Time series analysis requires to understand the notions of stationarity and non-stationarity, which will be presented in an intuitive and detailed way by the use of examples of macroeconomic and financial time series. Then, econometric models adapted to model such series will be explained and applied. The theme of prediction is obviously very important for time series and will be covered for each type of model. Although the course is focused on the univariate approach, an introduction to multivariate aspects is foreseen. Inference methods (like ordinary least squares and maximum likelihood) are taught or reminded in the context of the models that require them.
(subject to change)
1. Time Series Data and Programming
2. Stationarity
3. Moving Average Model (MA)
4. Auto-Regressive Model (AR)
5. ARMA Modeling
6. Non-stationarity and Integrated process
7. Filters and Seasonality
8. System Identification
9. Vector AR
10. VAR Modeling
11. Kalman Filter
Reference book:
Introductory Time Series with R (2009), Paul S.P. Cowpertwait, Andrew V. Metcalfe.
Other reference books:
Time Series Analysis and Its Applications with R Examples (2011), 3rd Edition, Robert H. Shumway, David S. Stoffer
Time Series Analysis: Forecasting and Control (2015), 5th Edition, George E. P. Box, Gwilym M. Jenkins, Gregory C. Reinsel, Greta M. Ljung
- Teacher: Monti Francesca
- Teacher: Toniotti Martial