3
$\begingroup$

if I want to use t-test to test significance of my returns, it assumes the random variable is distributed normally. But in my work I work under stable distributed returns. It seems inappropriate to use this test then. Is there an alternative? Cannot google anything.

Cheers guys

$\endgroup$
  • 2
    $\begingroup$ Using 'I'm Feeling Lucky' button: tandfonline.com/doi/abs/10.1080/02664763.2012.740618 Parkinson (2102) z Test for the significance of the mean of a stable probability distribution $\endgroup$ – noob2 Sep 7 '16 at 19:38
  • $\begingroup$ Thanks a lot @noob2 , exactly what I wanted. Guess should have searched z test :) Want to copy it as answer so I can accept it? Thanks a lot again! $\endgroup$ – Jan Sila Sep 8 '16 at 14:13
0
$\begingroup$

I am not an expert on this topic, but I saw a recent article

Parkinson (2102): z Test for the significance of the mean of a stable probability distribution http://tandfonline.com/doi/abs/10.1080/02664763.2012.740618

that may be of interest to you.

$\endgroup$
0
$\begingroup$

The four parameters of a stable distribution may be estimated by maximum likelihood. John Nolan's stable package is available from http://www.robustanalysis.com/ in forms suitable for use in C, C++, R, matlab Mathematica and excel with Windows, Linux or Mac. The package estimates the parameters and produces confidence intervals.

You might also look at the stable.exe program available at http://fs2.american.edu/jpnolan/www/stable/stable.html. This also does maximum likelihood estimates of the parameters and produces confidence intervals.

You might also find some of the material in http://www.tcd.ie/Economics/staff/frainj/Stable_Distribution/thesis_main_5.pdf useful

$\endgroup$
  • $\begingroup$ Thanks, I've got those. Nolan's MLE estimates are paid only, so I made my own before. I needed to test significance of non-zero mean (location parameter) for stable distributions as noob2 found in the answer above $\endgroup$ – Jan Sila Sep 14 '16 at 17:59
  • $\begingroup$ The Nolan stable,exe file is free. I will try and get a copy of the Parkinson paper and see what is new. The version of the z-statistic derived from the ML estimates has been widely used and the basic theory dates back to DuMouchel in the 70's. (1971, 1973 and 1975) $\endgroup$ – user1483 Sep 15 '16 at 21:34
  • $\begingroup$ I've got and implemented Parkinson's method... Will check our DuMouchel :) thanks $\endgroup$ – Jan Sila Sep 15 '16 at 21:37
  • $\begingroup$ Btw exe file is good as long as your dont have a Mac :D $\endgroup$ – Jan Sila Sep 15 '16 at 21:37
  • $\begingroup$ The stable.exe program is basically a simple MS-Dos program and runs in windows in a command window. I have no experience with Mac I would think that it would run on a Mac using one of the emulators used to run old Dos games $\endgroup$ – user1483 Sep 16 '16 at 21:50

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.