5
$\begingroup$

Are there any general assumptions for the calculation of the Hurst exponent?

  • Does the signal need to be stationary, for example?

  • Does it depend on the method?

  • What about the length of the time series, is longer better?

I am interested in using implementing it for the analysis of an EEG signal. I have read many articles but can't find answers for these questions.

$\endgroup$
2
$\begingroup$

The best is to calculate Hurst for stationary data (as then you can somehow find out if there are long range dependency signals which are not part of AR or MAs) but you can do non stationary as well. You can calculated froma fractal or wavelet transforms. Results are different

In calculating Hurst you have to divide the data in short windows and average the results, (place a range the last 8 elements). Hurst can fluctuate significantly depending on the period you select.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.