statsmodels.discrete.discrete_model.Poisson.score_obs

Poisson.score_obs(params)

Poisson model Jacobian of the log-likelihood for each observation

Parameters:params (array-like) – The parameters of the model Returns:score – The score vector (nobs, k_vars) of the model evaluated at params Return type:array-like

Notes

$$\frac{\partial\ln L_{i}}{\partial\beta}=\left(y_{i}-\lambda_{i}\right)x_{i}$$

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

where the loglinear model is assumed

$$\ln\lambda_{i}=x_{i}\beta$$