The cross-section of options holds great promise for identifying return distributions and risk premia, but estimating dynamic option valuation models with latent state variables is challenging when using large option panels. We propose a particle MCMC framework with a novel filtering approach and illustrate our method by estimating workhorse index option pricing models. Estimates of the variance risk premium, variance mean reversion, and higher moments differ from the literature. We show that these differences are due to the composition of the option sample. Restrictions on the option sample's maturity dimension have the strongest impact on parameter inference and option fit in these models.