MathGroup Archive 2007

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: Fractals and Time Series Analysis by R.J. Korsan appearing in

  • To: mathgroup at
  • Subject: [mg74857] Re: Fractals and Time Series Analysis by R.J. Korsan appearing in
  • From: Roger Bagula <rlbagula at>
  • Date: Sun, 8 Apr 2007 05:08:53 -0400 (EDT)

Peter wrote:

>I recently read Koran's 1993 article and downloaded the associated
>supplment,  I have been trying to replicate the examples
>from Korsans article without success.  I found several minor bugs in
>the code but there are obviously more.
>It occured to me that someone has probably done this already.  Has
>anybody looked at this article and the associated package Hurst.m?
Robert .J. Korsan is an insurance actuary executive.
The so called " Joseph effect"  was discovered by Beniot Mandelbrot:
``Robust R/S analysis of long-run serial correlation'' (with Benoit B.
Mandelbrot). Proceedings of the 42nd Session of the International
Statistical Institute, Manila (1979). / Bulletin of the I.S.I./, Vol. *
48*, Book 2, pp. 69-104. [Authors: M,T]. [MR Ref: 84k:62139], [AMS Subj.
Class.: 62M99 (60K99)].

Andrew Lo's paper is:
Long-Term Memory in Stock Market Prices
Andrew W. Lo
Econometrica, Vol. 59, No. 5 (Sep., 1991), pp. 1279-1313


A test for long-run memory that is robust to short-range dependence is
developed. It is an extension of the "range over standard deviation" or
$R/S$ statistic, for which the relevant asymptotic sampling theory is
derived via functional central limit theory. This test is applied to
daily and monthly stock returns indexes over several time periods and,
contrary to previous findings, there is no evidence of long-range
dependence in any of the indexes over any sample period or sub-period
once short-range dependence is taken into account. Illustrative Monte
Carlo experiments indicate that the modified $R/S$ test has power
against at least two specific models of long-run memory, suggesting that
stochastic models of short-range dependence may adequately capture the
time series behavior of stock returns.

A downloadable paper is which explains the mechanics :
*PS]* A critical look at Lo's modified R/S statistic yz
<> - group of 4 =BB
V Teverovsky, MS Taqqu, *W Willinger* -
Page 1. A critical look at Lo's modied R/S statistic yz Vadim Teverovsky
Boston University Murad S. Taqqu Boston University Walter *...*
Related Articles
- View as HTML
- Web Search

  • Prev by Date: Re: listdensityplot, black box?
  • Next by Date: Re: numerical inversion of laplace transform
  • Previous by thread: .NET/Link Callback from a DLL
  • Next by thread: some questions (unecessary-?-complicated results by Integrate)