Hello, I am working on converting the Fader & Hardie shifted Beta-Geometric model into PyMC3 and have run into a hitch. I’m using the data in the appendix to and then attempting to write the custom likelihood function. I’ve seen a post where this was done having the probability recursively define…

[image] luerkene: ln_prob_vec[i - 1] = beta_func(alpha + 1, beta + i - 1)/beta_func(alpha, beta) Anyway, your error is this line. You cannot assign symbolic values (the output of your beta_func call) to a numpy array as you are doing. You might be able to create a python list and then convert…

How to implement Beta Function effectively in Pymc3

Questions

luerkene June 22, 2021, 6:33pm 5

Oh thank you! I’ll incorporate betaln!

Topic		Replies	Views
Defining a numeric (custom) likelihood function in PyMC3 Questions theano	2	3070	August 25, 2018
AssertionError with logcdf method for a Beta Questions theano	10	1173	May 1, 2019
Beta Regression in pyMC3 Questions	7	5589	September 18, 2017
How to implement a GLM with a personalized link function different from the Identity function? Questions	7	1877	June 7, 2021
Shifted Beta Geometric (sBG) distribution in pymc3 Questions	9	3247	June 23, 2021

How to implement Beta Function effectively in Pymc3

Related topics