Master of Science in Economics

Updated A.Y. 2016-2017

This unit of study aims at providing an advanced knowledge on linear models and methods for economic time series analysis, forecasting and feature extraction. The focus is on state space models, a class of dynamic models such that the series under investigation are related to quantities called states, which are characterised by simple temporal dependence structure. The states have often substantial interpretation. Key estimation problems in macroeconomics concern latent variables, such as the output gap, potential output, the non-accelerating-inflation rate of unemployment, or NAIRU, core inflation, and so forth. These will be typically our states.

Topics addressed in this course include:
1. Introduction. The state space representation and its role in macroeconometrics. Review of optimal and linear prediction theory.
2. Unobserved components models for economic time series. Models for the trend component. Cyclical components. Seasonality and Calendar components. Outliers and structural breaks.
3. State space models and their statistical treatment. Kalman Filter. Maximum likelihood estimation Smoothing filters Forecasting, Diagnostics.
4. Regime Switching Models

Case studies and empirical applications form integral part of the syllabus.

Updated A.Y. 2015-2016

This unit of study aims at providing an advanced knowledge on linear models and methods for economic time series analysis, forecasting and feature extraction. The focus is on state space models, a class of dynamic models such that the series under investigation are related to quantities called states, which are characterised by simple temporal dependence structure. The states have often substantial interpretation. Key estimation problems in macroeconomics concern latent variables, such as the output gap, potential output, the non-accelerating-inflation rate of unemployment, or NAIRU, core inflation, and so forth. These will be typically our states.

Topics addressed in this course include:
1. Introduction. The state space representation and its role in macroeconometrics. Review of optimal and linear prediction theory.
2. Unobserved components models for economic time series. Models for the trend component. Cyclical components. Seasonality and Calendar components. Outliers and structural breaks.
3. State space models and their statistical treatment. Kalman Filter. Maximum likelihood estimation Smoothing filters Forecasting, Diagnostics.
4. Regime Switching Models

Case studies and empirical applications form integral part of the syllabus.

Updated A.Y. 2014-2015

This unit of study aims at providing an advanced knowledge on linear models and methods for economic time series analysis, forecasting and feature extraction. The focus is on state space models, a class of dynamic models such that the series under investigation are related to quantities called states, which are characterised by simple temporal dependence structure. The states have often substantial interpretation. Key estimation problems in macroeconomics concern latent variables, such as the output gap, potential output, the non-accelerating-inflation rate of unemployment, or NAIRU, core inflation, and so forth. These will be typically our states.

Topics addressed in this course include:
1. Introduction. The state space representation and its role in macroeconometrics. Review of optimal and linear prediction theory.
2. Unobserved components models for economic time series. Models for the trend component. Cyclical components. Seasonality and Calendar components. Outliers and structural breaks.
3. State space models and their statistical treatment. Kalman Filter. Maximum likelihood estimation Smoothing filters Forecasting, Diagnostics.
4. Regime Switching Models

Case studies and empirical applications form integral part of the syllabus.