Forecasting Equicorrelation

We study the out-of-sample forecasting performance of several time-series models of equicorrelation, which is the average pairwise correlation between a number of assets. Building on the existing Dynamic Conditional Correlation and Linear Dynamic Equicorrelation models, we propose a model that uses proxies for equicorrelation based on high-frequency intraday data, and the level of equicorrelation implied by options prices. Using state-of-the-art statistical evaluation technology, we find that the use of both realized and implied equicorrelations outperform models that use daily data alone. However, the out-of-sample forecasting benefits of implied equicorrelation disappear when used in conjunction with the realized measures.