The Refinement of Econometric Estimation and Test Procedures: Finite Sample and Asymptotic Analysis

Cover......Page 1
Half-title......Page 3
Title......Page 5
Copyright......Page 6
Dedication......Page 7
Contents......Page 9
List of figures......Page 13
List of tables......Page 15
List of contributors......Page 17
Preface......Page 19
Acknowledgements......Page 21
Michael Magdalinos 1949–2002......Page 23
Introduction......Page 27
1 Introduction......Page 31
2 GARCH with Pearson Family Disturbances......Page 32
3 Sampling Experiments......Page 38
4 Concluding Remarks......Page 63
1 Introduction......Page 64
1.1 Where Do Valid Instruments Come From?......Page 65
2 The Traditional IV Argument, a Summary......Page 66
3.1 A Statistical Model......Page 69
3.2 Embedding a Structural into a Statistical Model......Page 70
3.3 The Linking-up Model......Page 72
3.4 Reparameterization/Restriction......Page 73
3.5 Instrumental Variables and Endogeneity/Exogeneity......Page 75
4.1 The “Implicit Reduced Form”......Page 77
4.2 Weak Instruments......Page 79
4.3 Statistical Adequacy and the Reliability of Inference......Page 80
4.4 2SLS as the Quintessential IV Estimator......Page 83
5 The Reliability of IV-based Inference......Page 85
5.1 Testing Overidentifying Restrictions/Instrument Validity......Page 86
5.2 Testing “Exogeneity”......Page 88
6 Conclusions......Page 89
1 Introduction......Page 90
2 Model and Notation......Page 91
2.1 An Alternative Approach to Obtaining Approximations for the First and Second Moments......Page 95
3 Main Results......Page 97
3.1 The Bias Approximation......Page 98
3.2 The Second-moment Approximation......Page 100
4 A Simple Simultaneous Equation Model......Page 103
5 Conclusions......Page 106
Appendix 1......Page 107
Appendix 2......Page 108
1 Introduction......Page 130
2 The Model......Page 132
3 Estimators......Page 133
3.1 Empirical Probabilities......Page 135
3.2 First-order Conditions......Page 136
4 Asymptotic Theory for Local GEL......Page 137
5 HypothesisTests......Page 139
Appendix A: Proofs of Results......Page 140
Appendix B: Auxiliary Results......Page 147
1 Introduction......Page 153
2 Moderate Deviations with i.i.d. Errors......Page 155
3 Moderate Deviations from Unity with Weakly Dependent Errors......Page 156
4 Limit Theory for the Near Stationary Case......Page 160
4.1 Remarks......Page 165
4.2 Remarks......Page 167
4.3 The Stationary Case......Page 169
5 Limit Theory for the Near Explosive Case......Page 170
5.1 Remarks......Page 175
5.2 The Explosive Case......Page 176
6 Discussion......Page 179
Appendix and Proofs......Page 180
2 Likelihood-based Inference......Page 193
3 Main Results......Page 194
4 Comments......Page 196
Appendix:The Derivations......Page 197
1 Introduction......Page 203
2.1 Notation and Assumptions......Page 204
2.2 The t Test......Page 207
2.3 The F Test......Page 209
3 Cornish–Fisher Corrected t and v-statistics for a Parametric Model of Heteroscedasticity......Page 212
4 Simulation Experiments......Page 216
5 Empirical Example: Productivity Gains from in-company Training......Page 221
Notes......Page 228
Appendix......Page 229
1 Introduction......Page 235
2 The Test Statistic and Its Asymptotic Distribution......Page 236
3 Monte Carlo Results......Page 239
Appendix A......Page 241
Appendix B......Page 248
1 Introduction......Page 250
2 Derivation of the Test Statistic......Page 251
3 An Alternative Test when the δ Test Fails......Page 256
4 Diagonal R......Page 259
1 Introduction......Page 269
2 Panel Data Models with Observed and Unobserved Common Effects......Page 272
3 A Principal Components Augmentation Approach......Page 276
4.1 Monte Carlo Design......Page 278
4.2 Alternative Estimators Considered......Page 283
4.3 Monte Carlo Results......Page 285
5 An Empirical Application......Page 303
6 Conclusions......Page 311
1 Introduction......Page 312
2 Rules for Simulation Contests......Page 314
2.1 Methodologic Aspirations for an Adequate and Impartial Design of Simulation Studies that Aim to Rank Various Alternative Inference Techniques......Page 315
3 Initial Conditions......Page 318
4.1 Generic Framework......Page 321
4.2 Instruments for Panel AR(1) Models......Page 323
4.3 Weight Matrices......Page 326
5 A Limited Monte Carlo Contest......Page 330
5.1 An Orthogonal Monte Carlo Design......Page 331
5.2 Some New Monte Carlo Findings......Page 334
6 Concluding Remarks......Page 344
Notes......Page 347
1 Introduction......Page 349
2 The Transformation Theorem......Page 350
3 A Statistical Proof, Using Conditioning and Induction......Page 351
1 Introduction......Page 356
2.1 Simplifications......Page 359
2.2 The Regular Simplex......Page 360
2.3 Surface Integration......Page 362
3 Main Results......Page 364
4 Example: Censored Normal Model......Page 372
1 Introduction......Page 377
2.1 DGP......Page 379
2.3 Closed and Open Models......Page 380
2.4 Stationary VAR......Page 381
3.1 Impulse Response Analysis......Page 385
3.2 Dynamic Multiplier Analysis......Page 389
3.3 Stationary Example......Page 390
4 Response Analysis in a Non-stationary VAR......Page 392
4.1 Non-stationary Example......Page 395
5 Conclusion......Page 397
References......Page 398
Index......Page 415