A0438
Title: Factor multivariate stochastic volatility models of high dimension
Authors: Manabu Asai - Soka University (Japan) [presenting]
Benjamin Poignard - Osaka University (Japan)
Abstract: Building upon the pertinence of the factor decomposition to break the curse of dimensionality inherent to multivariate volatility processes, a factor model-based multivariate stochastic volatility (fMSV) framework is developed that relies on two viewpoints: sparse approximate factor model and sparse factor loading matrix. A two-stage estimation procedure is proposed for the fMSV model: the first stage obtains the estimators of the factor model, and the second stage estimates the MSV part using the estimated common factor variables. The asymptotic properties of the estimators are derived. Simulated experiments are performed to assess the forecasting performances of the covariance matrices. The empirical analysis based on vectors of asset returns illustrates that the forecasting performances of the fMSV models outperform competing conditional covariance models.
