Econometrics
Keywords |
Classification |
Keyword |
OFICIAL |
Economics |
Instance: 2022/2023 - 1S
Cycles of Study/Courses
Teaching language
Portuguese
Objectives
The course is designed for a one-semester introduction to Econometrics. Pre-requisites for the course are a solid background in Economic Theory (both Micro- and Macroeconomics), in Statistics and in Linear Algebra. The course's main objective is in interpreting, understanding and evaluating the findings of elementary econometric analyses.
Learning outcomes and competences
The student is expected to be able to read, interpret and evaluate elementary econometric findings. Hands-on experience with specialized econometric software is required.
Working method
Presencial
Pre-requirements (prior knowledge) and co-requirements (common knowledge)
Pre-requisites for the course are a solid background in Economic Theory (both Micro- and Macroeconomics), in Statistics and in Linear Algebra.
Program
INTRODUCTION: SUBJECT AND METHODOLOGY OF ECONOMETRICS
1. THE CLASSICAL LINEAR REGRESSION MODEL
1.1. Elementary concepts and notation.
1.2. Least squares (OLS) estimators of the regression coefficients.
1.3. Coefficient of determination.
1.4. Assumptions of the classical linear regression model.
1.5. Properties of the OLS estimators.
1.6. The estimator of the variance of the disturbances.
2. INFERENCE IN THE LINEAR REGRESSION MODEL
2.1. The normality assumption.
2.2. Testing hypothesis about a single coefficient.
2.3. Testing hypothesis about linear restrictions on coefficients.
2.4. Testing the overall significance of the regression.
3. SOME EXTENSIONS OF THE LINEAR REGRESSION MODEL
3.1. Choosing a functional form.
3.2. Dummy variables.
3.3. Models for the trend and seasonal components.
3.4. Testing the equality between sets of coefficients in two regressions.
4. THE GENERALIZED LINEAR REGRESSION MODEL
4.1. Assumptions.
4.2. GLS and EGLS estimators.
5. HETEROSKEDASTICITY
5.1. The nature of the problem.
5.2. Detecting heteroskedasticity: White and Breusch-Pagan tests.
5.3. Estimation methods.
6. AUTOCORRELATION
6.1. The nature of the problem.
6.2. Stochastic process. The 1st-order autoregressive process.
6.3. Detecting autocorrelation: Durbin-Watson and Breusch-Godfrey tests.
6.4. Estimation methods.
7. REGRESSION MODELS FOR CATEGORICAL DEPENDENT VARIABLES
7.1. Introduction. Binary choice models.
7.2. The logit and probit models.
Mandatory literature
M. Mendes de Oliveira, Luis Delfim Santos e Natércia Fortuna; Econometria, 2ª ed., Escolar Editora, 2018
Complementary Bibliography
Griffiths, W.E., Hill, R. C. and Lim , G.C.; Using EViews for Principles of Econometrics 4th ed., John Wiley & Sons, 2012
Damodar N. Gujarati;
Econometrics by example. ISBN: 978-1-137-37501-8
Damodar N. Gujarati;
Basic econometrics. ISBN: 9780071276252
Teaching methods and learning activities
Econometrics aims to provide the basic theoretical principles of estimation and inference in Econometrics. Classes will be held in computer labs, allowing students' access to hands-on experience with computer applications using specialized econometric software.
A page in the computer system will provide valuable information on the plan and syllabus of the course, including formula sheets, statistical tables and a sample of tests and exams of previous years.
Software
Eviews
Evaluation Type
Distributed evaluation with final exam
Assessment Components
Designation |
Weight (%) |
Teste |
100,00 |
Total: |
100,00 |
Amount of time allocated to each course unit
Designation |
Time (hours) |
Frequência das aulas |
58,50 |
Estudo autónomo |
103,50 |
Total: |
162,00 |
Eligibility for exams
Regular attendance is expected.
Calculation formula of final grade
Grades will be assigned according to the general rules of the University of Porto. A final written exam will be held at the end of the term.
Alternatively, the student may choose to submit to two tests in the course of the semester. The student's ability to use a computer for estimation and testing will be tested in the first one. The second test is a comprehensive written exam following the end of regular classes. The final grade is the weighted average of both scores, with weights of 40% to the first and 60% to the second. A positive grade requires a weighted average of 9,5 (out of 20) and no partial score below 7,0.
Students with a score equal or above 7,0 in the first test can choose to attend the second test or to attend the final exam (first and second season).
Students with a grade below 7,0 in the first test can attend the final exam (first and second season).
In tests and exams, students should provide a valid ID and bring their own writing materials; in final exams, standard (non graphical) calculators are allowed. A formula sheet and standard statistical tables will be made available to students taking the final exams. All other materials are excluded.
The final grade will be assigned in the 0/20 points scale. A grade lower than 9.5 is taken to mean a failure.
Examinations or Special Assignments
Erasmus students are required to submit to tests and/or exams. No special work or project will substitute for the regular method of assessment.
Classification improvement
Only by final exam (reseat season).