Evaluating Implied RNDs by some New Confidence Interval Estimation Techniques

This paper evaluates the precision of the parametric double lognormal (DLN) and the nonparametric smoothing spline method (SPLINE) for estimating risk-neutral distributions (RNDs) from observed option prices. By using a bootstrap technique confidence bands are estimated for the riskneutral distributions (RNDs) and the width is used as the criterion when evaluating the precision of the two. Previous literature on estimating confidence bands has to a large extent been estimated by Monte Carlo methods. We argue that the bootstrap technique is to be preferred due to the non-normality of the error structure. Our findings favour the SPLINE method, yielding tighter confidence bands. An example showing how the confidence intervals could be used for practical purposes is also provided.