statsmodels.stats.proportion.multinomial_proportions_confint fails with method="sison-glaz" for degenerate data. Goodman still gives a result. When method == 'sison-glaz', if for some reason c cannot ...

q0 = 1-p0 q1 = 1-p1 ps = [q0*q1, q0*p1, p0*q1, p0*p1] k00 = N - num_seen data = pm.math.stack((k00, k01, k10, k11)) y = pm.Multinomial('y', n=N, p=ps, observed=data ...