Table of Contents
Preface
1 Introduction
1.1 Panel Data: Some Examples
1.1.1 Examples of Micro-panels
1.1.2 Examples of Macro-panels
1.1.3 Some Basic References
1.2 Why Should We Use Panel Data? Their Benefits and Limitations
1.3 Note
References
2 The One-Way Error Component Regression Model
2.1 Introduction
2.2 The One-Way Fixed Effects Model
2.3 The One-Way Random Effects Model
2.4 Maximum Likelihood Estimation
2.5 Prediction
2.6 Examples
2.6.1 Example 1: Investment Equation
2.6.2 Example 2: Gasoline Demand Equation
2.6.3 Example 3: Public Capital Productivity
2.7 Selected Applications
2.8 Computational Note
2.9 Notes
2.10 Problems
References
3 The Two-Way Error Component Regression Model
3.1 Introduction
3.2 The Two-Way Fixed Effects Model
3.2.1 Testing for Fixed Effects
3.3 The Two-Way Random Effects Model
3.3.1 Monte Carlo Results
3.4 Maximum Likelihood Estimation
3.5 Prediction
3.6 Examples
3.6.1 Example 1: Investment Equation
3.6.2 Example 2: Gasoline Demand Equation
3.6.3 Example 3: Public Capital Productivity
3.7 Computational Note
3.8 Notes
3.9 Problems
References
4 Test of Hypotheses with Panel Data
4.1 Tests for Poolability
4.1.1 Test for Poolability u~N(0,σ2INT)
4.1.2 Test for Poolability Under the General Assumption u~N(0,Ω)
4.1.3 Examples
4.2 Tests for Individual and Time Effects
4.2.1 The Breusch—Pagan Test
4.2.2 Honda, King and Wu, and the Standardized Lagrange Multiplier Tests
4.2.3 Gourieroux, Holly and Monfort Test
4.2.4 Conditional LM Tests
4.2.5 ANOVA F and the Likelihood Ratio Tests
4.2.6 Monte Carlo Results
4.2.7 An Illustrative Example
4.3 Hausman's Specification Test
4.3.1 Example 1: Investment Equation
4.3.2 Example 2: Gasoline Demand Equation
4.3.3 Example 3: Canadian Manufacturing Industries
4.3.4 Example 4: Sawmills in Washington State
4.3.5 Example 5: Mariage Premium
4.3.6 Example 6: Currency Union
4.3.7 Hausman's Test for the Two-Way Model
4.4 Further Reading
4.5 Notes
4.6 Problems
References
5 Heteroskedasticity and Serial Correlation in the Error Component Model
5.1 Heteroskedasticity
5.1.1 Testing for Homoskedasticity in an Error Component Model
5.2 Serial Correlation
5.2.1 The AR(1) Process
5.2.2 The AR(2) Process
5.2.3 The AR(4) Process for Quarterly Data
5.2.4 The MA(1) Process
5.2.5 Unequally Spaced Panels with AR(1) Disturbances
5.2.6 Prediction
5.2.7 Testing for Serial Correlation and Individual Effects
5.3 Time-Wise Autocorrelated and Cross-Sectionally Heteroskedastic Panel Regression
5.4 Further Reading
5.5 Notes
5.6 Problems
References
6 Seemingly Unrelated Regressions with Error Components
6.1 The One-Way Model
6.2 The Two-Way Model
6.3 Applications and Extensions
6.4 Problems
References
7 Simultaneous Equations with Error Components
7.1 Single Equation Estimation
7.2 Empirical Example: Crime in North Carolina
7.3 System Estimation
7.4 The Hausman and Taylor Estimator
7.5 Empirical Example: Earnings Equation Using PSID Data
7.6 Further Reading
7.7 Notes
7.8 Problems
References
8 Dynamic Panel Data Models
8.1 Introduction
8.2 The Arellano and Bond Estimator
