Estimation and Filtering With Big Option Data

The computational cost of estimating option valuation models is very high, due to model complexity and the abundance of available option data. We propose an approach that addresses these computational constraints by filtering the state variables using particle weights based on model-implied spot volatilities rather than model prices. We show that this approach is reliable. We illustrate our method by estimating the workhorse stochastic volatility and double-jump models using a big option data set. We obtain more precise estimates of variance risk premia and more plausible implied preference parameters, and we show that for these models moneyness and especially maturity restrictions may result in identification problems. The composition of the option sample affects parameter inference and the relative importance of options and returns in joint estimation.