Asymptotic Expansion for the Normal Implied Volatility in Local Volatility Models

TL;DR

This paper derives a small-time asymptotic expansion for normal implied volatility in local volatility models, revealing similarities to log-normal cases and identifying potential failures in models with nonanalytical volatility.

Contribution

It provides a detailed asymptotic expansion for normal implied volatility in local volatility models, including cases with discontinuous derivatives, using perturbation theory.

Findings

Asymptotics similar to log-normal volatility at leading order

Differences appear at order T^2 in small-time expansion

Expansion can fail for models with nonanalytical local volatility

Abstract

We study the dynamics of the normal implied volatility in a local volatility model, using a small-time expansion in powers of maturity T. At leading order in this expansion, the asymptotics of the normal implied volatility is similar, up to a different definition of the moneyness, to that of the log-normal volatility. This relation is preserved also to order O(T) in the small-time expansion, and differences with the log-normal case appear first at O(T^2). The results are illustrated on a few examples of local volatility models with analytical local volatility, finding generally good agreement with exact or numerical solutions. We point out that the asymptotic expansion can fail if applied naively for models with nonanalytical local volatility, for example which have discontinuous derivatives. Using perturbation theory methods, we show that the ATM normal implied volatility for such a model contains a term ~ \sqrt{T}, with a coefficient which is proportional with the jump of the derivative.