MNLogit.score_obs()

statsmodels.discrete.discrete_model.MNLogit.score_obs

MNLogit.score_obs(params) [source]

Jacobian matrix for multinomial logit model log-likelihood

Parameters:

Parameters:	params : array The parameters of the multinomial logit model.
Returns:	jac : ndarray, (nobs, k_vars*(J-1)) The derivative of the loglikelihood for each observation evaluated at `params` .

params : array

The parameters of the multinomial logit model.

Returns:

jac : ndarray, (nobs, k_vars*(J-1))

The derivative of the loglikelihood for each observation evaluated at params .

Notes

$\frac{\partial\ln L_{i}}{\partial\beta_{j}}=\left(d_{ij}-\frac{\exp\left(\beta_{j}^{\prime}x_{i}\right)}{\sum_{k=0}^{J}\exp\left(\beta_{k}^{\prime}x_{i}\right)}\right)x_{i}$

for $j=1,...,J$ , for observations $i=1,...,n$

In the multinomial model the score vector is K x (J-1) but is returned as a flattened array. The Jacobian has the observations in rows and the flatteded array of derivatives in columns.

Links:

http://statsmodels.sourceforge.net/stable/generated/statsmodels.discrete.discrete_model.MNLogit.score_obs.html

doc_statsmodels

2017-01-18 16:12:23

Comments