[R] fSeries Package

From: ED <edzabc_at_gmail.com>
Date: Mon 08 Jan 2007 - 16:18:07 GMT


Dear All;

I have used fbmSim to simulate a fbm sequence, however, when I tried to estimate the Hurst effect, none of the nine procedures gave me an answer close enough to the real value, which is 0.5 (n=1000). So, would you please advice,

  1. which is the best method to estimate the H among the 9 mehods, R/S, higuchi or Whittle?
  2. how to choose the levels (default=50), minnpts, cutoff values or if there is any other issues to consider? Would you please send your code if you can get the right estimate for the attached dataset?
  3. I also simulated multiple sequences, but some of the estimated results have H>1, how would you explain this, and how to correct it.
  4. if I have a sample size of 30, what are your suggestions for estimating the hurst effect.

I really appreciate your help, and thanks in advance.

Sincerely;

Ed

        [[alternative HTML version deleted]]



R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Tue Jan 09 04:23:11 2007

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.1.8, at Mon 08 Jan 2007 - 17:30:30 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.