Mean-Reverting 4/2 Principal Components Model. Financial Applications

In this paper, we propose a new multivariate mean-reverting model incorporating state-of-the art 4/2 stochastic volatility and convenient principal component (PCSV) decomposition for the covariance. We find quasi closed-form characteristic function analytic approximations, which aid in pricing of derivatives calculation risk measures. Parameters are estimated on three bivariate series, using two-stage methodology involving method moments least squares. Moreover, scaling factor is added extra degrees freedom to match data features. As an application, consider investment strategies portfolio with two risky assets risk-free cash account. calculate value-at-risk (VaR) values at 95% level both simulation-based distribution-based methods. A comparison these VaR supports effectiveness our approximations potential higher dimensions.