scikits.statsmodels.discretemod.MNLogit

class scikits.statsmodels.discretemod.MNLogit(endog, exog=None)

Multinomial logit model

Parameters:

endog : array-like

endog is an 1-d vector of the endogenous response. endog can contain strings, ints, or floats. Note that if it contains strings, every distinct string will be a category. No stripping of whitespace is done.

exog : array-like

exog is an n x p array where n is the number of observations and p is the number of regressors including the intercept if one is included in the data.

Notes

See developer notes for further information on MNLogit internals.

Attributes

Methods

cdf(eXB) Multinomial logit cumulative distribution function.
fit([start_params, maxiter, method, tol]) Fits the multinomial logit model.
hessian(params) Multinomial logit Hessian matrix of the log-likelihood
information(params) Fisher information matrix of model
initialize() Preprocesses the data for MNLogit.
loglike(params) Log-likelihood of the multinomial logit model.
pdf(eXB) NotImplemented
predict(design) After a model has been fit predict returns the fitted values.
score(params) Score matrix for multinomial logit model log-likelihood

Previous topic

scikits.statsmodels.discretemod.Probit.score

Next topic

scikits.statsmodels.discretemod.MNLogit.cdf

This Page