‘Econometric Analysis of Panel Data’ has become established as the leading
textbook for postgraduate courses in panel data. This book is intended as a companion to
the main text. The prerequisites include a good background in mathematical statistics and
econometrics. The companion guide will add value to the existing textbooks on panel data
by solving exercises in a logical and pedagogical manner, helping the reader understand,
learn and teach panel data.
These exercises are based upon those in Baltagi (2008) and are complementary to that
text even though they are stand alone material and the reader can learn the basic material
as they go through these exercises. The exercises in this book start by providing some
background material on partitioned regressions and the Frisch-Waugh-Lovell theorem,
showing the reader some applications of this material that are useful in practice. Then it
goes through the basic material on fixed and random effects models in a one-way and
two-way error components models, following the same outline as in Baltagi (2008). The book
also provides some empirical illustrations and examples using Stata and EViews that the
reader can replicate. The data sets are available on the Wiley web site
(www.wileyeurope.com/college/baltagi).
Table of Contents
Preface.
1 Partitioned Regression and the Frisch–Waugh–Lovell Theorem.
Exercises.
1.1 Partitioned regression.
1.2 The Frisch–Waugh–Lovell theorem.
1.3 Residualing the constant.
1.4 Adding a dummy variable for the ith observation.
1.5 Computing forecasts and forecast standard errors.
2 The One-way Error Component Model.
2.1 The One-way Fixed Effects Model.
Exercises.
2.1 One-way fixed effects regression.
2.2 OLS and GLS for fixed effects.
2.3 Testing for fixed effects.
2.2 The One-way Random Effects Model.
Exercises.
2.4 Variance–covariance matrix of the one-way random effects model.
2.5 Fuller and Battese (1973) transformation for the one-way random effects model.
2.6 Unbiased estimates of the variance components: the one-way model.
2.7 Feasible unbiased estimates of the variance components: the one-way model.
2.8 Gasoline demand in the OECD.
2.9 System estimation of the one-way model: OLS versus GLS.
2.10 GLS is a matrix weighted average of between and within.
2.11 Efficiency of GLS compared to within and between estimators.
2.12 Maximum likelihood estimation of the random effects model.
2.13 Prediction in the one-way random effects model.
2.14 Mincer wage equation.
2.15 Bounds for s2 in a one-way random effects model.
2.16 Heteroskedastic fixed effects models.
3 The Two-way Error Component Model.
3.1 The Two-way Fixed Effects Model.
Exercise.
3.1 Two-way fixed effects regression.
3.2 The Two-way Random Effects Model.
Exercises.
3.2 Variance–covariance matrix of the two-way random effects model.
3.3 Fuller and Battese (1973) transformation for the two-way random effects model.
3.4 Unbiased estimates of the variance components: the two-way model.
3.5 Feasible unbiased estimates of the variance components: the two-way model.
3.6 System estimation of the two-way model: OLS versus GLS.
3.7 Prediction in the two-way random effects model.
3.8 Variance component estimation under misspecification.
3.9 Bounds for s2, in a two-way random effects model.
3.10 Nested effects.
3.11 Three-way error component model.
3.12 A mixed error component model.
3.13 Productivity of public capital in private production.
4 Test of Hypotheses Using Panel Data.
4.1 Tests for Poolability of the Data.
Exercises.
4.1 Chow (1960) test.
4.2 Roy (1957) and Zellner (1962) test.
4.2 Tests for Individual and Time Effects.
Exercises.
4.3 Breusch and Pagan (1980) Lagrange multiplier test.
4.4 Locally mean most powerful one-sided test.
4.5 Standardized Honda (1985) test.
4.6 Standardized King and Wu (1997) test.
4.7 Conditional Lagrange multiplier test: random individual effects.
4.8 Conditional Lagrange multiplier test: random time effects.
4.9 Testing for poolability using Grunfeld’s data.
4.10 Testing for random time and individual effects using Grunfeld’s data.
4.3 Hausman’s Test for Correlated Effects.
Exercises.
4.11 Hausman (1978) test based on a contrast of two estimators.
4.12 Hausman (1978) test based on an artificial regression.
4.13 Three contrasts yield the same Hausman test.
4.14 Testing for correlated effects in panels.
4.15 Hausman’s test as a Gauss–Newton regression.
4.16 Hausman’s test using Grunfeld’s data.
4.17 Relative efficiency of the between estimator with respect to the within estimator.
4.18 Hausman’s test using Munnell’s data.
4.19 Currency Union and Trade.
5 Heteroskedasticity and Serial Correlation.
5.1 Heteroskedastic Error Component Model.
Exercises.
5.1 Heteroskedastic individual effects.
5.2 An alternative heteroskedastic error component model.
5.3 An LM test for heteroskedasticity in a one-way error component model.
5.2 Serial Correlation in the Error Component Model.
Exercises.
5.4 AR(1) process.
5.5 Unbiased estimates of the variance components under the AR(1) model.
5.6 AR(2) process.
5.7 AR(4) process for quarterly data.
5.8 MA(1) process.
5.9 MA(q) process.
5.10 Prediction in the serially correlated error component model.
5.11 A joint LM test for serial correlation and random individual effects.
5.12 Conditional LM test for serial correlation assuming random individual effects.
5.13 An LM test for first-order serial correlation in a fixed effects model.
5.14 Gasoline demand example with first-order serial correlation.
5.15 Public capital example with first-order serial correlation.
6 Seemingly Unrelated Regressions with Error Components.
Exercises.
