On the Log Periodogram Regression Estimator of the Memory Parameter in Long Memory Stochastic Volatility Models
25 Pages Posted: 31 Oct 2008
Date Written: 1998
We consider semiparametric estimation of the memory parameter in a long memorystochastic volatility model. We study the estimator based on a log periodogramregression as originally proposed by Geweke and Porter-Hudak (1983,Journal of Time Series Analysis 4, 221ÃÂ¢ÃÂÃÂ"238). Expressions for the asymptotic biasand variance of the estimator are obtained, and the asymptotic distribution is shownto be the same as that obtained in recent literature for a Gaussian long memoryseries. The theoretical result does not require omission of a block of frequenciesnear the origin. We show that this ability to use the lowest frequencies is particularlydesirable in the context of the long memory stochastic volatility model.
Suggested Citation: Suggested Citation