In this paper we consider modeling and forecasting of large realized covariance matrices by penalized vector autoregressive models. We propose using Lasso-type estimators to reduce the dimensionality to a manageable one and provide strong theoretical performance guarantees on the forecast...

In this paper we consider modeling and forecasting of large realized covariance matrices by penalized vector autoregressive models. We propose using Lasso-type estimators to reduce the dimensionality to a manageable one and provide strong theoretical performance guarantees on the forecast...

In diesem Aufsatz wird die nichtparametrische Autoregression auf die Prognose von Quantilen angewendet. Verfahren der Kernregression werden benutzt, um zu autoregressiven Quantiisschätzern zu gelangen. Da die üblichen Maße zur Beurteilung der Prognose, wie etwa der mittlere quadratische...