Publication: Modelos de memoria larga para series económicas y financieras
No Thumbnail Available
Identifiers
Publication date
2002-09
Defense date
Authors
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Fundación Empresa Pública (Fundación SEPI)
Impact
Export
Abstract
En este trabajo se hace una revisión de los modelos de series temporales con memoria larga para la media y la varianza condicionada, con especial atención a los modelos ARMA fraccionalmente integrados (ARFIMA) y a los modelos GARCH y SV fraccionalmente integrados. Se estudian sus propiedades más importantes y se discute su aplicación en la modelización de series económicas y financieras. También se describen los principales métodos de estimación propuestos para estos modelos y se revisan algunos contrastes para detectar la presencia de memoria larga. Finalmente, se revisan los principales resultados sobre predicción de valores futuros de series temporales con memoria larga.
This paper provides a review of time series models with long memory in the mean and conditional variance, with special attention to Fractionally Integrated ARMA processes (ARFIMA) and fractionally integrated GARCH and SV processes. Their more important properties are reviewed and its application to model economic and financial time series is discussed. The main estimation methods and tests proposed in the literature for the long memory property are also reviewed. Finally, this paper reviews the main results on prediction of future values of long memory time series.
This paper provides a review of time series models with long memory in the mean and conditional variance, with special attention to Fractionally Integrated ARMA processes (ARFIMA) and fractionally integrated GARCH and SV processes. Their more important properties are reviewed and its application to model economic and financial time series is discussed. The main estimation methods and tests proposed in the literature for the long memory property are also reviewed. Finally, this paper reviews the main results on prediction of future values of long memory time series.
Description
Keywords
Integración fraccional, Persistencia, Dominio de las frecuencias, Densidad espectral, Volatilidad, Fractional integration, Persistency, Frequency domain, Spectral density, Volatility
Bibliographic citation
Investigaciones Económicas (2002), 26 (3), 395-445