THEORY AND METHODS NIG-GARCH MODELS BASED ON OPEN, CLOSE, HIGH AND LOW PRICES

Lildholdt (2002) introduces a method to fit GARCH models to financial return series using open, close, high and low prices. This method assumes that the price process on each day follows a lognormal diffusion with constant volatility for that day. It is well known that the consequent normality of the innovation distribution of the GARCH model for the return process is too light tailed to be realistic in many cases in practice. Accumulating evidence points to the NIG based approach being more realistic. This paper extends Lildholdt's model to incorporate the latter approach. An example illustrates the effectiveness of the extension.