Análise de volatilidade e risco do mercado transoceânico à vista deminério de ferro via modelos ARMA-GARCH e medidas de risco VaR eCVaR

• Ano de defesa: 2016
• Autor(a) principal: José Henrique do Valle Pácola
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Minas Gerais; UFMG
• Palavras-chave em Português: Cvar; Var; Arch; Garch; Preço à vista do minério de ferro; Minérios de ferro; Engenharia elétrica; Índices de preços
• Link de acesso: http://hdl.handle.net/1843/BUOS-ATJLXW

With the change in the seaborne iron ore pricing mechanism in 2009, from an annual benchmark system to a system based on monthly spot prices, as well as the spot sales without a pre-agreement, market agents have to deal with an increased volatility and, consequently, with an increased risk. ARCH and GARCH models are widely used to model the volatility of financial series. They have also been employed to compute the risk measures such as Value-at-Risk (VaR) and Conditional Value-at-Risk (CVaR). These measures have been increasingly adopted by market agents in evaluating risk. This work aims to model the volatility and compute the risk for the returns of three Platts-owned iron ore spot prices assessments, the Iron Ore Fines 58% Fe, the IODEX 62% Fe and the Iron Ore Fines 65% Fe. For such a purpose, we identify different orders of ARMA-GARCH models as means of modeling the conditional variance of price returns. Both normal and Students t probability distributions are tested for the innovations. The parameters of the models are estimated via maximum likelihood and the models are selected according to the AIC and BIC information criteria. For the selected models, we run Monte Carlo Simulations to generate samples of future returns in the upcoming month and then compute the VaR and CVaR risk measures using linear programming for confidence levels varying from 10% to 99 %. Finally, we compute trimmed monthly average returns using the CVaR measures, and examined whether there is a hierarchy of risk and return between the three iron ore price assessments.