Skip to content

Instantly share code, notes, and snippets.

@dadaromeo

dadaromeo/Conway-Maxwell-Poisson distribution.ipynb

Last active April 27, 2021 07:45
Show Gist options
  • Star 6 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save dadaromeo/33e581d9e3bcbad83531b4a91a87509f to your computer and use it in GitHub Desktop.
Save dadaromeo/33e581d9e3bcbad83531b4a91a87509f to your computer and use it in GitHub Desktop.
Download ZIP
Implementation of the Conway-Maxwell-Poisson distribution in pymc3
Display the source blob
Display the rendered blob
Raw
Conway-Maxwell-Poisson distribution.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@aloctavodia
Copy link

Hi! May be you would like to add this distribution to PyMC3! I interested about learning how this distribution compares with the negative binomial one (that is also used to model over-dispersed data). I was unable to open the first reference it seems that the correct link is www.galitshmueli.com/system/files/JRSS-COM-Poisson.pdf).

@jhurliman
Copy link

+1 to adding this to PyMC3

@giamp66
Copy link

giamp66 commented Jul 1, 2017

Hi, many thanks for the job done!
When i try to use it with nu less than 1 the code loop forever in the cycle "while any(u > cdf):"
You can try with "CMPoisson.dist(lamda= 1.24598558, nu=0.5681564).random(size=1000)"
I do not have the right mathematical background to solve the problem.
Do you have any guess or direction ?
Thanks a lot!
Regards.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment