Assessing dependence between financial market indexes using conditional time-varying copulas: applications to Value at Risk (VaR)
Quantitative finance (Print)
In this paper, we analyze the time dynamics of the dependence structure between IBOVESPA (Índice da Bolsa de Valores do Estado de São Paulo) and the following three indexes: FTSE100 (Financial Times and London Stock Exchange Index), IPCMX (Índice de Precios y Cotizaciones da Bolsa Mexicana de Valores) and S&P500 (Standard and Poor 500 Index). We follow Patton's (2006) conditional copula setting and additionally observe the impact of different copula functions on Value at Risk (VaR) estimation
... r a naive proposed portifolio. We conclude that the dependence between IBOVESPA and other financial market indexes has intensified from the beginning of 2006. Furthermore in our case the copula form seems not to be relevant for VaR estimation, since all copulas lead to significant VaR estimates. Finally, to identify which copula functions lead to the best fit to the data we apply a goodness-of-fit test based on parametric bootstrap. We find that the best fits are obtained via the time constant t-student and the time-varying Normal copulas.