generate_tweedie_cpg

superglm.generate_tweedie_cpg(

n: int,

mu,

phi,

p: float,

rng=None,

) → NDArray

Simulate Tweedie(mu, phi, p) as compound Poisson-gamma: N ~ Poisson, Y | N ~ Gamma.

rng is a numpy Generator, or any object whose poisson(lam) and gamma(shape, scale=...) return one draw per element as numpy’s do; the draws are checked, since fractional counts or one draw broadcast over every row would sample a different distribution.