Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Univariate and Multivariate GARCH Models Applied to the CARBS Indices
Ist Teil von
Advances in Panel Data Analysis in Applied Economic Research, 2018, p.69-83
Ort / Verlag
Switzerland: Springer International Publishing AG
Erscheinungsjahr
2018
Link zum Volltext
Quelle
Alma/SFX Local Collection
Beschreibungen/Notizen
The purpose of this paper is to estimate the calibrated parameters of different univariate and multivariate generalised autoregressive conditional heteroskedasticity (GARCH) family models. It is unrealistic to assume that volatility of financial returns is constant. In the empirical analysis, the symmetric GARCH and asymmetric GJR-GARCH and EGARCH models were estimated for the CARBS (Canada, Australia, Russia, Brazil, and South Africa) indices and a global minimum variance portfolio (GMVP); the best fitting model was determined using the AIC and BIC. The asymmetric terms of the GJR-GARCH and EGARCH models indicate signs of the leverage effect. The information criterion suggests that the EGARCH model is the best fitting model for the CARBS indices and the GMVP.