statsmodels.genmod.families.links.Logit.inverse_deriv Logit.inverse_deriv(z) [source] Derivative of the inverse of the logit transform Parameters: z : array-like z is usually the linear predictor for a GLM or GEE model. Returns: The value of the derivative of the inverse of the logit function :

statsmodels.robust.norms.TukeyBiweight.psi_deriv TukeyBiweight.psi_deriv(z) [source] The derivative of Tukey?s biweight psi function Notes Used to estimate the robust covariance matrix.

statsmodels.regression.mixed_linear_model.MixedLMResults.remove_data MixedLMResults.remove_data() remove data arrays, all nobs arrays from result and model This reduces the size of the instance, so it can be pickled with less memory. Currently tested for use with predict from an unpickled results and model instance. Warning Since data and some intermediate results have been removed calculating new statistics that require them will raise exceptions. The exception will occur the first time an

statsmodels.stats.weightstats.DescrStatsW.corrcoef static DescrStatsW.corrcoef() [source] weighted correlation with default ddof assumes variables in columns and observations in rows

statsmodels.duration.hazard_regression.PHReg.efron_gradient PHReg.efron_gradient(params) [source] Returns the gradient of the log partial likelihood evaluated at params, using the Efron method to handle tied times.

statsmodels.genmod.generalized_estimating_equations.GEEResults.save GEEResults.save(fname, remove_data=False) save a pickle of this instance Parameters: fname : string or filehandle fname can be a string to a file path or filename, or a filehandle. remove_data : bool If False (default), then the instance is pickled without changes. If True, then all arrays with length nobs are set to None before pickling. See the remove_data method. In some cases not all arrays will be set to None. Not

statsmodels.robust.scale.Huber class statsmodels.robust.scale.Huber(c=1.5, tol=1e-08, maxiter=30, norm=None) [source] Huber?s proposal 2 for estimating location and scale jointly. Parameters: c : float, optional Threshold used in threshold for chi=psi**2. Default value is 1.5. tol : float, optional Tolerance for convergence. Default value is 1e-08. maxiter : int, optional0 Maximum number of iterations. Default value is 30. norm : statsmodels.robust.norms.RobustNorm, optional A robust

statsmodels.discrete.discrete_model.NegativeBinomialResults.remove_data NegativeBinomialResults.remove_data() remove data arrays, all nobs arrays from result and model This reduces the size of the instance, so it can be pickled with less memory. Currently tested for use with predict from an unpickled results and model instance. Warning Since data and some intermediate results have been removed calculating new statistics that require them will raise exceptions. The exception will occur the f

statsmodels.stats.outliers_influence.OLSInfluence.hat_diag_factor static OLSInfluence.hat_diag_factor() [source] (cached attribute) factor of diagonal of hat_matrix used in influence this might be useful for internal reuse h / (1 - h)

statsmodels.regression.quantile_regression.QuantReg.information QuantReg.information(params) Fisher information matrix of model Returns -Hessian of loglike evaluated at params.