Panel Data Econometrics with R

Panel Data Econometrics with R provides a tutorial for using R in the field of panel data econometrics. Illustrated throughout with examples in econometrics, political science, agriculture and epidemiology, this book presents classic methodology and applications as well as more advanced topics and recent developments in this field including error component models, spatial panels and dynamic models. They have developed the software programming in R and host replicable material on the book's accompanying website.

Autorentext

Yves Croissant, Professor of Economics, CEMOI, Faculté de Droit et d'Economie, Université de La Réunion, France Giovanni Millo, Senior Economist, Group Insurance Research, Assicurazioni Generali S.p.A., Trieste, Italy

Klappentext
Panel Data Econometrics with R A practical guide to using R in the growing field of panel data econometrics This book serves as a tutorial for using R in the field of panel data econometrics, illustrated throughout with examples in econometrics, political science, agriculture and ecology. It presents classic methodology and applications as well as more advanced topics and recent developments in this field including spatial panels, dynamic and generalised linear models. Software procedures are presented at a basic level to provide access to the casual R users. More advanced users will appreciate the scalability of the software and find directions towards more sophisticated operation, exploiting the functional nature of R and its object-orientation features. Key features: Panel data econometrics is explained in a rigorous but practical way A rich collection of fully reproducible examples features throughout Written by the authors of the well-known 'plm' package for R Covers the basics of panel data econometrics as taught in graduate econometrics classes Includes datasets with examples in econometrics, political science, agriculture and ecology Supported by accompanying website featuring R code, examples, replicable material and instructor materials Enriched by a wide collection of examples, Panel Data Econometrics with R can be a practical companion to advanced textbooks as well as a primary reference text for practitioners. The techniques covered will also appeal to many social and natural scientists beside economists.

