Panel Data Analysis Using EViews -- Contents -- Preface -- About the Author -- Part One: Panel Data as a Multivariate Time Series by States -- 1 Data Analysis Based on a Single Time Series by States -- 1.1 Introduction -- 1.2 Multivariate Growth Models -- 1.2.1 Continuous Growth Models -- 1.2.2 Discontinuous Growth Models -- 1.3 Alternative Multivariate Growth Models -- 1.3.1 A Generalization of MAR(p)_GM -- 1.3.2 Multivariate Lagged Variables Growth Models -- 1.3.3 Multivariate Lagged-Variable Autoregressive Growth Models -- 1.3.4 Bounded MLVAR(p -- q)_GM -- 1.3.5 Special Notes -- 1.4 Various Models Based on Correlated States -- 1.4.1 Seemingly Causal Models with Trend -- 1.4.2 The Application of the Object "VAR" -- 1.4.3 The Application of the Instrumental Variables Models -- 1.5 Seemingly Causal Models with Time-Related Effects -- 1.5.1 SCM Based on the Path Diagram in Figure 1.10(a) -- 1.5.2 SCM Based on the Path Diagram in Figure 1.10(b) -- 1.6 The Application of the Object POOL -- 1.6.1 What is a Fixed-Effect Model? -- 1.6.2 What is a Random Effect Model? -- 1.6.3 Special Notes -- 1.7 Growth Models of Sample Statistics -- 1.8 Special Notes on Time-State Observations -- 1.9 Growth Models with an Environmental Variable -- 1.9.1 The Simplest Possible Model -- 1.9.2 The Application of VAR and VEC Models -- 1.9.3 Application of ARCH Model -- 1.9.4 The Application of Instrumental Variables Models -- 1.10 Models with an Environmental Multivariate -- 1.10.1 Bivariate Correlation and Simple Linear Regressions -- 1.10.2 Simple Models with an Environmental Multivariate -- 1.10.3 The VAR Models -- 1.11 Special Piece-Wise Models -- 1.11.1 The Application of Growth Models -- 1.11.2 Equality Tests by Classifications -- 2 Data Analysis Based on Bivariate Time Series by States -- 2.1 Introduction -- 2.2 Models Based on Independent States.

2.2.1 MAR(p) Growth Model with an Exogenous Variable -- 2.2.2 A General MAR(p) Model with an Exogenous Variable -- 2.3 Time-Series Models Based on Two Correlated States -- 2.3.1 Analysis using the Object System -- 2.3.2 Two-SLS Instrumental Variables Models -- 2.3.3 Three-SLS Instrumental Variables Models -- 2.3.4 Analysis using the Object "VAR" -- 2.4 Time-Series Models Based on Multiple Correlated States -- 2.4.1 Extension of the Path Diagram in Figure 2.6 -- 2.4.2 SCMs as VAR Models -- 2.5 Time-Series Models with an Environmental Variable Zt, Based on Independent States -- 2.5.1 The Simplest Possible Model -- 2.5.2 Interaction Models Based on Two Independent States -- 2.6 Models Based on Correlated States -- 2.6.1 MLV(1) Interaction Model with Trend -- 2.6.2 Simultaneous SCMs with Trend -- 2.7 Piece-Wise Time-Series Models -- 3 Data Analysis Based on Multivariate Time Series by States -- 3.1 Introduction -- 3.2 Models Based on (X_i,Y_i,Z_i) for Independent States -- 3.2.1 MLVAR(p -- q) Model with Trend Based on (X_i,Y_i,Z_i) -- 3.3 Models Based on (X_i, Y_i,Z_i) for Correlated States -- 3.3.1 MLV(1) Interaction Model with Trend -- 3.3.2 MLV(1) Interaction Model with Time-Related Effects -- 3.4 Simultaneous SCMs with Trend -- 3.4.1 The Basic Simultaneous SCMs with Trend -- 3.4.2 Alternative Time Series Models -- 3.5 Models Based on (X1_i,X2_i,X3_i, Y1_i,Y2_i) for Independent States -- 3.5.1 Lagged Endogenous Variables: First Autoregressive Model with Exogenous Variables and Trend -- 3.5.2 A Mixed Lagged Variables First Autoregressive Model with Trend -- 3.5.3 Lagged Endogenous Variables: First Autoregressive Model with Exogenous Variables and Time-Related Effects -- 3.5.4 Various Interaction Models -- 3.6 Models Based on (X_i,Y_i) for Correlated States -- 3.6.1 Additive Models -- 3.6.2 Interaction Models.

