Hurst exponent confidence intervals

For questions regarding programming in the EViews programming language.

Moderators: EViews Gareth, EViews Jason, EViews Moderator, EViews Matt

Posts: 1
Joined: Tue Sep 12, 2023 6:28 am

Hurst exponent confidence intervals

Postby cauret » Thu Sep 14, 2023 1:23 am

Some time ago you created an EViews program for me to calculate the Hurst exponent of a time series, using the R/S methodology. Running the program, I just get 1 result which is the Hurst exponent. I also need the lower and upper confidence levels, preferably for the 95% level. If you can also add the 90% and 99% levels, it will be great. I am presenting a paper in Europe shortly and I need the 95% lower and upper confidence intervals rather urgently.

Also, according to the literature the R/S methodology of calculating the Hurst exponent is the preferred one for monthly and quarterly i.e., lower frequencies. The Peng methodology is best for calculating the Hurst exponent for daily frequencies and the Whittle methodology is best for calculating the Hurst exponent for weekly frequencies. Would it be possible for you to add these two methodologies for calculating the Hurst exponent in future together with the confidence intervals?

I am awaiting your speedy response, in particular my request in the first paragraph above as I need it for my paper to be presented in Europe in a week from now.

Best regards.
Prof Christo Auret
University of the Witwatersrand, Johannesburg, South Africa.

Return to “Programming”

Who is online

Users browsing this forum: No registered users and 12 guests