EcoSta 2022: Start Registration
View Submission - EcoSta2022
A0438
Title: Option-implied forecasts with robust change of measure Authors:  Mamiko Yamashita - Toulouse School of Economics (France) [presenting]
Abstract: Option prices can be useful in forecasting since it has forward-looking information, yet the challenge lies in how to transform the risk-neutral measure implied by options to the physical one. Whereas existing papers overcome this issue by assuming an equilibrium model, we introduce a novel approach that does not require any model assumptions. Following the robustness literature, we take the risk-neutral measure as the reference model, and consider a set of measures that are ``close'' to the risk-neutral measure in the relative entropy sense. Then the robust forecast involves minimizing the maximum risk that corresponds to the nature of the forecast in question over this set. We also provide three indicators on the relative entropy bound, which is needed to be determined by a forecaster in our approach, by exploiting the theoretical connection between the risk-neutral and physical measures. In an empirical application, we compute 5\% value-at-risk and expected shortfall on S\&P500 Index returns. In our sample, we document that the robust value-at-risk is about 4\%/12\%/17\% (for 1-day/10-day/22-day horizons) higher, and the robust expected shortfall is about 5\%/15\%/24\% (for 1-day/10-day/22-day horizons) higher than the risk-neutral counterparts.