3.6.3 Alternative Models for Two Correlated States -- 3.7 Discontinuous Time-Series Models -- 3.8 Additional Examples for Correlated States -- 3.9 Special Notes and Comments -- 3.9.1 Extended Models -- 3.9.2 Not-Recommended Models -- 3.9.3 Problems with Data Analysis -- 4 Applications of Seemingly Causal Models -- 4.1 Introduction -- 4.1.1 Deleting Time t from Models -- 4.1.2 Replacing Time t with an Environmental Variable -- 4.2 SCMs Based on a Single Time Series Y_it -- 4.3 SCMs Based on Bivariate Time Series (X_it,Y_it) -- 4.3.1 Additive SCM -- 4.3.2 ATwo-Way Interaction Standard SCM -- 4.3.3 AThree-Way Interaction Standard SCM -- 4.4 SCMs Based on a Trivariate (X1_i,X2_i,Y1_i) -- 4.4.1 Simple SCMs for Two Correlated States -- 4.4.2 Various Time-Series Models -- 4.5 SCMs Based on a Trivariate (X_it,Y1_it,Y2_it) -- 4.6 SCMs Based on Multivariate Endogenous and Exogenous Variables -- 4.6.1 Simple Additive SCM -- 4.6.2 A Two-Way Interaction SCM -- 4.6.3 A Three-Way Interaction SCM -- 4.6.4 Special Notes and Comments -- 4.6.5 Various Alternative SCMs -- 4.7 Fixed- and Random Effects Models -- 4.7.1 A Fixed-Effect Model and a MANCOVA Model -- 4.7.2 A Random Effect Model and a Single Regression -- 4.8 Models with Cross-Section Specific Coefficients -- 4.8.1 MAR(p) Model with Cross-Section Specific Coefficients -- 4.8.2 Advanced PLS Estimation Methods -- 4.8.3 Instrumental Variables Model -- 4.8.4 Special Notes and Comments -- 4.9 Cases in Industry -- 4.9.1 Dummy Variables Models -- Part Two: Pool Panel Data Analysis -- 5 Evaluation Analysis -- 5.1 Introduction -- 5.2 Preliminary Evaluation Analysis -- 5.3 The Application of the Object "Descriptive Statistics and Tests" -- 5.3.1 Analysis Using the Option "Stats by Classification. . ." -- 5.3.2 Analysis Using the Option "Equality Tests by Classification. . .".

