def test_panel_other_lsdv(data): mod = PanelOLS(data.y, data.x, other_effects=data.c) res = mod.fit(auto_df=False, count_effects=False, debiased=False) y = mod.dependent.dataframe.copy() x = mod.exog.dataframe.copy() c = mod._other_effect_cats.dataframe.copy() d = [] d_columns = [] for i, col in enumerate(c): s = c[col].copy() dummies = pd.get_dummies(s.astype(np.int64), drop_first=(mod.has_constant or i > 0)) dummies.columns = [s.name + '_val_' + str(c) for c in dummies.columns] d_columns.extend(list(dummies.columns)) d.append(dummies.values) d = np.column_stack(d) if mod.has_constant: z = np.ones_like(y) d = d - z @ np.linalg.lstsq(z, d)[0] xd = np.c_[x.values, d] xd = pd.DataFrame(xd, index=x.index, columns=list(x.columns) + list(d_columns)) ols_mod = IV2SLS(y, xd, None, None) res2 = ols_mod.fit('unadjusted') assert_results_equal(res, res2, test_fit=False) res3 = mod.fit(cov_type='unadjusted', auto_df=False, count_effects=False, debiased=False) assert_results_equal(res, res3) res = mod.fit(cov_type='robust', auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit('robust') assert_results_equal(res, res2, test_fit=False) clusters = data.vc1 ols_clusters = mod.reformat_clusters(clusters) res = mod.fit(cov_type='clustered', clusters=clusters, auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit('clustered', clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) clusters = data.vc2 ols_clusters = mod.reformat_clusters(clusters) res = mod.fit(cov_type='clustered', clusters=clusters, auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit('clustered', clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) res = mod.fit(cov_type='clustered', cluster_time=True, auto_df=False, count_effects=False, debiased=False) clusters = pd.DataFrame(mod.dependent.time_ids, index=mod.dependent.index, columns=['var.clust']) res2 = ols_mod.fit('clustered', clusters=clusters) assert_results_equal(res, res2, test_fit=False) res = mod.fit(cov_type='clustered', cluster_entity=True, auto_df=False, count_effects=False, debiased=False) clusters = pd.DataFrame(mod.dependent.entity_ids, index=mod.dependent.index, columns=['var.clust']) res2 = ols_mod.fit('clustered', clusters=clusters) assert_results_equal(res, res2, test_fit=False)
def test_panel_entity_lsdv_weighted(data): mod = PanelOLS(data.y, data.x, entity_effects=True, weights=data.w) res = mod.fit(auto_df=False, count_effects=False, debiased=False) y = mod.dependent.dataframe x = mod.exog.dataframe w = mod.weights.dataframe d = mod.dependent.dummies('entity', drop_first=mod.has_constant) d_cols = d.columns d = d.values if mod.has_constant: z = np.ones_like(y) root_w = np.sqrt(w.values) wd = root_w * d wz = root_w * z d = d - z @ lstsq(wz, wd)[0] xd = np.c_[x.values, d] xd = pd.DataFrame(xd, index=x.index, columns=list(x.columns) + list(d_cols)) ols_mod = IV2SLS(y, xd, None, None, weights=w) res2 = ols_mod.fit(cov_type='unadjusted') assert_results_equal(res, res2, test_fit=False) assert_allclose(res.rsquared_inclusive, res2.rsquared) res = mod.fit(cov_type='robust', auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit(cov_type='robust') assert_results_equal(res, res2, test_fit=False) clusters = data.vc1 ols_clusters = mod.reformat_clusters(clusters) res = mod.fit(cov_type='clustered', clusters=clusters, auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit(cov_type='clustered', clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) clusters = data.vc2 ols_clusters = mod.reformat_clusters(clusters) res = mod.fit(cov_type='clustered', clusters=clusters, auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit(cov_type='clustered', clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) res = mod.fit(cov_type='clustered', cluster_time=True, auto_df=False, count_effects=False, debiased=False) clusters = pd.DataFrame(mod.dependent.time_ids, index=mod.dependent.index, columns=['var.clust']) res2 = ols_mod.fit(cov_type='clustered', clusters=clusters) assert_results_equal(res, res2, test_fit=False) res = mod.fit(cov_type='clustered', cluster_entity=True, auto_df=False, count_effects=False, debiased=False) clusters = pd.DataFrame(mod.dependent.entity_ids, index=mod.dependent.index, columns=['var.clust']) res2 = ols_mod.fit(cov_type='clustered', clusters=clusters) assert_results_equal(res, res2, test_fit=False)
def test_panel_both_lsdv(data): mod = PanelOLS(data.y, data.x, entity_effects=True, time_effects=True) res = mod.fit(auto_df=False, count_effects=False, debiased=False) y = mod.dependent.dataframe x = mod.exog.dataframe d1 = mod.dependent.dummies('entity', drop_first=mod.has_constant) d2 = mod.dependent.dummies('time', drop_first=True) d = np.c_[d1.values, d2.values] if mod.has_constant: z = np.ones_like(y) d = d - z @ lstsq(z, d)[0] xd = np.c_[x.values, d] xd = pd.DataFrame(xd, index=x.index, columns=list(x.columns) + list(d1.columns) + list(d2.columns)) ols_mod = IV2SLS(y, xd, None, None) res2 = ols_mod.fit(cov_type='unadjusted') assert_results_equal(res, res2, test_fit=False) assert_allclose(res.rsquared_inclusive, res2.rsquared) res = mod.fit(cov_type='robust', auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit(cov_type='robust') assert_results_equal(res, res2, test_fit=False) clusters = data.vc1 ols_clusters = mod.reformat_clusters(clusters) res = mod.fit(cov_type='clustered', clusters=clusters, auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit(cov_type='clustered', clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) clusters = data.vc2 ols_clusters = mod.reformat_clusters(clusters) res = mod.fit(cov_type='clustered', clusters=clusters, auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit(cov_type='clustered', clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) res = mod.fit(cov_type='clustered', cluster_time=True, auto_df=False, count_effects=False, debiased=False) clusters = pd.DataFrame(mod.dependent.time_ids, index=mod.dependent.index, columns=['var.clust']) res2 = ols_mod.fit(cov_type='clustered', clusters=clusters) assert_results_equal(res, res2, test_fit=False) res = mod.fit(cov_type='clustered', cluster_entity=True, auto_df=False, count_effects=False, debiased=False) clusters = pd.DataFrame(mod.dependent.entity_ids, index=mod.dependent.index, columns=['var.clust']) res2 = ols_mod.fit(cov_type='clustered', clusters=clusters) assert_results_equal(res, res2, test_fit=False)
def test_panel_time_lsdv_weighted(large_data): mod = PanelOLS(large_data.y, large_data.x, time_effects=True, weights=large_data.w) res = mod.fit(auto_df=False, count_effects=False, debiased=False) y = mod.dependent.dataframe x = mod.exog.dataframe w = mod.weights.dataframe d = mod.dependent.dummies("time", drop_first=mod.has_constant) d_cols = d.columns d = d.values if mod.has_constant: z = np.ones_like(y) root_w = np.sqrt(w.values) wd = root_w * d wz = root_w * z d = d - z @ lstsq(wz, wd, rcond=None)[0] xd = np.c_[x.values, d] xd = pd.DataFrame(xd, index=x.index, columns=list(x.columns) + list(d_cols)) ols_mod = IV2SLS(y, xd, None, None, weights=w) res2 = ols_mod.fit(cov_type="unadjusted") assert_results_equal(res, res2, test_fit=False) res = mod.fit(cov_type="robust", auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit(cov_type="robust") assert_results_equal(res, res2, test_fit=False) clusters = large_data.vc1 ols_clusters = mod.reformat_clusters(clusters) res = mod.fit( cov_type="clustered", clusters=clusters, auto_df=False, count_effects=False, debiased=False, ) res2 = ols_mod.fit(cov_type="clustered", clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) clusters = large_data.vc2 ols_clusters = mod.reformat_clusters(clusters) res = mod.fit( cov_type="clustered", clusters=clusters, auto_df=False, count_effects=False, debiased=False, ) res2 = ols_mod.fit(cov_type="clustered", clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) res = mod.fit( cov_type="clustered", cluster_time=True, auto_df=False, count_effects=False, debiased=False, ) clusters = pd.DataFrame(mod.dependent.time_ids, index=mod.dependent.index, columns=["var.clust"]) res2 = ols_mod.fit(cov_type="clustered", clusters=clusters) assert_results_equal(res, res2, test_fit=False) res = mod.fit( cov_type="clustered", cluster_entity=True, auto_df=False, count_effects=False, debiased=False, ) clusters = pd.DataFrame(mod.dependent.entity_ids, index=mod.dependent.index, columns=["var.clust"]) res2 = ols_mod.fit(cov_type="clustered", clusters=clusters) assert_results_equal(res, res2, test_fit=False)
def test_panel_entity_lsdv(data): mod = PanelOLS(data.y, data.x, entity_effects=True) res = mod.fit(auto_df=False, count_effects=False, debiased=False) y = mod.dependent.dataframe x = mod.exog.dataframe if mod.has_constant: d = mod.dependent.dummies("entity", drop_first=True) z = np.ones_like(y) d_demean = d.values - z @ lstsq(z, d.values, rcond=None)[0] else: d = mod.dependent.dummies("entity", drop_first=False) d_demean = d.values xd = np.c_[x.values, d_demean] xd = pd.DataFrame(xd, index=x.index, columns=list(x.columns) + list(d.columns)) ols_mod = IV2SLS(y, xd, None, None) res2 = ols_mod.fit(cov_type="unadjusted", debiased=False) assert_results_equal(res, res2, test_fit=False) assert_allclose(res.rsquared_inclusive, res2.rsquared) res = mod.fit(cov_type="robust", auto_df=False, count_effects=False, debiased=False) res2 = ols_mod.fit(cov_type="robust") assert_results_equal(res, res2, test_fit=False) clusters = data.vc1 ols_clusters = mod.reformat_clusters(data.vc1) res = mod.fit( cov_type="clustered", clusters=clusters, auto_df=False, count_effects=False, debiased=False, ) res2 = ols_mod.fit(cov_type="clustered", clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) clusters = data.vc2 ols_clusters = mod.reformat_clusters(data.vc2) res = mod.fit( cov_type="clustered", clusters=clusters, auto_df=False, count_effects=False, debiased=False, ) res2 = ols_mod.fit(cov_type="clustered", clusters=ols_clusters.dataframe) assert_results_equal(res, res2, test_fit=False) res = mod.fit( cov_type="clustered", cluster_time=True, auto_df=False, count_effects=False, debiased=False, ) clusters = pd.DataFrame(mod.dependent.time_ids, index=mod.dependent.index, columns=["var.clust"]) res2 = ols_mod.fit(cov_type="clustered", clusters=clusters) assert_results_equal(res, res2, test_fit=False) res = mod.fit( cov_type="clustered", cluster_entity=True, auto_df=False, count_effects=False, debiased=False, ) clusters = pd.DataFrame(mod.dependent.entity_ids, index=mod.dependent.index, columns=["var.clust"]) res2 = ols_mod.fit(cov_type="clustered", clusters=clusters) assert_results_equal(res, res2, test_fit=False)