Complete and Incomplete Econometric Models

John Geweke is Distinguished Research Professor at the University of Technology Sydney, and research professor at the University of Colorado. He is the coeditor of the "Journal of Econometrics" and his most recent previous book is "Contemporary Bayesian Econometrics and Statistics" (Wiley).

"This book is original and powerful. It develops a Bayesian paradigm that embraces the reality of applied modeling, in which 'discoveries' of things previously unimagined are made regularly. It will be of immediate interest to all economists and statisticians who want to push Bayesian principles toward innovative practice (and who doesn't?)."—Francis X. Diebold, University of Pennsylvania

• Series Editors' Introduction vii Preface ix Chapter 1: Introduction 1 Chapter 2: The Bayesian Paradigm 7 2.1 Complete Models 10 2.2 Model Comparison and Averaging 16 2.3 Simulation 19 2.4 Model Evaluation 23 Chapter 3: Prior Predictive Analysis and Model Evaluation 34 3.1 Data and Models 35 3.2 Prior Predictive Analysis 47 3.3 Comparison with an Incomplete Model 71 3.4 Appendix: A Gaussian Copula for Evaluating Predictive Densities of Vector Functions of Interest 84 Chapter 4: Incomplete Structural Models 86 4.1 The Essential Elements of DSGE Models 88 4.2 Strong Econometric Interpretation 95 4.3 Weak Econometric Interpretation 98 4.4 Minimal Econometric Interpretation 109 4.5 Implications for Structural Modeling 118 Chapter 5: An Incomplete Model Space 122 5.1 Context and Motivation 123 5.2 Pools of Two Models 130 5.3 Examples of Two-Model Pools 135 5.4 Pools of Multiple Models 142 5.5 Multiple-Model Pools: An Example 150 5.6 Pooling and Model Improvement 155 5.7 Consequences of an Incomplete Model Space 158 References 161