5.3.3 Analysis Using the Option "N-Way Tabulation. . ." -- 5.4 Analysis Based on Ordinal Problem Indicators -- 5.5 Multiple Association between Categorical Variables -- 5.5.1 Applications of N-Way Tabulation -- 5.5.2 Application of Kendall's Tau -- 6 General Choice Models -- 6.1 Introduction -- 6.2 Multi-Factorial Binary Choice Models -- 6.2.1 One-Way Binary Choice Model -- 6.2.2 Two-Way Binary Choice Model -- 6.2.3 Multi-Factorial Binary Choice Model -- 6.3 Binary Logit Model of Yit on a Numerical Variable Xit -- 6.3.1 A Comparative Study -- 6.3.2 General Binary Logit Model with a Single Numerical Variable X -- 6.3.3 Special Notes and Comments -- 6.4 Binary Logit Model of a Zero-One Indicator Yit on (X1it,X2it) -- 6.4.1 The Simplest Possible Function -- 6.4.2 Functions for Binary Logit Translog Models -- 6.5 Binary Choice Model of a Zero-One Indicator Yit on (X1it,X2it,X3it) -- 6.5.1 The Linear Effect of X3 on Y Depends on X1 and X2 -- 6.5.2 Alternative Effects of X3 on Y Depends on X1 and X2 -- 6.6 Binary Choice Model of a Zero-One Indicator Yit on (X1it,. . ., Xhit,. . .) -- 6.7 Special Notes and Comments -- 7 Advanced General Choice Models -- 7.1 Introduction -- 7.2 Categorical Data Analyses -- 7.2.1 Multi-Factorial Binary Choice Models -- 7.2.2 Ordered Choice Models -- 7.2.3 Not-Recommended Models -- 7.2.4 Application of N-Way Tabulation -- 7.2.5 Applications of Ordinal-Ordinal Association -- 7.3 Multi-Factorial Choice Models with a Numerical Independent Variable -- 7.3.1 Nonparametric Estimation Methods -- 7.3.2 Parametric Estimation Methods -- 7.3.3 Polynomial-Effect BCM with Three Numerical Exogenous Variables -- 7.3.4 A Study of Li, et al. (2010) -- 7.3.5 A Study of Hameed, et al. (2010) -- 7.3.6 A Study of Francis and Martin (2010) -- 8 Univariate General Linear Models -- 8.1 Introduction -- 8.2 ANOVA and Quantile Models.

8.3 Continuous Linear-Effect Models -- 8.3.1 Bivariate Correlation Analysis -- 8.3.2 STEPLS Regressions -- 8.4 Piece-Wise Autoregressive Linear Models by Time Points -- 8.4.1 The Simplest Linear-Effect Models Based on (Xit,Yit) by Time Points -- 8.4.2 General Linear-Effect Model Based on (Xit,Yit) by Time Points -- 8.4.3 Linear-Effect Model Based on (X1it, X2it,Yit) by Time Points -- 8.4.4 Linear Models Based on (X1it, X2it, X3it,Yit) by Time Points -- 8.5 ANCOVA Models -- 9 Fixed-Effects Models and Alternatives -- 9.1 Introduction -- 9.2 Cross-Section Fixed-Effects Models -- 9.2.1 Individual Fixed-Effects Models -- 9.2.2 Group Fixed-Effects Models -- 9.3 Time-Fixed-Effects Models -- 9.4 Two-Way Fixed-Effects Models -- 9.4.1 Two-Way Fixed-Effects Models -- 9.4.2 Interaction FEMs -- 9.5 Extended Fixed-Effects Models -- 9.5.1 Least Square FEMs -- 9.5.2 Alternative FEMs -- 9.6 Selected Fixed-Effects Models from the Journal of Finance, 2011 -- 9.6.1 Additive FEM Applied by Hendershott, et al. (2011) -- 9.6.2 FEM Applied by Engelberg and Parsons (2011) -- 9.6.3 Special FEMs Applied by Benmelech and Bergman (2011) -- 9.7 Heterogeneous Regression Models -- 9.7.1 Heterogeneous Regressions by Individuals -- 9.7.2 Heterogeneous Classical Growth Models by Individuals or Groups -- 9.7.3 Piece-Wise Heterogeneous Regressions -- 9.7.4 Heterogeneous Regressions with Trend by Individuals or Groups -- 9.7.5 Heterogeneous Regressions with Time-Related Effects by Individuals or Groups -- 10 Special Notes on Selected Problems -- 10.1 Introduction -- 10.2 Problems with Dummy Variables -- 10.2.1 A Dummy of the Return Rate Rit -- 10.2.2 Other Types of Dummy Variables -- 10.3 Problems with the Numerical Variable Rit -- 10.3.1 Problem with Outliers -- 10.3.2 Problem with the Models of Rit with its Dummy DRit -- 10.4 Problems with the First Difference Variable.

10.5 Problems with Ratio Variables.