Optimal futures hedging under jump switching dynamics

The article develops a Markov regime switching Generalized Orthogonal GARCH model with conditional jump dynamics (JSGO) for optimal futures hedging. To the author's knowledge, there is no existing study on dynamic futures hedging investigating both the effects of regime switching and conditional jumps. This might be the fact that there is no existing hedging model encompassing both of these features. The JSGO solves this problem by introducing a jump switching filtering algorithm to infer ex post both the distributions of jumps and state variables and a recombining procedure to solve the path-dependency problem. To justify the usefulness of the JSGO on dynamic futures hedging, hedging exercises are performed using FTSE 100 futures data traded in the London International Financial Futures and Options Exchange (LIFFE). JSGO exhibits good out-of-sample performance compared to its jump-free and state-independent counterparts in terms of both criteria of variance reductions and utility improvements.