Malaysian Journal of Mathematical Sciences, October 2014, Vol. 8(S)
Special Issue: International Conference on Mathematical Sciences and Statistics 2013 (ICMSS2013)
Dependence Measures in Malaysian Stock Market
Ruzanna Ab Razak and Noriszura Ismail
Corresponding Email: [email protected]
Received date: -
Accepted date: -
Abstract:
Return series tend to have leptokurtic distribution thus making linear correlation an inappropriate measure of dependence. The copula has been used to capture such dependency. However, there has been little literature on modeling and estimating the dependence between two series in Malaysian financial stock market. The purpose of this study is to investigate the dependence structure between two return series of the Kuala Lumpur Composite Index (KLCI) and the capitalization weighted index (EMAS) for the period 1998:M1 to 2005:M12. The results show that the Student's $t$ copula is suitable to represent the dependence structure of KLCI-EMAS pair. This finding indicates that there is slight strong dependence at the upper and lower tails of the two series. The significance of these tail dependences implies that the return series of Kuala Lumpur Composite Index and the capitalization weighted index tend to experience concurrent shocks.
Keywords: copula, tail dependence, dependence structure
