Binomial

class superglm.Binomial

Bases: object

Binomial (Bernoulli) distribution. V(mu) = mu * (1 - mu).

For use with binary y in {0, 1}. This is a Bernoulli GLM (n_trials=1); sample_weight is case/frequency weight, not binomial trials.

variance(

mu: NDArray,

) → NDArray

V(μ) = μ(1 − μ).

variance_derivative(

mu: NDArray,

) → NDArray

V’(μ) = 1 − 2μ.

variance_second_derivative(

mu: NDArray,

) → NDArray

V’’(μ) = -2. Wood (2011) Appendix D.

deviance_unit(

y: NDArray,

mu: NDArray,

) → NDArray

Bernoulli unit deviance: 2[y log(y/μ) + (1-y) log((1-y)/(1-μ))].

log_likelihood(

y: NDArray,

mu: NDArray,

weights: NDArray,

phi: float = 1.0,

) → float

Bernoulli log-likelihood.