Modeling Dependence using Copula Garch
Floriane Nsabimana *
The Catholic University of Eastern Africa, Nairobi, Kenya.
Hellen Waititu
The Catholic University of Eastern Africa, Nairobi, Kenya.
Cornelious Nyakundi
The Catholic University of Eastern Africa, Nairobi, Kenya.
*Author to whom correspondence should be addressed.
Abstract
This study sought to investigate the tail dependence between government debt and bank's nonperforming loans. The objectives of this study were formulation of a bivariate copula model which captures the dependence between government debt and bank non-performing loans and measuring the tail and asymmetric dependence between the two variables, the study used quarterly data sourced from World Bank. To model the dependence between debt and bank non-performing, dierent methods have been used. The study estimated the dependence using copula GARCH, an approach that combines copula functions and GARCH models. According to forming the effect of local government debt and bank's non-performing loans, copula models have been applied to analyze the asymmetry of tail dependence structure between government debt exposure and bank non-performing loans. We used R programming language and Excel to plot and analyze data. The results showed that student t copula parameter provided the best fit for the marginal distributions. The results show the in uence of government debt on bank non-performing loans. Further researchers should focus on time to ensure the effectiveness of risk measurement and management.
Keywords: Copula, tail dependence, Government debt, bank non-performing loans