Asymmetries in volatility and perturbations in multivariate GARCH models

• Grant number: 12/09597-7
• Support Opportunities: Scholarships abroad - Research Internship - Master's degree
• Start date: September 01, 2012
• End date: January 31, 2013
• Field of knowledge: Physical Sciences and Mathematics - Probability and Statistics - Statistics
• Principal Investigator: Luiz Koodi Hotta
• Grantee: Daniel de Almeida
• Supervisor: Esther Ruiz Ortega
• Host Institution: Instituto de Matemática, Estatística e Computação Científica (IMECC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Institution abroad: Universidad Carlos III de Madrid (UC3M), Spain
• Associated to the scholarship: 11/02881-9 - Asymmetries in volatility and perturbations in volatility models, BP.MS

Abstract

The main goal of the project to be developed at the University Carlos III, Spain, is to study multivariate models of volatility which takes into account two types of asymmetry commonly found in financial series, the asymmetry of the disturbances and the leverage effect. The first type of asymmetryis used to consider one of the stylized facts that losses have distribution with heavier tails than gains. The second type of asymmetry, the leverage effect, takes into account that the losses have larger influence in volatility than the gains. To date, in the master's project, univariate GARCH models were compared with standardized Student-t disturbances with i) standardized asymmetric t-Student disturbances models without asymmetry and leverage effect and ii) EGARCH, TGARCH, GJR and APARCH models which have the leverage effect. The applications to 16 series, mostly Brazilian, showed clearly that the models considering the two types of asymmetry are better both in the adjustments and in the predictions. This project goals is to extend the study to the multivariate case, considering the various specifications of multivariate GARCH models, incorporating both types of asymmetries, separately and jointly. (AU)