Poslední úprava: PhDr. Petr Bednařík, Ph.D. (17.02.2020)
Please switch to the english version.
Poslední úprava: Mgr. Michaela Čuprová (20.11.2019)
THE COURSE WILL NOT BE OFFERED IN 2017/2018 ACADEMIC YEAR.
The primary objective of this course is to provide the students with the basic tools used in the contemporary macroeconometrics. Specifically, Bayesian and state space techniques will be introduced. These techniques are the workhorse models in the state-of-art macroeconomic research and are heavily used in practice as well (e.g central banks, international insititutions). The course will provide introduction to basic methodological and theoretical concepts. The main focus, however, will be on practical examples in Matlab. After successful completion of the course, the students should be able to understand and use these techniques in their applied research. Moreover, they should be well prepared to apply and extend baseline macroeconometric models in their bachelor or master thesis. The knowledge of these models will allow the students to pursue research that can be publishable in quality international journals.
Podmínky zakončení předmětu -
Poslední úprava: PhDr. Petr Bednařík, Ph.D. (17.02.2020)
Please switch to the english version.
Poslední úprava: PhDr. Jaromír Baxa, Ph.D. (15.02.2023)
Assignment: Final paper
Choose one country for which you will estimate the propagation of a shock of your interest and forecast the GDP growth and inflation. To do that, you will utilize the methods covered in the course and explore their properties, forecast performance, and robustness.
The final paper will be prepared throughout the whole semester, with three intermediate deadlines:
after lecture 4: ARIMA model of inflation and GDP, estimation of potential structural breaks, estimation of spectra of both series, forecast 1 period and 1 year ahead; evaluation of a cyclical position of the economy
after lecture 8: VAR I - short-run restrictions, sign restrictions + VAR forecasts.
after lecture 11: VAR II - local projections, Bayesian VAR + BVAR forecasts.
The outcomes of these intermediate stages will be presented and discussed during the seminars.
Grades: Intermediate stages and presentations - 20 points each (60 in total), final paper + presentation, and participation at the workshop 40 points. The final paper and participation at the workshop are necessary conditions to pass the course, even if the sum of intermediate points exceeds 50.5
Poslední úprava: PhDr. Petr Bednařík, Ph.D. (17.02.2020)
Please switch to the english version.
Poslední úprava: PhDr. Petr Bednařík, Ph.D. (06.06.2020)
Recommended textbooks:
Koop, G. (2003): Bayesian Econometrics, John Wiley & Sons
Kim, Ch. & Nelson, C.R. (1999): State-Space Models with Regime Switching, MIT Press
Metody výuky -
Poslední úprava: PhDr. Jaromír Baxa, Ph.D. (07.02.2022)
Lectures will provide context and description of the empirical methods.
Students are supposed to cover selected methods in regular problem sets, that are based on replications of academic papers. Sample R codes will be provided. Problem sets are presented and discussed during the seminars.
Poslední úprava: PhDr. Jaromír Baxa, Ph.D. (07.02.2022)
Lectures will provide context and description of the empirical methods.
Students are supposed to cover selected methods in regular problem sets, that are based on replications of academic papers. Sample R codes will be provided. Problem sets are presented and discussed during the seminars.
Sylabus -
Poslední úprava: PhDr. Petr Bednařík, Ph.D. (17.02.2020)
Please switch to the english version.
Poslední úprava: PhDr. Petr Bednařík, Ph.D. (06.06.2020)
THE COURSE WILL NOT BE OFFERED IN 2017/2018 ACADEMIC YEAR.
Lecture 1 - Course overview / Introduction to Bayesian Econometrics
Lecture 2 - Normal linear regression with natural conjugate prior
Lecture 3 - Normal linear regression with other priors / Gibbs sampling
Lecture 4 - Nonlinear regression model / Metropolis Hastings algorithm
Lecture 5 - Bayesian model averaging
Lecture 6 - Bayesian vector autoregressions
Lecture 7 - Introduction to state space modelling & Kalman filter
Lecture 8 - Estimation of state-space models (classical)
Lecture 9 - Estimation of state-space models (Bayesian)
