2
$\begingroup$

Let say i have some data that follows gamma distribution, and i calculated the Mean and Standard deviation of the gamma distribution.

I also know that there are some outliers(Noise) in the data i want to exclude.

Now ,

  1. Is it OK to take Mean+ 3 sigma to cover almost (99.7 %) all data ( like Normal distribution) ?
  2. My target is to exclude the data those are not inside 3 sigma considering as a noise. does it make sense?
$\endgroup$
1
$\begingroup$

It's looks like 3 sigma consideration is kind of acceptable.

While the area within three standard deviations of the mean does drop slightly at first, it stabilizes for the J-shaped Gammas at about 97.5 percent. This means that a fixed-width, three-standard-deviation central interval for a Gamma distribution will always contain at least 97.5 percent of that distribution.

For more details : Properties of Probability Models, Part 2

$\endgroup$

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.