Ben Vogelvang. Econometrics. Theory and Applications with EViews

Pearson Education Limited, 2005. — 379 p. — ISBN-10: 0-273-63374-3Economists are regularly confronted with results of quantitative economics research. Econometrics: Theory and Applications with EViews provides a broad introduction to quantitative economic methods: how models arise, their underlying assumptions and how estimates of parameters or other economic quantities are computed.
The author combines econometrics theory with practice be demonstrating its use with the software package EViews. The emphasis is on understanding how to select the right method of analysis for a given situation, and how to actually apply the theoretical methods in the right way.Preparatory Work
introduction to Part I
Basic Concepts of Econometric Models
Scienti c quantitative economic research
Economic and econometric models
Economic data
Variables of an economic model
Structural and reduced-fortn equations
Parameters and elasticities
Stochastic models
Applied quantitative economic research
Description of the Data Sets and introduction to the CasesData set I: commodity prices
Data set 2: macroeconomic data
Data set 3: oil market-related data
Data set 4: money market
Data set 5: cross-section data
Basic Concepts of EViews and Starting the Research ProjectThe creation of a work le in EViews
Viewing variables and some procedures
Some basic calculations in Eviews
Case 1: the data analysis
The Reduced-Form Model
introduction to Part two
Description of the Reduced-Form Model
lntroduction
The assumptions of the classical regression model
The ordinary least squares (OLS) estimator
Relationship between disturbances and residuals
Estimation of the variance of the disturbance term
Desirable statistical properties of estimators
The distribution and some properties of the OLS estimator
Maximum likelihood estimation
Regression analysis with EViews
Testing the Deterministic AssumptionsRelationships among variables of the linear model
The coef cient of determination
Survey of some useful distributions and test principles
Distribution of the residual variance estimator
Interval estimates and the I-test to test restrictions on parameters
The Wald F-test to test restrictions on parameters
Alternative expressions for the Wald F-test and the LM-test
Testing the Stochastic Assumptions and Model StabilityA normality test
Tests for residual autocorrelation
Tests for heteroskedasticity
Checking the parameter stability
Model estimation and presentation of estimation results
Case 2: an econometric model for time-series data
A Collection of Topics Around the Linear ModelSpeci cation errors
Prediction
Multicollinearity
Arti cial explanatory variables
Case 3: exercises with the estimated model
Specific Structural Models
introduction to Part Three
Estimation with More General Disturbance-Term AssumptionsThe generalised least squares (GLS) estimator in theory
The SUR model
Case 4: a SUR model for the macroeconomic data
Autocorrelated disturbances
Heteroskedastic disturbances
Case 5: heteroskedastic disturbances
Introduction to ARCH and GARCH models
Models with Endogenous Explanatory VariablesThe instrumental-variable (IV) estimator
The two-stage least squares (2SLS) estimator
IV and 2SLS estimation in EViews
Case 6: consistent estimation of structural models
Simultaneous Equation ModelsMathematical notation of the SEM
Identi cation
Case 7: identi cation of the equations of a SEM
Estimation methods 226
Case 8: simultaneous estimation of a macroeconomic model
Two speci c multiple-equation models
Qualitative Dependent VariablesThe linear probability model
Probit and legit models
Estimation of binary dependent variable models with EViews
Case 9: modelling a qualitative dependent variable
Time-series Models
Introduction to Part IV
Dynamic Models, Unit Roots and ColntegrationLag operators. notation and examples
Long-run effects of short-irun dynamic models
Error—correction models
Trends and unit-root tests
Relationships between non-stationary variables
Case 10: cointegration analysis
Distributed Lag ModelsA nite distributed lag model with EViews
Models with a lagged dependent variable
Univariate Time-Series ModelsTime—series models and some properties
Box—Jenkins procedures
The autocorrelation function (ACF)
The partial autocorrelation function (PACF)
Examples oftheoretical ACFs and PACFs for some
TS models
The Box-Jenkins approach in practice
Case 11: Box-—Jenlrins procedures