Forecasting linear dynamical systems using subspace methods
ISSN: 2341-2356
Año de publicación: 2009
Número: 2
Páginas: 1-15
Tipo: Documento de Trabajo
Otras publicaciones en: Documentos de Trabajo (ICAE)
Resumen
This paper presents a novel approach to predict with subspace methods. It consists in combining multiple forecasts obtained from setting a range of values for a speci c parameter that is typically xed by the user in this literature. Two procedures are proposed. The rst one combines all the forecast in a particular range. The second one predicts with a restricted number of combinations previously optimized. Both methods are evaluated using Monte Carlo experiments and by forecasting the German gross domestic product.