CURSO 2008/2009, FIRST TERM
LICENCIATURA EN ECONOMÍA
LICENCIATURA EN ADMINISTRACIÓN
Y DIRECCIÓN DE EMPRESAS
ESTUDIOS SIMULTÁNEOS EN
ECONOMÍA/ADM. DE EMPRESAS Y DERECHO
ESTUDIOS COMBINADOS EN
ECONOMÍA Y PERIODISMO
Página Web: http://www.eco.uc3m.es/~EI/
Departamento de Economía
TRONCAL
CURSO: 3º
CREDITOS: 7
CREDITOS ECTS: 6
CUATRIMESTRE: 1º
HORAS/SEMANA: 4
COURSE
DIRECTOR: César Alonso-Borrego
OBJECTIVES:
Understand the consequences
about estimation and inference when any of the assumptions of the classical
regression model fails. Propose well-behaved estimators (in terms of
consistency and efficiency) in such situations. Introduce the problem of
estimation and inference with discrete choice models. At the end of the course,
the student must be able to know:
- The consequences of omitting relevant variables.
- The concepts of endogeneity and simultaneity and their implications.
- The instrumental variable estimator.
- How to test whether an explanatory variable is exogenous or endogenous.
- The consequences of heteroskedasticity and how to make inference in such
context.
- The generalized least squares estimator.
- The modelling of discrete choices of economic agents and the inference about
parameters in such context.
PROGRAMME:
1. INTRODUCTION. Review of main
concepts. Economic data and econometric modelling. Classical regression model.
OLS estimator and its properties. Inference.
2. REGRESSION ANALYSIS WITH
QUALITATIVE INFORMATION: BINARY OR DUMMY VARIABLES. Describing qualitative
information. A single dummy independent variable. Dummy variables for multiple
categories. Interactions involving dummy variables.
3. MORE ON SPECIFICATION AND DATA
PROBLEMS. Functional form misspecification. Using proxy variables for
unobserved explanatory variables. Properties of OLS under measurement error.
Missing Data. Nonrandom samples and outlying observations.
4. INSTRUMENTAL VARIABLES
ESTIMATION AND TWO STAGE LEAST SQUARES. Motivation: omitted variables. IV
estimation of the multiple regression model. Two stage least squares. IV
solutions to errors-in-variables problems. Testing for endogeneity and testing
overidentifying restrictions.
Simultaneous equations models. The nature of simultaneous equations models.
Simultaneity bias in OLS. Identifying and estimating a structural equation.
5. HETEROSKEDASTICITY.
Consequences of heteroskedasticity for OLS. Heteroskedasticity-robust inference
after OLS estimation. 2SLS with heteroskedasticity.
6. LIMITED DEPENDENT VARIABLE
MODELS. The linear probability model. Logit and Probit models for binary
response. Economic explanation. Interpretation.
ASSESSMENT CRITERIA:
A final exam and individual student’s work produced in lectures and classes.
PRACTICAL SESSIONS:
Practical classes are a core part of the course. Most practical classes require
computer use with the programs E-Views and Gretl. The topics that are covered
in the course are illustrated by means of econometric models that are
well-known in empirical economics. Such models are estimated and tested with
real economic data.
BASIC BIBLIOGRAPHY:
The main textbook is Wooldridge (2006).
ADDITIONAL BIBLIOGRAPHY:
- CARRASCAL, U, Y. GONZALEZ y B. RODRÍGUEZ.: Análisis Econométrico con
E-views. Ra-Ma. 2001.
- GOLDBERGER, A.S. Introducción a la Econometría. Ariel Economía. 2001.
- GOLDBERGER, A.S. Introductory Econometrics. Harvard University Press,
1999.
- GREENE, W.H.: Análisis Econométrico, Prentice Hall,
Madrid, 1998.
- WOOLDRIDGE, J.M. Introductory Econometrics. A modern approach.
South-Western College Publishing. 2003. (Traducido por Thomson, 2006).
The
course is scheduled in 12 weeks, leaving the last one to compensate unexpected
delays.
|
CLASES DE TEORÍA |
|
|
TOPIC |
|
|
1.
Introduction.
Economic data and econometric modeling. The classical regression model. OLS estimation. Interpretation.
Inference. |
Weeks 1 to 3 |
|
2.
Regression analysis with qualitative information. |
Weeks 3 to 4 |
|
3.
Specification problems. |
Weeks 5 to 6 |
|
4.
Instrumental variable estimation. Simultaneous
equations models. |
Weeks 7 to 9 |
|
5.
Heteroskedasticity. |
Week 10 |
|
6. Models with binary dependent variables. |
Weeks 11 to 12 |