Statistical inference for random-variance option pricing

This article deals with the estimation of continuous-time stochastic volati lity models of option pricing. We argue that option prices are much more in formative about the parameters than are asset prices. This is confirmed in a Monte Carlo experiment that compares two very simple strategies based on the different information sets. Both approaches are based on indirect infer ence and avoid any discretization bias by simulating the continuous-time mo del. We assume an Ornstein-Uhlenbeck process for the log of the volatility, a zero-Volatility risk premium, and no leverage effect. We do not pursue a symptotic efficiency or specification issues; rather, we stick to a framewo rk with no overidentifying restrictions and show that, given our option-pri cing model, estimation based on option prices is much more precise in sampl es of typical size, without increasing the computational burden.