Limitation of the Least Square Method in the Evaluation of Dimension of Fractal Brownian Motions

preprint2015arXivOpen access

Abstract

With the standard deviation for the logarithm of the re-scaled range ⟨∣F(t+τ)−F(t)∣⟩\langle |F(t+τ)-F(t)|\rangle of simulated fractal Brownian motions F(t)F(t) given in a previous paper \cite{q14}, the method of least squares is adopted to determine the slope, SS, and intercept, II, of the log(⟨∣F(t+τ)−F(t)∣⟩)(\langle |F(t+τ)-F(t)|\rangle) vs log(τ)\rm{log}(τ) plot to investigate the limitation of this procedure. It is found that the reduced χ2χ^2 of the fitting decreases with the increase of the Hurst index, HH (the expectation value of SS), which may be attributed to the correlation among the re-scaled ranges. Similarly, it is found that the errors of the fitting parameters SS and II are usually smaller than their corresponding standard deviations. These results show the limitation of using the simple least square method to determine the dimension of a fractal time series. Nevertheless, they may be used to reinterpret the fitting results of the least square method to determine the dimension of fractal Brownian motions more self-consistently. The currency exchange rate between Euro and Dollar is used as an example to demonstrate this procedure and a fractal dimension of 1.511 is obtained for spans greater than 30 transactions.

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.