Doubly Multiplicative Error Models with Long- and Short-run Components

TL;DR

This paper introduces the Doubly Multiplicative Error Models (DMEM) for improved realized volatility forecasting by combining low- and high-frequency data components, supported by theoretical analysis and empirical validation.

Contribution

It proposes the DMEM framework, including the Component-MEM and MEM-MIDAS models, with theoretical properties and superior empirical performance over existing models.

Findings

DMEM models outperform HAR and GARCH-type models in volatility forecasting

Theoretical properties of MLE and GMM estimators are derived

Empirical results across major indices show consistent improvements

Abstract

We suggest the Doubly Multiplicative Error class of models (DMEM) for modeling and forecasting realized volatility, which combines two components accommodating low-, respectively, high-frequency features in the data. We derive the theoretical properties of the Maximum Likelihood and Generalized Method of Moments estimators. Two such models are then proposed, the Component-MEM, which uses daily data for both components, and the MEM-MIDAS, which exploits the logic of MIxed-DAta Sampling (MIDAS). The empirical application involves the S&P 500, NASDAQ, FTSE 100 and Hang Seng indices: irrespective of the market, both DMEM's outperform the HAR and other relevant GARCH-type models.