Copula is a favored method used to measure dependency for financial data due to its flexibility. Yet, studies about dependence structure between bivariate data especially by using time-varying copula approach is very limited. Hence, this paper will examine the dependenc
More
Copula is a favored method used to measure dependency for financial data due to its flexibility. Yet, studies about dependence structure between bivariate data especially by using time-varying copula approach is very limited. Hence, this paper will examine the dependency between KLCI-FBMHS pair by considering static and time-varying copula. Traditionally, ARCH model is used to measure the volatility. However, it failed to capture stylized facts that usually exist in financial data such as the volatility clustering and leverage effect. Thus, the study also investigates the effect of different marginal models (GARCH and EGARCH) towards dependence structure and parameter estimations. Generally, the findings reveal that KCLI-FBMHS pair have strong dependency. In addition, this study highlight that ARMA(1,0)-GARCH(1,1) and ARMA(1,0)-EGARCH(1,1) with student t distribution are well-fitted to both (KLCI and FBMHS) series, the KLCI-FBMHS pair have similar dependence structure for both static and dynamic copula models.
Manuscript profile
