I’m running into what I think might be a bug with PyMC3’s Binomial likelihood. Here’s the example. Simulate data itrs = 100 p = 0.4 W = [] L = [] N = [] for i in range(itrs): n = int(np.random.normal(loc=100, scale=20)) wins = np.random.binomial(n=n,p=p) losses = n - wins N.append(n) …

I am not sure where did I make a typo. A beta-binomial distribution or model refers to this kind of model where each observation is modelled with a binomial likelihood whose p parameter is in turn given a unique beta prior that has shared alpha/beta hyper priors. This: with pm.Model() as m1: alp…

Beta-Binomial conjugate prior -- pm.Binomial buggy results...?

Questions

jbuddy_13 November 3, 2021, 9:39pm 8

So, your code used pm.Binomial() not pm.BetaBinomial(). I ran it as listed and it worked perfectly! Was this just a typo on this comment?

Topic		Replies	Views
Beta Binomial distribution Questions	1	700	August 26, 2018
Beta Regression in pyMC3 Questions	7	5589	September 18, 2017
Parameter Learning in Simple Bayesian Network Questions	5	2828	April 2, 2018
Beta-Binomial vs Binomial likelihood with Beta prior? Questions	1	712	January 29, 2021
Struggling with Beta mixture models Questions	3	1874	February 2, 2019

Beta-Binomial conjugate prior -- pm.Binomial buggy results...?

Related topics