 25 |
| Problems | p. 29 |
| Dynamic linear models | p. 31 |
| Introduction | p. 31 |
| A simple example | p. 35 |
| State space models | p. 39 |
| Dynamic linear models | p. 41 |
| Dynamic linear models in package dlm | p. 43 |
| Examples of nonlinear and non-Gaussian state space models | p. 48 |
| State estimation and forecasting | p. 49 |
| Filtering | p. 51 |
| Kalman filter for dynamic linear models | p. 53 |
| Filtering with missing observations | p. 59 |
| Smoothing | p. 60 |
| Forecasting | p. 66 |
| The innovation process and model checking | p. 73 |
| Controllability and observability of time-invariant DLMs | p. 77 |
| Filter stability | p. 80 |
| Problems | p. 83 |
| Model specification | p. 85 |
| Classical tools for time series analysis | p. 85 |
| Empirical methods | p. 85 |
| ARIMA models | p. 87 |
| Univariate DLMs for time series analysis | p. 88 |
| Trend models | p. 89 |
| Seasonal factor models | p. 100 |
| Fourier form seasonal models | p. 102 |
| General periodic components | p. 109 |
| DLM representation of ARIMA models | p. 112 |
| Example: estimating the output gap | p. 115 |
| Regression models | p. 121 |
| Models for multivariate time series | p. 125 |
| DLMs for longitudinal data | p. 126 |
| Seemingly unrelated time series equations | p. 127 |
| Seemingly unrelated regression models | p. 132 |
| Hierarchical DLMs | p. 134 |
| Dynamic regression | p. 136 |
| Common factors | p. 138 |
| Multivariate ARMA models | p. 139 |
| Problems | p. 142 |
| Models with unknown parameters | p. 143 |
| Maximum likelihood estimation | p. 144 |
| Bayesian inference | p. 148 |
| Conjugate Bayesian inference | p. 149 |
| Unknown covariance matrices: conjugate inference | p. 150 |
| Specification of Wt by discount factors | p. 152 |
| A discount factor model for time-varying Vt | p. 158 |
| Simulation-based Bayesian inference | p. 160 |
| Drawing the states given y1:T: forward filtering backward sampling | p. 161 |
| General strategies for MCMC | p. 162 |
| Illustration: Gibbs sampling for a local level model | p. 165 |
| Unknown variances | p. 167 |
| Constant unknown variances: d Inverse Gamma Prior | p. 167 |
| Multivariate extensions | p. 171 |
| A model for outliers and structural breaks | p. 177 |
| Further examples | p. 186 |
| Estimating the output gap: Bayesian inference | p. 186 |
| Dynamic regression | p. 192 |
| Factor models | p. 200 |
| Problems | p. 206 |
| Sequential Monte Carlo methods | p. 207 |
| The basic particle filter | p. 208 |
| A simple example | p. 213 |
| Auxiliary particle filter | p. 216 |
| Sequential Monte Carlo with unknown parameters | p. 219 |
| A simple example with unknown parameters | p. 226 |
| Concluding remarks | p. 228 |
| Useful distributions | p. 231 |
| Matrix algebra: Singular Value Decomposition | p. 237 |
| Index | p. 241 |
| References | p. 245 |
| Table of Contents provided by Ingram. All Rights Reserved. |
