| Abstract: | This article proposes a new approach to exploit the informationin high-frequency data for the statistical inference of continuous-timeaffine jump diffusion (AJD) models with latent variables. Forthis purpose, we construct unbiased estimators of the latentvariables and their power functions on the basis of the observedstate variables over extended horizons. With the estimates ofthe latent variables, we propose a generalized method of moments(GMM) procedure for the estimation of AJD models with the distinguishingfeature that moments of both observed and latent state variablescan be used without resorting to path simulation or discretizationof the continuous-time process. Using high frequency returnobservations of the S&P 500 index, we implement our estimationapproach to various continuous-time asset return models withstochastic volatility and random jumps. |
