We develop a general multivariate aggregation property which encompasses the distinct versions of the property that were introduced by Neuberger [2012] and Bondarenko [2014] independently. This way, we classify new types of model-free realised characteristics for which risk premia may be estimated without bias. We focus on the aggregation property for multivariate martingales and log martingales, and then define realised third and fourth moments which allow long-term higher-moment risk premia to be measured, efficiently and without bias, using high-frequency returns.
↧