SFEP
Smooth Forecasting of Evolutionary Panels
| Coordinatore | UNIVERSITEIT MAASTRICHT
Organization address
address: Minderbroedersberg 4-6 contact info |
| Nazionalità Coordinatore | Netherlands [NL] |
| Totale costo | 154˙548 € |
| EC contributo | 154˙548 € |
| Programma | FP7-PEOPLE
Specific programme "People" implementing the Seventh Framework Programme of the European Community for research, technological development and demonstration activities (2007 to 2013) |
| Code Call | FP7-PEOPLE-2009-IEF |
| Funding Scheme | MC-IEF |
| Anno di inizio | 2010 |
| Periodo (anno-mese-giorno) | 2010-08-01 - 2012-07-31 |
Partecipanti
| # | ||||
|---|---|---|---|---|
| 1 |
UNIVERSITEIT MAASTRICHT
Organization address
address: Minderbroedersberg 4-6 contact info |
NL (MAASTRICHT) | coordinator | 154˙548.80 |
Mappa
Word cloud
Esplora la "nuvola delle parole (Word Cloud) per avere un'idea di massima del progetto.
Obiettivo del progetto (Objective)
'The main goal of this project is to develop theoretical and applied research on forecasting economic and financial data, whose structure changes over time. The classical theory of forecasting is well developed under the assumption that the data generating process is stationary over time. Put loosely, stationarity means that the properties of the underlying model do not change through time. Economies are manifestly non-stationary for many reasons, and in particular, are subjected to structural changes. This can lead to huge forecasting errors and unreliability of the model in general. For example, structural instability pervades many representative Post War US macroeconomic time series, and the forecasting relations that exist between those series. The so-called structural break model is based on the assumption that the breaks occur over time in an abrupt way. The disadvantage of modeling non-stationarity by means of a structural-break model is that the exact moment when the break occurs is unknown and often difficult to detect. An alternative way to specify the non-stationarity is based on the assumption that the changes in the structure of the data are not abrupt but smooth. In addition to non-stationarity, these time series can be highly correlated, which motivates the use of dimension-reduction techniques. Linear factor models have attracted considerable interest over recent years because of the intuitively appealing idea to explain a panel with a large number of time series by a few common latent factors. In our PhD thesis (see Motta 2009) we developed for the first time a theoretical framework to model economic and financial time series whose behavior is characterized by smooth evolutions of the dynamics and a factor structure. In this project we intend to go further and develop the forecasting dimension. The forecasting of how interest rates will develop, for example, can function as an early warning system for economic crises.'