Department of Statistics Seminar*
North Carolina State University

presents

Dr. George Tiao

University of Chicago

"Effect of Non-Normality and Dependence on the Precision of Variance Estimates Using High-Frequency Financial Data"

ABSTRACT

Volatility (variance) is central to financial theory. Merton's seminal work (1980) suggests that as the sampling interval approach zero arbitrarily precise variance estimates can be obtained. We examine the precision of estimates of unconditional daily variance that use high frequency intra-day data, and derive analytical expression for the precision as a function of the prominent features of intra-day data including leptokurtosis, autocorrelation in the returns, deterministic diurnal variance pattern and volatility clustering. Once these features are accounted for, we find that large amounts of high frequency data do not necessarily translate into very precise estimates. Our results provide a measure of the usefulness of high frequency data in estimating volatility.

Thursday, February, 14, 2002*

4:00 - 5:00 pm

208 Patterson Hall

*This talk is on a Thursday [Notice the change in time and place]