objectif

Régression logistique avec p-valeurs/IC.

code minimal

import statsmodels.api as sm
import numpy as np

rng = np.random.default_rng(0)
X = rng.normal(size=(100,2))
y = (X[:,0] - X[:,1] > 0).astype(int)
Xc = sm.add_constant(X)
model = sm.Logit(y, Xc).fit(disp=False)
print(model.params.size == 3)

utilisation

print(hasattr(model, "bse"))

variante(s) utile(s)

import statsmodels.api as sm
glm = sm.GLM(y, Xc, family=sm.families.Binomial()).fit()
print(glm.deviance >= 0.0)

notes

• GLM offre d’autres familles (Poisson, Gamma…).