Acceso usuarios
Ana Filipa Carvalho, J. M. G. Sá da Costa, José Assis Lopes
Over the past decade, econometric modelling of the volatility clustering phenomenon has been a very active area of research and several new approaches have been proposed and tested. Given the ever greater role of futures markets in risk management in modern economic theory, it seems advisable to formulate a systematic methodology for modelling these financial tools. In this paper, using soybean futures data, a systematic modelling strategy is proposed that takes into account the various aspects that should be incorporated in a bona fide volatility model. Several volatility models are analysed and compared in terms of their in-sample fit adequacy and predictive ability. Special attention is devoted to the asymmetric effect that the arrival of news may have on volatility. The proposed approach is sufficiently broad to be applied to other futures markets.
