DiffMeansPermute Limitations

[gmrwvu]

I would like to clarify any distribution limitations for your DiffMeansPermute hypothesis class. This class computes its own distribution of the test statistic for two groups. So, the two groups can have a uniform, exponential, normal, or Pareto distribution and the resultant p-value would still indicate significance in the difference between the means. Am I understanding this correctly?

[AllenDowney]

Yes, permutation tests do not make any distribution assumptions.

…

On Wed, Mar 21, 2018 at 10:41 AM, George Ray ***@***.***> wrote: I would like to clarify any distribution limitations for your DiffMeansPermute hypothesis class. This class computes its own distribution of the test statistic for two groups. So, the two groups can have a uniform, exponential, normal, or Pareto distribution and the resultant p-value would still indicate significance in the difference between the means. Am I understanding this correctly? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#102>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ABy37SyVpA9XmJideyIaJBdC8ZbLyQsuks5tgmaBgaJpZM4S0JC0> .

[gmrwvu]

Thank you.