6.1 Seemingly unrelated regressions with one-way error component disturbances.
6.2 Unbiased estimates of the variance components of the one-way SUR model.
6.3 Special cases of the SUR model with one-way error component disturbances.
6.4 Seemingly unrelated regressions with two-way error component disturbances.
6.5 Unbiased estimates of the variance components of the two-way SUR model.
6.6 Special cases of the SUR model with two-way error component disturbances.
7 Simultaneous Equations with Error Components.
7.1 Single Equation Estimation.
Exercises.
7.1 2SLS as a GLS estimator.
7.2 Within 2SLS and between 2SLS.
7.3 Within 2SLS and between 2SLS as GLS estimators.
7.4 Error component two-stage least squares.
7.5 Equivalence of several EC2SLS estimators.
7.6 Hausman test based on FE2SLS vs EC2SLS.
7.2 System Estimation.
Exercises.
7.7 3SLS as a GLS estimator.
7.8 Within 3SLS and between 3SLS.
7.9 Within 3SLS and between 3SLS as GLS estimators.
7.10 Error component three-stage least squares.
7.11 Equivalence of several EC3SLS estimators.
7.12 Special cases of the simultaneous equations model with one-way error component
disturbances.
7.3 Endogenous Effects.
Exercises.
7.13 Mundlak’s (1978) augmented regression.
7.14 Hausman and Taylor (1981) estimator.
7.15 Cornwell and Rupert (1988): Hausman and Taylor application.
7.16 Serlenga and Shin (2007): gravity models of intra-EU trade.
7.17 Cornwell and Trumbull (1994): crime in North Carolina.
8 Dynamic Panels.
Exercises.
8.1 Bias of OLS, FE and RE estimators in a dynamic panel data model.
8.2 Anderson and Hsiao (1981) estimator.
8.3 Arellano and Bond (1991) estimator.
8.4 Sargan’s (1958) test of overidentifying restrictions.
8.5 Ahn and Schmidt (1995) moment conditions.
8.6 Ahn and Schmidt (1995) additional moment conditions.
8.7 Arellano and Bond (1991) weak instruments.
8.8 Alternative transformations that wipe out the individual effects.
8.9 Arellano and Bover (1995) estimator.
8.10 Baltagi and Levin (1986): dynamic demand for cigarettes.
9 Unbalanced Panels.
9.1 The Unbalanced One-way Error Component Model.
Exercises.
9.1 Variance–covariance matrix of unbalanced panels.
9.2 Fixed effects for the one-way unbalanced panel data model.
9.3 Wallace and Hussain (1969)-type estimators for the variance components of a one-way
unbalanced panel data model.
9.4 Comparison of variance component estimators using balanced vs unbalanced data.
9.2 The Unbalanced Two-way Error Component Model.
Exercises.
9.5 Fixed effects for the two-way unbalanced panel data model.
9.6 Fixed effects for the three-way unbalanced panel data model.
9.7 Random effects for the unbalanced two-way panel data model.
9.8 Random effects for the unbalanced three-way panel data model.
9.9 Wansbeek and Kapteyn (1989)-type estimators for the variance components of a
two-way unbalanced panel data model.
9.3 Testing for Individual and Time Effects Using Unbalanced Panel Data.
Exercises.
9.10 Breusch and Pagan (1980) LM test for unbalanced panel data.
9.11 Locally mean most powerful one-sided test for unbalanced panel data.
9.12 Standardized Honda (1985) and King and Wu (1997) tests for unbalanced panel data.
9.13 Harrison and Rubinfeld (1978): hedonic housing.
10 Special Topics.
10.1 Measurement Error and Panel Data.
Exercise.
10.1 Measurement error and panel data.
10.2 Rotating Panels.
Exercises.
10.2 Rotating panel with two waves.
10.3 Rotating panel with three waves.
10.3 Spatial Panels.
Exercises.
10.4 Spatially autocorrelated error component model.
10.5 Random effects and spatial autocorrelation with equal weights.
10.4 Count Panel Data.
Exercises.
10.6 Poisson panel regression model.
10.7 Patents and R&D expenditures.
11 Limited Dependent Variables.
Exercises.
11.1 Fixed effects logit model.
11.2 Equivalence of two estimators of the fixed effects logit model.
11.3 Dynamic fixed effects logit model with no regressors.
11.4 Dynamic fixed effects logit model with regressors.
11.5 Binary response model regression.
11.6 Random effects probit model.
11.7 Identification in a dynamic binary choice panel data model.
11.8 Union membership.
11.9 Beer taxes and motor vehicle fatality rates.
12 Nonstationary Panels.
12.1 Panel Unit Root Tests.
Exercise.
12.1 Panel unit root tests: GDP of G7 countries.
12.2 Panel Cointegration Tests.
Exercises.
12.2 Panel cointegration tests: manufacturing shipment and inventories.
12.3 International R&D spillover.
References.
Index.
312 pages, Paperback