Working Paper: CEPR ID: DP12687
Authors: Tim Bollerslev; Benjamin Hood; John Huss; Lasse Heje Pedersen
Abstract: Based on a unique high-frequency dataset for more than fifty commodities, currencies, equity indices, and fixed income instruments spanning more than two decades, we document strong similarities in realized volatilities patterns across assets and asset classes. Exploiting these similarities within and across asset classes in panel-based estimation of new realized volatility models results in superior out-of-sample risk forecasts, compared to forecasts from existing models and more conventional procedures that do not incorporate the information in the high-frequency intraday data and/or the similarities in the volatilities. A utility-based framework designed to evaluate the economic gains from risk modeling highlights the interplay between parsimony of model specification, transaction costs, and speed of trading in the practical implementation of the different risk models.
Keywords: Market and Volatility Risk; High-Frequency Data; Realized Volatility; Risk Modeling and Forecasting; Volatility Trading; Risk Targeting; Realized Utility
JEL Codes: C22; C51; C53; C58
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| forecasting accuracy (C53) | investor utility (G11) |
| model specification (C52) | trading outcomes (F10) |
| new models (C59) | forecasting accuracy (C53) |
| improved risk models (C52) | investor utility (G11) |