def test_glm(self): # prelimnimary, getting started with basic test for GLM.get_prediction from statsmodels.genmod.generalized_linear_model import GLM res_wls = self.res_wls mod_wls = res_wls.model y, X, wi = mod_wls.endog, mod_wls.exog, mod_wls.weights w_sqrt = np.sqrt(wi) # notation wi is weights, `w` is var mod_glm = GLM(y * w_sqrt, X * w_sqrt[:,None]) # compare using t distribution res_glm = mod_glm.fit(use_t=True) pred_glm = res_glm.get_prediction() sf_glm = pred_glm.summary_frame() pred_res_wls = res_wls.get_prediction() sf_wls = pred_res_wls.summary_frame() n_compare = 30 # in glm with predict wendog assert_allclose(sf_glm.values[:n_compare], sf_wls.values[:n_compare, :4]) # compare using normal distribution res_glm = mod_glm.fit() # default use_t=False pred_glm = res_glm.get_prediction() sf_glm = pred_glm.summary_frame() res_wls = mod_wls.fit(use_t=False) pred_res_wls = res_wls.get_prediction() sf_wls = pred_res_wls.summary_frame() assert_allclose(sf_glm.values[:n_compare], sf_wls.values[:n_compare, :4]) # function for parameter transformation # should be separate test method from statsmodels.genmod._prediction import params_transform_univariate rates = params_transform_univariate(res_glm.params, res_glm.cov_params()) rates2 = np.column_stack((np.exp(res_glm.params), res_glm.bse * np.exp(res_glm.params), np.exp(res_glm.conf_int()))) assert_allclose(rates.summary_frame().values, rates2, rtol=1e-13) from statsmodels.genmod.families import links # with identity transform pt = params_transform_univariate(res_glm.params, res_glm.cov_params(), link=links.identity()) assert_allclose(pt.tvalues, res_glm.tvalues, rtol=1e-13) assert_allclose(pt.se_mean, res_glm.bse, rtol=1e-13) ptt = pt.t_test() assert_allclose(ptt[0], res_glm.tvalues, rtol=1e-13) assert_allclose(ptt[1], res_glm.pvalues, rtol=1e-13) # prediction with exog and no weights does not error res_glm = mod_glm.fit() pred_glm = res_glm.get_prediction(X)
def test_glm(self): # prelimnimary, getting started with basic test for GLM.get_prediction from statsmodels.genmod.generalized_linear_model import GLM res_wls = self.res_wls mod_wls = res_wls.model y, X, wi = mod_wls.endog, mod_wls.exog, mod_wls.weights w_sqrt = np.sqrt(wi) # notation wi is weights, `w` is var mod_glm = GLM(y * w_sqrt, X * w_sqrt[:, None]) # compare using t distribution res_glm = mod_glm.fit(use_t=True) pred_glm = res_glm.get_prediction() sf_glm = pred_glm.summary_frame() pred_res_wls = res_wls.get_prediction() sf_wls = pred_res_wls.summary_frame() n_compare = 30 # in glm with predict wendog assert_allclose(sf_glm.values[:n_compare], sf_wls.values[:n_compare, :4]) # compare using normal distribution res_glm = mod_glm.fit() # default use_t=False pred_glm = res_glm.get_prediction() sf_glm = pred_glm.summary_frame() res_wls = mod_wls.fit(use_t=False) pred_res_wls = res_wls.get_prediction() sf_wls = pred_res_wls.summary_frame() assert_allclose(sf_glm.values[:n_compare], sf_wls.values[:n_compare, :4]) # function for parameter transformation # should be separate test method from statsmodels.genmod._prediction import params_transform_univariate rates = params_transform_univariate(res_glm.params, res_glm.cov_params()) rates2 = np.column_stack( (np.exp(res_glm.params), res_glm.bse * np.exp(res_glm.params), np.exp(res_glm.conf_int()))) assert_allclose(rates.summary_frame().values, rates2, rtol=1e-13) from statsmodels.genmod.families import links # with identity transform pt = params_transform_univariate(res_glm.params, res_glm.cov_params(), link=links.identity()) assert_allclose(pt.tvalues, res_glm.tvalues, rtol=1e-13) assert_allclose(pt.se_mean, res_glm.bse, rtol=1e-13) ptt = pt.t_test() assert_allclose(ptt[0], res_glm.tvalues, rtol=1e-13) assert_allclose(ptt[1], res_glm.pvalues, rtol=1e-13)
pred_wls_n = res_wls_n.get_prediction() print(pred_wls_n.summary_frame().head()) from statsmodels.genmod.generalized_linear_model import GLM w_sqrt = np.sqrt(w) mod_glm = GLM(y / w_sqrt, X / w_sqrt[:, None]) res_glm = mod_glm.fit() pred_glm = res_glm.get_prediction() print(pred_glm.summary_frame().head()) res_glm_t = mod_glm.fit(use_t=True) pred_glm_t = res_glm_t.get_prediction() print(pred_glm_t.summary_frame().head()) rates = params_transform_univariate(res_glm.params, res_glm.cov_params()) print('\nRates exp(params)') print(rates.summary_frame()) rates2 = np.column_stack( (np.exp(res_glm.params), res_glm.bse * np.exp(res_glm.params), np.exp(res_glm.conf_int()))) assert_allclose(rates.summary_frame().values, rates2, rtol=1e-13) from statsmodels.genmod.families import links # with identity transform pt = params_transform_univariate(res_glm.params, res_glm.cov_params(), link=links.identity()) print(pt.tvalues)
pred_wls_n = res_wls_n.get_prediction() print(pred_wls_n.summary_frame().head()) from statsmodels.genmod.generalized_linear_model import GLM w_sqrt = np.sqrt(w) mod_glm = GLM(y/w_sqrt, X/w_sqrt[:,None]) res_glm = mod_glm.fit() pred_glm = res_glm.get_prediction() print(pred_glm.summary_frame().head()) res_glm_t = mod_glm.fit(use_t=True) pred_glm_t = res_glm_t.get_prediction() print(pred_glm_t.summary_frame().head()) rates = params_transform_univariate(res_glm.params, res_glm.cov_params()) print('\nRates exp(params)') print(rates.summary_frame()) rates2 = np.column_stack((np.exp(res_glm.params), res_glm.bse * np.exp(res_glm.params), np.exp(res_glm.conf_int()))) assert_allclose(rates.summary_frame().values, rates2, rtol=1e-13) from statsmodels.genmod.families import links # with identity transform pt = params_transform_univariate(res_glm.params, res_glm.cov_params(), link=links.identity()) print(pt.tvalues) assert_allclose(pt.tvalues, res_glm.tvalues, rtol=1e-13)