statsmodels.genmod.families.family.Poisson

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

Poisson exponential family.

Parameters:

link : a link instance, optional

The default link for the Poisson family is the log link. Available links are log, identity, and sqrt. See statsmodels.family.links for more information.

See also

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

Attributes

Poisson.link (a link instance) The link function of the Poisson instance.
Poisson.variance (varfuncs instance) variance is an instance of statsmodels.genmod.families.family.varfuncs.mu

Methods

deviance(endog, mu[, freq_weights, scale]) Poisson deviance function
fitted(lin_pred) Fitted values based on linear predictors lin_pred.
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) Anscombe residuals for the Poisson exponential family distribution
resid_dev(endog, mu[, scale]) Poisson deviance residual
starting_mu(y) Starting value for mu in the IRLS algorithm.
variance
weights(mu) Weights for IRLS steps

Methods

deviance(endog, mu[, freq_weights, scale]) Poisson deviance function
fitted(lin_pred) Fitted values based on linear predictors lin_pred.
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) Anscombe residuals for the Poisson exponential family distribution
resid_dev(endog, mu[, scale]) Poisson deviance residual
starting_mu(y) Starting value for mu in the IRLS algorithm.
weights(mu) Weights for IRLS steps