Estimating volatility for long holding periods

MaRDI QIDQ4518933zbMATH OpenFDO

Authors Rüdiger Kiesel, William R. M. Perraudin, Alex M. K. P. Taylor

Publication date 18 January 2001

zbMATH Keywords

first-difference stationary processinterest rate volatilityMonte Carlo illustrationsvariance ratio

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Applications of statistics to actuarial sciences and financial mathematics (62P05) Stochastic models in economics (91B70)

Review text

The paper deals with estimation of short-term interest rate volatility over long holding periods without using any specific parametric model. The basic assumption is that the process is first-difference stationary (which excludes continuous-time mean-reverting processes). Such processes may be represented as a sum of a stationary and a random walk component whose variance is the dominating part of the long-term behavior of the total variance. The proposed estimator results from this representation with direct application of sample estimators of autocovariances. Its asymptotic properties and bias adjustment are studied. Monte Carlo illustrations under various distributional assumptions and empirical comparisons of the related single-factor diffusion models of the short-term interest rates are presented. For the entire collection see [Zbl 0943.00038].

Recommendations

• Estimating continuous-time stochastic volatility models of the short-term interest rate
• Estimation of long memory in integrated variance
• Estimation of long memory in volatility
• Estimating Long Memory in Volatility
• ON THE LOG PERIODOGRAM REGRESSION ESTIMATOR OF THE MEMORY PARAMETER IN LONG MEMORY STOCHASTIC VOLATILITY MODELS

Cited in

(1)

• Estimating the long rate and its volatility

This page was built for publication: Estimating volatility for long holding periods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4518933)