statsmodels.genmod.families.family.Binomial

class statsmodels.genmod.families.family.Binomial(link=<class 'statsmodels.genmod.families.links.logit'>)[source]

Binomial exponential family distribution.

Parameters:

link : a link instance, optional

The default link for the Binomial family is the logit link. Available links are logit, probit, cauchy, log, and cloglog. See statsmodels.family.links for more information.

See also

statsmodels.genmod.families.family.Family, Link Functions

Notes

endog for Binomial can be specified in one of three ways.

Attributes

Binomial.link (a link instance) The link function of the Binomial instance
Binomial.variance (varfunc instance) variance is an instance of statsmodels.family.varfuncs.binary

Methods

deviance(endog, mu[, freq_weights, scale]) Deviance function for either Bernoulli or Binomial data.
fitted(lin_pred) Fitted values based on linear predictors lin_pred.
initialize(endog, freq_weights) Initialize the response variable.
loglike(endog, mu[, freq_weights, scale]) The log-likelihood function in terms of the fitted mean response.
predict(mu) Linear predictors based on given mu values.
resid_anscombe(endog, mu) The Anscombe residuals
resid_dev(endog, mu[, scale]) Binomial deviance residuals
starting_mu(y) The starting values for the IRLS algorithm for the Binomial family.
variance
weights(mu) Weights for IRLS steps

Methods

deviance(endog, mu[, freq_weights, scale]) Deviance function for either Bernoulli or Binomial data.
fitted(lin_pred) Fitted values based on linear predictors lin_pred.
initialize(endog, freq_weights) Initialize the response variable.
loglike(endog, mu[, freq_weights, scale]) The log-likelihood function in terms of the fitted mean response.
predict(mu) Linear predictors based on given mu values.
resid_anscombe(endog, mu) The Anscombe residuals
resid_dev(endog, mu[, scale]) Binomial deviance residuals
starting_mu(y) The starting values for the IRLS algorithm for the Binomial family.
weights(mu) Weights for IRLS steps