Inhalt

Preface xiii Acknowledgments xvii About the CompanionWebsite xix 1 Introduction 1 1.1 Panel Data Econometrics: A Gentle Introduction 1 1.1.1 Eliminating Unobserved Components 2 1.1.1.1 Differencing Methods 2 1.1.1.2 LSDV Methods 2 1.1.1.3 Fixed Effects Methods 2 1.2 R for Econometric Computing 6 1.2.1 The Modus Operandi of R 7 1.2.2 Data Management 8 1.2.2.1 Outsourcing to Other Software 8 1.2.2.2 Data ManagementThrough Formulae 8 1.3 plm for the Casual R User 8 1.3.1 R for the Matrix Language User 9 1.3.2 R for the User of Econometric Packages 10 1.4 plm for the Proficient R User 11 1.4.1 Reproducible EconometricWork 12 1.4.2 Object-orientation for the User 13 1.5 plm for the R Developer 13 1.5.1 Object-orientation for Development 14 1.6 Notations 17 1.6.1 General Notation 18 1.6.2 Maximum Likelihood Notations 18 1.6.3 Index 18 1.6.4 The Two-way Error Component Model 18 1.6.5 Transformation for the One-way Error Component Model 19 1.6.6 Transformation for the Two-ways Error Component Model 20 1.6.7 Groups and Nested Models 20 1.6.8 Instrumental Variables 20 1.6.9 Systems of Equations 20 1.6.10 Time Series 21 1.6.11 Limited Dependent and Count Variables 21 1.6.12 Spatial Panels 21 2 The Error Component Model 23 2.1 Notations and Hypotheses 23 2.1.1 Notations 23 2.1.2 Some Useful Transformations 24 2.1.3 Hypotheses Concerning the Errors 25 2.2 Ordinary Least Squares Estimators 27 2.2.1 Ordinary Least Squares on the Raw Data: The Pooling Model 27 2.2.2 The between Estimator 28 2.2.3 The within Estimator 29 2.3 The Generalized Least Squares Estimator 33 2.3.1 Presentation of the GLS Estimator 34 2.3.2 Estimation of the Variances of the Components of the Error 35 2.4 Comparison of the Estimators 39 2.4.1 Relations between the Estimators 39 2.4.2 Comparison of the Variances 40 2.4.3 Fixed vs Random Effects 40 2.4.4 Some Simple Linear Model Examples 42 2.5 The Two-ways Error Components Model 47 2.5.1 Error Components in the Two-ways Model 47 2.5.2 Fixed and Random Effects Models 48 2.6 Estimation of a Wage Equation 49 3 Advanced Error Components Models 53 3.1 Unbalanced Panels 53 3.1.1 Individual Effects Model 53 3.1.2 Two-ways Error Component Model 54 3.1.2.1 Fixed Effects Model 55 3.1.2.2 Random Effects Model 56 3.1.3 Estimation of the Components of the Error Variance 57 3.2 Seemingly Unrelated Regression 64 3.2.1 Introduction 64 3.2.2 Constrained Least Squares 65 3.2.3 Inter-equations Correlation 66 3.2.4 SUR With Panel Data 67 3.3 The Maximum Likelihood Estimator 71 3.3.1 Derivation of the Likelihood Function 71 3.3.2 Computation of the Estimator 73 3.4 The Nested Error Components Model 74 3.4.1 Presentation of the Model 74 3.4.2 Estimation of the Variance of the Error Components 75 4 Tests on Error Component Models 83 4.1 Tests on Individual and/or Time Effects 83 4.1.1 F Tests 84 4.1.2 Breusch-Pagan Tests 84 4.2 Tests for Correlated Effects 88 4.2.1 The Mundlak Approach 89 4.2.2 Hausman Test 90 4.2.3 Chamberlain's Approach 90 4.2.3.1 Unconstrained Estimator 91 4.2.3.2 Constrained Estimator 93 4.2.3.3 Fixed Effects Models 93 4.3 Tests for Serial Correlation 95 4.3.1 Unobserved Effects Test 95 4.3.2 Score Test of Serial Correlation and/or Individual Effects 96 4.3.3 Likelihood Ratio Tests for AR(1) and Individual Effects 99 4.3.4 Applying Traditional Serial Correlation Tests to Panel Data 101 4.3.5 Wald Tests for Serial Correlation using within and First-differenced Estimators 102 4.3.5.1 Wooldridge's within-based Test 102 4.3.5.2 Wooldridge's First-difference-based Test 103 4.4 Tests for Cross-sectional Dependence 104 4.4.1 Pairwise Correlation Coefficients 104 4.4.2 CD-type Tests for Cross-sectional Dependence 105 4.4.3 Testing Cross-sectional Dependence in a pseries 107 5 Robust Inference and Estimation for Non-spherical Errors 109 5.1 Robust Inference 109 5.1.1 Robust Covariance Estimators 109 5.1.1.1 Cluster-robust Estimation in a Panel Setting 110 5.1.1.2 Double Clustering 115 5.1.1.3 Panel Newey-west and SCC 116 5.1.2 Generic Sandwich Estimators and Panel Models 120 5.1.2.1 Panel Corrected Standard Errors 122 5.1.3 Robust Testing of Linear Hypotheses 123 5.1.3.1 An Application: Robust Hausman Testing 125 5.2 Unrestricted Generalized Least Squares 127 5.2.1 General Feasible Generalized Least Squares 128 5.2.1.1 Pooled GGLS 129 5.2.1.2 Fixed Effects GLS 130 5.2.1.3 First Difference GLS 132 5.2.2 Applied Examples 133 6 Endogeneity 139 6.1 Introduction 139 6.2 The Instrumental Variables Estimator 140 6.2.1 Generalities about the Instrumental Variables Estimator 140 6.2.2 The within Instrumental Variables Estimator 141 6.3 Error Components Instrumental Variables Estimator 143 6.3.1 The General Model 143 6.3.2 Special Cases of the General Model 145 6.3.2.1 The within Model 145 6.3.2.2 Error Components Two Stage Least Squares 146 6.3.2.3 The Hausman and Taylor Model 146 6.3.2.4 The Amemiya-Macurdy Estimator 147 6.3.2.5 The Breusch, Mizon and Schmidt's Estimator 147 6.3.2.6 Balestra and Varadharajan-Krishnakumar Estimator 147 6.4 Estimation of a System of Equations 154 6.4.1 TheThree Stage Least Squares Estimator 155 6.4.2 The Error Components Three Stage Least Squares Estimator 156 6.5 More Empirical Examples 158 7 Estimation of a Dynamic Model 161 7.1 Dynamic Model and Endogeneity 163 7.1.1 The Bias of the ols Estimator 163 7.1.2 The within Estimator 164 7.1.3 Consistent Estimation Methods for Dynamic Models 165 7.2 GMM Estimation of the Differenced Model 168 7.2.1 Instrumental Variables and Generalized Method of Moments 168 7.2.2 One-step Estimator 169 7.2.3 Two-steps Estimator 171 7.2.4 The Proliferation of I…