Finance Discipline Group
UTS Business School
University of Technology, Sydney

Working Paper Series

Title:
Modelling the Expected Value of the Classical Rescaled Adjusted Range for Long-Term Dependent Series
Author(s): Craig Ellis
Date of publication: April 1998
Working paper number: 79
Abstract:
Hurst exponent estimates for long-term dependent series are well known to be biased with respect to their true value. Consequently, results based on the estimation of the classical rescaled adjusted range are conditional upon the choice of an appropriate benchmark, or expected value. The objective of this paper is to propose a framework for the estimation of the expected rescaled adjusted range for a general class of long-term dependent time-series.
Paper: Download (Format: PDF, Size: 644 Kb)
Known citations: Ellis, C., 1999, "Estimation of the ARFIMA (p, d, q) Fractional Differencing Parameter (d) Using the Classical Rescaled Adjusted Range Technique", International Review of Financial Analysis, 8(1), 53-65.