Econometrics

Code:

2ECON03

Acronym:

ME

Keywords
Classification	Keyword
CNAEF	Economics

Instance: 2014/2015 - 1S (of 15-09-2014 to 09-01-2015)

Active?	Yes
Responsible unit:	Agrupamento Científico de Economia
Course/CS Responsible:	Master in Economics

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
ME	54	Bologna Syllabus	1	-	7,5	56	202,5

Teaching language

Portuguese

Objectives

The course provides information on several econometric methods, illustrated with models where these methods are recommended. A major pre-requisite is knowledge of Econometrics at an introductory level, including the classical linear regression model, the ordinary least squares (OLS) estimators, the standard techniques of statistical inference and the heteroskedasticity and serial correlation extensions, at the level of both estimation methods and diagnostic tests. The emphasis of the course will also be in introducing the students to the computer tools they will need in applied work, thus paving the way for thesis preparation.

Learning outcomes and competences

Students are expected to get acquainted with a number of estimation methods (OLS, EGLS, NLS, ML, IV, GMM, etc.) and the main classes of models where they are employed and be able to replicate these methods in applied work.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

Pre-requisites are a solid knowledge of Econometrics ate the introductory level and a reasonable background in Mathematics, Linear Algebra and Statistical Inference.

Program

0. A BRIEF REVIEW OF LEAST SQUARES ESTIMATION

0.0. The linear regression model: concepts, assumptions and standard notation

0.1. Least squares estimators (OLS, GLS, EGLS) of the parameters

0.2. Properties of LS estimators

 

1. NONLINEAR LEAST SQUARES ESTIMATION

1.0. Linear models, nonlinear models and linearization

1.1. Nonlinear least squares (NLS) estimators

1.2. Properties of NLS estimators

1.3. The linearized regression

1.4. An illustration: estimating models with autocorrelation

 

2. MAXIMUM LIKELIHOOD ESTIMATION

2.0. Maximum likelihood (ML) estimators

2.1. Properties of ML estimators

2.2. ML estimation of the parameters of the linear regression model

2.3. An illustration: estimating models with autocorrelation

2.4. An illustration: estimating binary choice models

2.5. An illustration: estimating models with a censored or truncated dependent variable

 

3. INSTRUMENTAL VARIABLES ESTIMATION

3.0. Instrumental variable (IV) estimators

3.1. Properties of IV estimators

3.2. An illustration: estimating simultaneous equations systems

 

4. GENERALIZED METHOD OF MOMENTS ESTIMATION

4.0. The method of moments

4.1. Generalized method of moments (GMM) estimators

4.2. Overidentifying restrictions

 

Mandatory literature

William H. Greene; Econometric Analysis, 7th ed., Pearson Education, Inc., 2012. ISBN: 0-13-139538-6

Comments from the literature

Lecture notes on the major topics will be made available in the course's site (\\deer\public\disciplinas\2e103). They were written in Portuguese, however.

Teaching methods and learning activities

Basic theory will be presented, computer usage of methods and models will be documented and practiced and main results discussed.

Software

EViews

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Exame	70,00
Participação presencial	0,00
Trabalho escrito	30,00
Total:	100,00

Eligibility for exams

Regular attendance is expected. Following each of the major topics of the syllabus, homework will be assigned. A comprehensive written exam will be held on a date to be announced by the programme's Scientific Committee.

Calculation formula of final grade

As a rule, assessment will be determined in a comprehensive written examination at the end of the term. The final grade will be assigned on a 0 to 20 points scale; less than 10 points is taken to be a failure.
The student may choose to supplement the final exam with the marks earned in assigned homework. Several homeworks will be prescribed as the semester unfolds. If the student so chooses, the final grade will be the weighted average of the marks earned in the homework (30%) and in the exam (70%), provided that the latter is not less than 7; otherwise, the final grade will be equal to the exam mark.
The final grade will also be equal to the exam mark for students who failed to complete assigned homework in the terms and deadlines prescribed. Please contact your instructor for further details.  

Observations

Students with no previous background in Econometrics should abstain from enrollment in the course. Weaknesses in Math and Statistics will require intensive further work.