发帖
雷达卡
by Donggyu Sul (Author)
About the Author
Donggyu Sul is currently the John Kain Professor of Economics at the University of Texas at Dallas, USA. He specializes in panel data econometrics, international finance, and empirical economic growth, and his articles have been published in numerous major research journals.
About this book
In the last 20 years, econometric theory on panel data has developed rapidly, particularly for analyzing common behaviors among individuals over time. Meanwhile, the statistical methods employed by applied researchers have not kept up-to-date. This book attempts to fill in this gap by teaching researchers how to use the latest panel estimation methods correctly.
Almost all applied economics articles use panel data or panel regressions. However, many empirical results from typical panel data analyses are not correctly executed. This book aims to help applied researchers to run panel regressions correctly and avoid common mistakes. The book explains how to model cross-sectional dependence, how to estimate a few key common variables, and how to identify them. It also provides guidance on how to separate out the long-run relationship and common dynamic and idiosyncratic dynamic relationships from a set of panel data.
Aimed at applied researchers who want to learn about panel data econometrics by running statistical software, this book provides clear guidance and is supported by a full range of online teaching and learning materials. It includes practice sections on MATLAB, STATA, and GAUSS throughout, along with short and simple econometric theories on basic panel regressions for those who are unfamiliar with econometric theory on traditional panel regressions.
Brief contents
1 Basic structure of panel data 1
1.1 Meaning of fixed effect 2
1.1.1 Fixed effects with non-trended data 2
1.1.2 Fixed effects with trended panel data 3
1.2 Meaning of common components 4
1.2.1 Aggregation or macro factor 4
1.2.2 Source of cross-sectional dependence 6
1.2.3 Central location parameter 7
1.3 Meaning of idiosyncratic components 7
2 Statistical models for cross-sectional dependence 10
2.1 Spatial dependence 11
2.2 Gravity model 13
2.3 Common factor approach 15
2.4 Other variations 18
2.4.1 Dynamic factor model 18
2.4.2 Hierarchical factor model 19
3 Factor number identification 20
3.1 A step-by-step procedure for determining the factor number 20
3.2 Information criteria and alternative methods 23
3.3 Standardization and prewhitening 25
3.4 Practice: factor number estimation 27
3.4.1 STATA practice with crime rates 27
3.4.2 STATA practice with price indices 29
3.4.3 Practice with GAUSS 31
3.4.4 Practice with MATLAB 33
4 Decomposition of panel: estimation of common and idiosyncratic components 35
4.1 Measurement of accuracy: order in probability 35
4.2 Estimation of the common factors 36
4.2.1 Cross-sectional average (CSA) approach 37
4.2.2 Principal component estimator 38
4.2.3 Comparison between two estimators for the common factors 40
4.3 Estimation of the idiosyncratic components 42
4.4 Variance decomposition 43
4.5 Cross-sectional dependence and level of aggregation 45
4.5.1 General static factor structure 46
4.5.2 Hierarchical factor structure 49
4.6 Practice: common factors estimation 50
4.6.1 GAUSS practice I: principal component estimation 50
4.6.2 GAUSS practice II: standardization and estimation of PC factors 51
4.6.3 MATLAB practice 52
4.6.4 STATA practice 53
5 Identification of Common Factors 55
5.1 Difference between statistical and latent factors 56
5.2 Asymptotically weak factors approach 58
5.2.1 Single-factor case 59
5.2.2 Multi-factor case 60
5.2.3 Some tips to identify latent factors 62
5.2.4 Application: testing homogeneity of factor loadings 63
5.3 Residual-based approach 64
5.4 Empirical example: exchange rates 65
5.5 Practice: identifying common factors 67
5.5.1 MATLAB practice I: leadership model 67
5.5.2 MATLAB practice II: multiple variables as single factor 70
5.5.3 Practice with GAUSS 71
5.5.4 Practice with STATA 72
6 Static and dynamic relationships 75
6.1 Static and dynamic relationship under cross-sectional independence 76
6.1.1 Spurious cross-sectional regression 77
6.1.2 Spurious pooled OLS estimator 80
6.1.3 Time series and panel-fixed effect regressions 80
6.1.4 Between-group estimator 82
6.2 Static and dynamic relationship under cross-sectional dependence 84
6.2.1 Homogeneous factor loadings 85
6.2.2 Heterogeneous factor loadings: factor-augmented panel regression 87
6.2.3 Cross-sectional regressions with nonstationary common factors 89
6.3 Practice: factor-augmented and aggregation regressions 95
6.3.1 Practice with GAUSS I: common-dynamic relationship 95
6.3.2 Practice with GAUSS II: idio-dynamic relationship 97
6.3.3 Practice with MATLAB 100
6.3.4 Practice with STATA 101
6.4 Appendix: modified between group estimators and an econometric application 101
6.4.1 Appendix A: relationships between the five estimators 101
6.4.2 Appendix B: estimation of static relationships 105
6.4.3 Appendix C: econometric application 107
7 Convergence 110
7.1 β-Convergence: pitfalls of cross-country regressions 111
7.2 Relative convergence 114
7.2.1 Notion of relative convergence 115
7.2.2 How to test: log t regression 115
7.2.3 Clustering algorithm 117
7.2.4 Pitfalls of the log t regression and alternative solutions 118
7.3 σ-Convergence 120
7.4 Empirical example I: household expenditure data from KLIPS 123
7.5 Practice: convergence tests 125
7.5.1 Practice with MATLAB I: weak σ-convergence test 126
7.5.2 Practice with MATLAB II: relative convergence test 128
7.5.3 Practice with GAUSS 130
7.5.4 Practice with STATA 131
8 Appendix: basic panel regressions 134
8.1 Standard two-way fixed effects estimation 134
8.1.1 POLS estimation 134
8.1.2 One-way fixed effect estimation 135
8.1.3 Two-way fixed effect estimation 136
8.2 Valid test statistics 138
8.2.1 Basic inference theory 138
8.2.2 Cross-sectional dependence 139
8.2.3 Solution: use two-way fixed effect 140
8.2.4 Serial dependent panel: use panel robust covariance 141
References 145
Index 149
Pages: 164 pages
Publisher: Routledge; 1 edition (February 25, 2019)
Language: English
ISBN-10: 1138389668
ISBN-13: 978-1138389663
Routledge__Panel Data Econometrics.pdf
(2.18 MB, 需要: 15 个论坛币)
提升卡
置顶卡
沉默卡
变色卡
抢沙发
千斤顶
显身卡
京公网安备 11010802022788号
