statsmodels.genmod.generalized_estimating_equations.GEEResults

class statsmodels.genmod.generalized_estimating_equations.GEEResults(model, params, cov_params, scale, cov_type='robust', use_t=False, **kwds)

This class summarizes the fit of a marginal regression model using GEE.

Returns:

• **Attributes**
• cov_params_default (ndarray) – default covariance of the parameter estimates. Is chosen among one of the following three based on cov_type
• cov_robust (ndarray) – covariance of the parameter estimates that is robust
• cov_naive (ndarray) – covariance of the parameter estimates that is not robust to correlation or variance misspecification
• cov_robust_bc (ndarray) – covariance of the parameter estimates that is robust and bias reduced
• converged (bool) – indicator for convergence of the optimization. True if the norm of the score is smaller than a threshold
• cov_type (string) – string indicating whether a “robust”, “naive” or “bias_reduced” covariance is used as default
• fit_history (dict) – Contains information about the iterations.
• fittedvalues (array) – Linear predicted values for the fitted model. dot(exog, params)
• model (class instance) – Pointer to GEE model instance that called fit.
• normalized_cov_params (array) – See GEE docstring
• params (array) – The coefficients of the fitted model. Note that interpretation of the coefficients often depends on the distribution family and the data.
• scale (float) – The estimate of the scale / dispersion for the model fit. See GEE.fit for more information.
• score_norm (float) – norm of the score at the end of the iterative estimation.
• bse (array) – The standard errors of the fitted GEE parameters.

Methods

bse()
centered_resid()	Returns the residuals centered within each group.
conf_int([alpha, cols, cov_type])	Returns confidence intervals for the fitted parameters.
cov_params([r_matrix, column, scale, cov_p, …])	Returns the variance/covariance matrix.
f_test(r_matrix[, cov_p, scale, invcov])	Compute the F-test for a joint linear hypothesis.
fittedvalues()	Returns the fitted values from the model.
get_margeff([at, method, atexog, dummy, count])	Get marginal effects of the fitted model.
initialize(model, params, **kwd)
llf()
load(fname)	load a pickle, (class method)
normalized_cov_params()
params_sensitivity(dep_params_first, …)	Refits the GEE model using a sequence of values for the dependence parameters.
plot_added_variable(focus_exog[, …])	Create an added variable plot for a fitted regression model.
plot_ceres_residuals(focus_exog[, frac, …])	Produces a CERES (Conditional Expectation Partial Residuals) plot for a fitted regression model.
plot_isotropic_dependence([ax, xpoints, min_n])	Create a plot of the pairwise products of within-group residuals against the corresponding time differences.
plot_partial_residuals(focus_exog[, ax])	Create a partial residual, or ‘component plus residual’ plot for a fited regression model.
predict([exog, transform])	Call self.model.predict with self.params as the first argument.
pvalues()
remove_data()	remove data arrays, all nobs arrays from result and model
resid()	Returns the residuals, the endogeneous data minus the fitted values from the model.
resid_anscombe()
resid_centered()	Returns the residuals centered within each group.
resid_centered_split()	Returns the residuals centered within each group.
resid_deviance()
resid_pearson()
resid_response()
resid_split()	Returns the residuals, the endogeneous data minus the fitted values from the model.
resid_working()
save(fname[, remove_data])	save a pickle of this instance
sensitivity_params(dep_params_first, …)	Refits the GEE model using a sequence of values for the dependence parameters.
split_centered_resid()	Returns the residuals centered within each group.
split_resid()	Returns the residuals, the endogeneous data minus the fitted values from the model.
standard_errors([cov_type])	This is a convenience function that returns the standard errors for any covariance type.
summary([yname, xname, title, alpha])	Summarize the GEE regression results
t_test(r_matrix[, cov_p, scale, use_t])	Compute a t-test for a each linear hypothesis of the form Rb = q
t_test_pairwise(term_name[, method, alpha, …])	perform pairwise t_test with multiple testing corrected p-values
tvalues()	Return the t-statistic for a given parameter estimate.
wald_test(r_matrix[, cov_p, scale, invcov, …])	Compute a Wald-test for a joint linear hypothesis.
wald_test_terms([skip_single, …])	Compute a sequence of Wald tests for terms over multiple columns

Attributes

use_t