statsmodels.genmod.families.family.Family.loglike¶

Family.
loglike
(endog, mu, var_weights=1.0, freq_weights=1.0, scale=1.0)[source]¶ The loglikelihood function in terms of the fitted mean response.
Parameters:  endog (array) – Usually the endogenous response variable.
 mu (array) – Usually but not always the fitted mean response variable.
 var_weights (arraylike) – 1d array of variance (analytic) weights. The default is 1.
 freq_weights (arraylike) – 1d array of frequency weights. The default is 1.
 scale (float) – The scale parameter. The default is 1.
Returns: ll – The value of the loglikelihood evaluated at (endog, mu, var_weights, freq_weights, scale) as defined below.
Return type: Notes
Where \(ll_i\) is the byobservation loglikelihood:
\[ll = \sum(ll_i * freq\_weights_i)\]ll_i
is defined for each family. endog and mu are not restricted toendog
andmu
respectively. For instance, you could call bothloglike(endog, endog)
andloglike(endog, mu)
to get the loglikelihood ratio.