RT Journal Article
T1 Threshold stochastic volatility: properties and forecasting
A1 Mao, Xiuping
A1 Ruiz Ortega, Esther
A1 Lopes Moreira Da Veiga, María Helena
AB We analyze the ability of Threshold Stochastic Volatility (TSV) models to represent andforecast asymmetric volatilities. First, we derive the statistical properties of TSV models.Second, we demonstrate the good finite sample properties of a MCMC estimator, implementedin the software package WinBUGS, when estimating the parameters of a generalspecification, denoted CTSV, that nests the TSV and asymmetric autoregressive stochasticvolatility (A-ARSV) models. The MCMC estimator also discriminates between the twospecifications and allows us to obtain volatility forecasts. Third, we analyze daily S&P 500and FTSE 100 returns and show that the estimated CTSV model implies plug-in momentsthat are slightly closer to the observed sample moments than those implied by other nestedspecifications. Furthermore, different asymmetric specifications generate rather differentEuropean options prices. Finally, although none of the models clearly emerge as best outof-sample, it seems that including both threshold variables and correlated errors may be agood compromise.
PB Elsevier
SN 0169-2070
YR 2017
FD 2017-11-01
LK https://hdl.handle.net/10016/34949
UL https://hdl.handle.net/10016/34949
LA eng
NO We acknowledge financial support from the Spanish Ministry of Economy and Competitiveness, research projects ECO2015-70331-C2-2-R and ECO2015-65701-P, as well as FCT grant UID/GES/00315/2013.
DS e-Archivo
RD 1 sept. 2024