The refinement of econometric estimation and test procedures : finite sample and asymptotic analysis

Cover -- Half-title -- Title -- Copyright -- Dedication -- Contents -- List of figures -- List of tables -- List of contributors -- Preface -- Acknowledgements -- Michael Magdalinos 1949-2002 -- Introduction -- 1 Conditional Heteroskedasticity Models with Pearson Family Disturbances -- 1 Introduction -- 2 GARCH with Pearson Family Disturbances -- 3 Sampling Experiments -- 4 Concluding Remarks -- 2 The Instrumental Variables Method Revisited: On the Nature and Choice of Optimal Instruments -- 1 Introduction -- 1.1 Where Do Valid Instruments Come From? -- 2 The Traditional IV Argument, a Summary -- 3 A Statistical Framework for the IVs Method -- 3.1 A Statistical Model -- 3.2 Embedding a Structural into a Statistical Model -- 3.3 The Linking-up Model -- 3.4 Reparameterization/Restriction -- 3.5 Instrumental Variables and Endogeneity/Exogeneity -- 4 The Nature and Choice of Instruments -- 4.1 The "Implicit Reduced Form" -- 4.2 Weak Instruments -- 4.3 Statistical Adequacy and the Reliability of Inference -- 4.4 2SLS as the Quintessential IV Estimator -- 5 The Reliability of IV-based Inference -- 5.1 Testing Overidentifying Restrictions/Instrument Validity -- 5.2 Testing "Exogeneity" -- 6 Conclusions -- 3 Nagar-Type Moment Approximations in Simultaneous Equation Models: Some Further Results -- 1 Introduction -- 2 Model and Notation -- 2.1 An Alternative Approach to Obtaining Approximations for the First and Second Moments -- 3 Main Results -- 3.1 The Bias Approximation -- 3.2 The Second-moment Approximation -- 4 A Simple Simultaneous Equation Model -- 5 Conclusions -- Appendix 1 -- Appendix 2 -- 4 Local GEL Methods for Conditional Moment Restrictions -- 1 Introduction -- 2 The Model -- 3 Estimators -- 3.1 Empirical Probabilities -- 3.2 First-order Conditions -- 4 Asymptotic Theory for Local GEL -- 5 HypothesisTests -- Appendix A: Proofs of Results.