8.2.1 Testing for Over-Indentification Restrictions and Serial Correlation in Dynamic Panel Models
8.2.2 Downward Bias of the Estimated Asymptotic Standard Errors
8.2.3 Too Many Moment Conditions and the Bias Efficiency Trade-Off
8.3 The Arellano and Bover Estimator
8.4 The Ahn and Schmidt Moment Conditions
8.5 The Blundell and Bond System GMM Estimator
8.6 The Keane and Runkle Estimator
8.7 Limited Information Maximum Likelihood
8.8 Empirical Examples
8.8.1 Example 1: Dynamic Demand for Cigarettes
8.8.2 Example 2: Democracy and Education
8.9 Selected Applications
8.10 Further Reading
8.11 Notes
8.12 Problems
References
9 Unbalanced Panel Data Models
9.1 Introduction
9.2 The Unbalanced One-Way Error Component Model
9.2.1 ANOVA Methods
9.3 Maximum Likelihood Estimators
9.3.1 Minimum Norm and Minimum Variance Quadratic Unbiased Estimators (MINQUE and MIVQUE)
9.3.2 Monte Carlo Results
9.4 Empirical Example: Hedonic Housing
9.5 The Unbalanced Two-Way Error Component Model
9.5.1 The Fixed Effects Model
9.5.2 The Random Effects Model
9.6 Testing for Individual and Time Effects Using Unbalanced Panel Data
9.7 The Unbalanced Nested Error Component Model
9.7.1 Empirical Example: Nested States Public Capital Productivity
9.8 Notes
9.9 Problems
References
10 Special Topics
10.1 Measurement Error and Panel Data
10.2 Rotating Panels
10.3 Pseudo-Panels
10.4 Short-Run versus Long-Run Estimates in Pooled Models
10.5 Heterogeneous Panels
10.6 Count Panel Data
10.7 Notes
10.8 Problems
References
11 Limited Dependent Variables and Panel Data
11.1 Fixed and Random Logit and Probit Models
11.2 Simulation Estimation of Limited Dependent Variable Models with Panel Data
11.3 Dynamic Panel Data Limited Dependent Variable Models
11.4 Selection Bias in Panel Data
11.5 Censored and Truncated Panel Data Models
11.6 Empirical Applications
11.7 Empirical Example: Nurses Labor Supply
11.8 Further Reading
11.9 Notes
11.10 Problems
References
12 Nonstationary Panels
12.1 Introduction
12.2 Panel Unit Roots Tests Assuming Cross-Sectional Independence
12.2.1 Levin, Lin and Chu Test
12.2.2 Im, Pesaran and Shin Test
12.2.3 Breitung's Test
12.2.4 Combining p-Value Tests
12.2.5 Residual-Based LM Test
12.3 Panel Unit Roots Tests Allowing for Cross-Sectional Dependence
12.4 Spurious Regression in Panel Data
12.5 Panel Cointegration Tests
12.5.1 Residual-Based DF and ADF Tests (Kao Tests)
12.5.2 Residual-Based LM Test
12.5.3 Pedroni Tests
12.5.4 Likelihood-Based Cointegration Test
12.5.5 Finite Sample Properties
12.6 Estimation and Inference in Panel Cointegration Models
12.7 Empirical Examples
12.7.1 Example 1: Purchasing Power Parity
12.7.2 Example 2: International R&D Spillover
12.7.3 Example 3: OECD Health Care Expenditures
12.8 Further Reading
12.9 Notes
12.10 Problems
References
13 Spatial Panel Data Models
13.1 Introduction
13.2 Spatial Error Component Regression Model
13.3 Spatial Lag Panel Data Regression Model
13.4 Forecasts using Panel Data with Spatial Error Correlation
13.5 Panel Unit Root Tests and Spatial Dependence
13.6 Panel Data Tests for Cross-Sectional Dependence
13.7 Computational Note
13.8 Problems
References