DescriptionWritten by one of the world's leading researchers and writers in the field, Econometric Analysis of Panel Data has become established as the leading textbook for postgraduate courses in panel data. This new edition reflects the rapid developments in the field covering the vast research that has been conducted on panel data since its initial publication. Featuring the most recent empirical examples from panel data literature, data sets are also provided as well as the programs to implement the estimation and testing procedures described in the book. These programs will be made available via an accompanying website which will also contain solutions to end of chapter exercises that will appear in the book.
The text has been fully updated with new material on dynamic panel data models and recent results on non-linear panel models and in particular work on limited dependent variables panel data models.
1 Introduction 1
1.1 Panel Data: Some Examples 1
1.2 Why Should We Use Panel Data? Their Benefits and Limitations 6
2 The One-way Error Component Regression Model 13
2.1 Introduction 13
2.2 The Fixed Effects Model 14
2.3 The Random Effects Model 17
2.4 Maximum Likelihood Estimation 22
2.5 Prediction 23
2.6 Examples 24
2.7 Selected Applications 31
2.8 Computational Note 31
3 The Two-way Error Component Regression Model 35
3.1 Introduction 35
3.2 The Fixed Effects Model 35
3.3 The Random Effects Model 37
3.4 Maximum Likelihood Estimation 42
3.5 Prediction 44
3.6 Examples 45
3.7 Selected Applications 48
4 Test of Hypotheses with Panel Data 57
4.1 Tests for Poolability of the Data 57
4.2 Tests for Individual and Time Effects 63
4.3 Hausman's Specification Test 72
4.4 Further Reading 81
5 Heteroskedasticity and Serial Correlation in the Error Component Model 87
5.1 Heteroskedasticity 87
5.2 Serial Correlation 92
6 Seemingly Unrelated Regressions with Error Components 115
6.1 The One-way Model 115
6.2 The Two-way Model 116
6.3 Applications and Extensions 117
7 Simultaneous Equations with Error Components 121
7.1 Single Equation Estimation 121
7.2 Empirical Example: Crime in North Carolina 124
7.3 System Estimation 130
7.4 The Hausman and Taylor Estimator 133
7.5 Empirical Example: Earnings Equation Using PSID Data 136
7.6 Further Reading and Extensions 140
8 Dynamic Panel Data Models 147
8.1 Introduction 147
8.2 The Arellano and Bond Estimator 149
8.3 The Arellano and Bover Estimator 155
8.4 The Ahn and Schmidt Moment Conditions 158
8.5 The Blundell and Bond System GMM Estimator 160
8.6 The Keane and Runkle Estimator 162
8.7 Further Developments 164
8.8 Empirical Examples 170
8.9 Further Reading 173
9 Unbalanced Panel Data Models 181
9.1 Introduction 181
9.2 The Unbalanced One-way Error Component Model 181
9.3 Empirical Example: Hedonic Housing 187
9.4 The Unbalanced Two-way Error Component Model 191
9.5 Testing for Individual and Time Effects Using Unbalanced Panel Data 193
9.6 The Unbalanced Nested Error Component Model 196
10 Special Topics 205
10.1 Measurement Error and Panel Data 205
10.2 Rotating Panels 208
10.3 Pseudo-panels 210
10.4 Alternative Methods of Pooling Time Series of Cross-Section Data 214
10.5 Spatial Panels 216
10.6 Short-run vs. Long-run Estimates in Pooled Models 219
10.7 Heterogeneous Panels 220
10.8 Count Panel Data 226
11 Limited Dependent Variables and Panel Data 237
11.1 Fixed and Random Logit and Probit Models 237
11.2 Simulation Estimation of Limited Dependent Variable Models with Panel Data 245
11.3 Dynamic Panel Data Limited Dependent Variable Models 246
11.4 Selection Bias in Panel Data 251
11.5 Censored and Truncated Panel Data Models 256
11.6 Empirical Applications 260
11.7 Empirical Example: Nurses Labor Supply 262
11.8 Further Reading 266
12 Nonstationary Panels 273
12.1 Introduction 273
12.2 Panel Unit Roots Tests Assuming Cross-sectional Independence 275
12.3 Panel Unit Roots Tests Allowing for Cross-sectional Dependence 284
12.4 Spurious Regression in Panel Data 287
12.5 Panel Cointegration Tests 292
12.6 Estimation and Inference in Panel Cointegration Models 298
12.7 Empirical Example: Purchasing Power Parity 301
12.8 Further Reading 303
- Includes most recent empirical examples from panel data literature. For example, a simultaneous equation on Crime will be added to chapter 7, which will be illustrated with STATA.
- Chapter 12 on nonstationary panels will be totally rewritten, including an empirical illustration on the purchasing power parity literature and illustrated with EViews.
- Data sets will be provided as well as the programs to implement the estimation and testing procedures described in the book on the web site. Additional exercises will be added to each chapter and their solutions will be provided on the web site .
- The third edition will also update the panel data literature using newly published papers on dynamic panel data models (see chapter 8) and recent results on non-linear panel models and in particular work on limited dependent variables panel data models (see chapter 11). An empirical example using mortgage lending data is illustrated using STATA. The material on heteroskedasticity in panels (see chapter 5) is completely revised and updated with recent estimation and testing results. Other sections that will be updated include unbalanced panels (chapter 9), pseudo panels, heterogeneous panels and spatial panels
- Emphasis will be placed on the applications and the motivation for these methods and the reader will be referred to the corresponding article for technical details.
- A web site will be developed containing supplementary materials for lecturers
- Revision of established textbook by one of the leading international researchers and writers on panel data
"This is a definitive book written by one of the architects of modern, panel data econometrics. It provides both a practical introduction to the subject matter, as well as a thorough discussion of the underlying statistical principles without taxing the reader too greatly. Since its first publication in 1995, it has quickly become a standard accompanying text in advanced econometrics courses around the world, and a major reference for researchers doing empirical work with longitudinal data."
Professor Kajal Lahiri, State University of New York, Albany, USA.
"Econometric Analysis of Panel Dta is a classic in its field, used by researchers and graduate students throughout the world. In this new edition, Professor Baltagi has incorporated extensive new material, reflecting recent advances in the panel data literature in areas such as dynamic (including non-stationary) and limited dependent variable panel data models. It is an invaluable read for anyone interested in panel data."
Professor Gary Koop, University of Strathclyde, UK.
"Panel data econometrics is in its ascendancy, combining the power of cross section averaging with all the subtleties of temporal and spatial dependence. Badi Baltagi provides a remarkable roadmap of this fascinating interface of econometric method, enticing the novitiate with technical gentleness, the expert with comprehensive coverage and the practitioner with many empirical applications."
Professor Peter C.B. Phillips, Cowles Foundation, Yale University, USA.
"This book is the most comprehensive work available on panel data. It is written by one of the leading contributors to the field, and is notable for its encyclopedic coverage and its clarity of exposition. It is useful to theorists and to people doing applied work using panel data. It is valuable as a text for a course in panel data, as a supplementary text for more general courses in econometrics, and as a reference."
Professor Peter Schmidt, Michigan State University, USA.
"In this new edition Baltagi covers many of the recent developments in the literature on econometric analysis of panel data models. It is aimed at graduate students but many of its introductory chapters could also be helpful to advanced undergraduates and applied researchers across many disciplines including economics, finance, sociology, and politics. Baltagi has a gift explaining difficult concepts and ideas in a simple language, accessible to researchers and students alike. It is a timely and welcome addition to a growing literature."
Professor M. Hashem Pesaran, University of Cambridge, and USC.