[Numpy-discussion] power function distribution or power-law distribution?
robert.kern at gmail.com
Thu Aug 24 13:19:27 EDT 2017
On Thu, Aug 24, 2017 at 7:56 AM, Renato Fabbri <renato.fabbri at gmail.com>
> On Thu, Aug 24, 2017 at 11:47 AM, Nathan Goldbaum <nathan12343 at gmail.com>
>> The latest version of numpy is 1.13.
>> In this case, as described in the docs, a power function distribution is
one with a probability desnity function of the form ax^(a-1) for x between
0 and 1.
> ok, let's try ourselves to relate the terms.
> Would you agree that the "power function distribution" is a "power-law
> in which the domain is restricted to be [0,1]?
I probably wouldn't. The coincidental similarity in functional form (domain
and normalizing constants notwithstanding) obscures the very different
mechanisms each represent.
The ambiguous name of the method `power` instead of `power_function` is my
fault. You have my apologies.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the NumPy-Discussion