In the present paper we consider the Quasi Maximum Likelihood (QML) procedure for the estimation of stationary Stochastic Volatility models. We prove the consistency of the QML estimators and compute explicitly their asymptotic variances. This allows us to obtain also consistent estimators of the asymptotic variances in explicit forms. The knowledge of the asymptotic variance-covariance matrix of the QML estimators gives a concrete possibility for the use of the classical testing procedures. Our results are related to those obtained in Ruiz (1994) and Bartolucci and De Luca (2001) (2003).
Quasi Maximum Likelihood Inference for Stochastic Volatility Models / Cavicchioli, Maddalena. - In: FRONTIERS IN FINANCE AND ECONOMICS. - ISSN 1814-2044. - STAMPA. - 11:(2014), pp. 1-24.
Quasi Maximum Likelihood Inference for Stochastic Volatility Models
CAVICCHIOLI, MADDALENA
2014
Abstract
In the present paper we consider the Quasi Maximum Likelihood (QML) procedure for the estimation of stationary Stochastic Volatility models. We prove the consistency of the QML estimators and compute explicitly their asymptotic variances. This allows us to obtain also consistent estimators of the asymptotic variances in explicit forms. The knowledge of the asymptotic variance-covariance matrix of the QML estimators gives a concrete possibility for the use of the classical testing procedures. Our results are related to those obtained in Ruiz (1994) and Bartolucci and De Luca (2001) (2003).
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
