ECTS - University of Pisa
Scheda programma d'esame
TIME SERIES ECONOMETRICS
GIUSEPPE RAGUSA
Academic year2018/19
CourseECONOMICS
Code247PP
Credits6
PeriodSemester 2
LanguageEnglish

ModulesAreaTypeHoursTeacher(s)
TIME SERIES ECONOMETRICS SECS-P/05LEZIONI42
GIUSEPPE RAGUSA unimap
Obiettivi di apprendimento
Learning outcomes
Conoscenze

Time Series Econometrics is aimed at students who wish to gain a working knowledge of time series and forecasting methods as applied in economics, social sciences, and finance. The course introduces the theory and practice of time series analysis, with an emphasis on practical skills. More generally, students will gain an appreciation for the role of dependence in statistical modeling. 
Knowledge

Time Series Econometrics is aimed at students who wish to gain a working knowledge of time series and forecasting methods as applied in economics, social sciences, and finance. The course introduces the theory and practice of time series analysis, with an emphasis on practical skills. More generally, students will gain an appreciation for the role of dependence in statistical modeling. 
Assessment criteria of knowledge

At the end of the course, students should be able to model and forecast a time series as well as read papers from the literature and start to do research in time series analysis.
Prerequisiti (conoscenze iniziali)

Students need to be familiar with basic concepts in probability and statistics, linear algebra, and calculus.
Prerequisites

Students need to be familiar with basic concepts in probability and statistics, linear algebra, and calculus.
Indicazioni metodologiche

It is expected that all students attend the lectures, be up to date with their readings and be prepared to participate fully in class. If you have problems mastering the material covered in class, please ask questions in class or during office hours.
Teaching methods

It is expected that all students attend the lectures, be up to date with their readings and be prepared to participate fully in class. If you have problems mastering the material covered in class, please ask questions in class or during office hours.
Programma (contenuti dell'insegnamento)
  1. From Cross-Section to Time Series: asymptotic theory under serial correlation
  2. Stationary Process
    1. Linear processes
    2. The Wold decomposition
    3. ARMA processes
      1. Representation. Estimation. Forecasting. Applications.
  3. Non-stationary Time Series Model
    1. ARIMA models for non-stationary time series
    2. Unit Roots
    3. Forecasting with ARIMA models
  4. Multivariate Time Series
    1. Vector Auto-Regressions (VAR)
    2. Modeling and Forecasting with VAR
    3. Cointegration
    4. Structural vs Reduced Form VAR: identification
  5. State-Space Models
    1. Linear State-Space models
    2. State-Space representation of ARIMA models
    3. The Kalman filter
    4. Parameter Estimation for State Space models
Syllabus
  1. From Cross-Section to Time Series: asymptotic theory under serial correlation
  2. Stationary Process
    1. Linear processes
    2. The Wold decomposition
    3. ARMA processes
      1. Representation. Estimation. Forecasting. Applications.
  3. Non-stationary Time Series Model
    1. ARIMA models for non-stationary time series
    2. Unit Roots
    3. Forecasting with ARIMA models
  4. Multivariate Time Series
    1. Vector Auto-Regressions (VAR)
    2. Modeling and Forecasting with VAR
    3. Cointegration
    4. Structural vs Reduced Form VAR: identification
  5. State-Space Models
    1. Linear State-Space models
    2. State-Space representation of ARIMA models
    3. The Kalman filter
    4. Parameter Estimation for State Space models
Bibliografia e materiale didattico

The main reference for this courses is:

  • Brockwell, Peter J. and Richard A. Davis, Introduction to Time Series and Forecasting, Springer, 2002

However, especially for some of the topics, other references are going to be useful:

  • Enders, Walter. Applied econometric time series. John Wiley & Sons, 2008
  • James D. Hamilton, Time Series Analysis, Princeton University Press, 2005
Bibliography

The main reference for this courses is:

  • Brockwell, Peter J. and Richard A. Davis, Introduction to Time Series and Forecasting, Springer, 2002

However, especially for some of the topics, other references are going to be useful:

  • Enders, Walter. Applied econometric time series. John Wiley & Sons, 2008
  • James D. Hamilton, Time Series Analysis, Princeton University Press, 2005
Modalità d'esame

The final grade depends on their performances on two written in-class exams, a midterm and a comprehensive final, and a take-home exam. The take-home is made available to students two weeks prior to the end of the course and it is due back at the beginning of the last day of class.   Midterm, comprehensive final and take-home exam are compulsory for successfully completing the course, and they will be valid until the second semester of the academic year 2019—2020. The final grade is calculated as a weighted average the three exams according to the following weighting scheme:   Take-home: 30% Midterm: 20% Final: 50%      
Assessment methods

The final grade depends on their performances on two written in-class exams, a midterm and a comprehensive final, and a take-home exam. The take-home is made available to students two weeks prior to the end of the course and it is due back at the beginning of the last day of class.   Midterm, comprehensive final and take-home exam are compulsory for successfully completing the course, and they will be valid until the second semester of the academic year 2019—2020. The final grade is calculated as a weighted average the three exams according to the following weighting scheme:   Take-home: 30% Midterm: 20% Final: 50%      
Updated: 21/02/2019 13:32