A dynamic factor model framework for forecast combination

• Autores: Mark W. Watson, James H. Stock, Yeung Lewis Chan
• Localización: Spanish economic review, ISSN 1435-5469, Vol. 1, Nº 2, 1999, págs. 91-121
• Idioma: alemán
• Texto completo no disponible (Saber más ...)
• Dialnet Métricas: 1 Cita
• Resumen

  • Abstract. A panel of ex-ante forecasts of a single time series is modeled as a dynamic factor model, where the conditional expectation is the single unobserved factor. When applied to out-of-sample forecasting, this leads to combination forecasts that are based on methods other than OLS. These methods perform well in a Monte Carlo experiment. These methods are evaluated empirically in a panel of simulated real-time computer-generated univariate forecasts of U.S. macroeconomic time series.