def test_results_access(data):
mod = PooledOLS(data.y, data.x)
res = mod.fit(debiased=False)
d = dir(res)
for key in d:
if not key.startswith('_'):
val = getattr(res, key)
if callable(val):
val()
mod = PooledOLS(data.y, data.x)
res = mod.fit(debiased=True)
d = dir(res)
for key in d:
if not key.startswith('_'):
val = getattr(res, key)
if callable(val):
val()
if not isinstance(data.x, pd.Panel):
return
x = data.y.copy()
x.iloc[:, :] = 1
mod = PooledOLS(data.y, x)
res = mod.fit(debiased=False)
d = dir(res)
for key in d:
if not key.startswith('_'):
val = getattr(res, key)
if callable(val):
val()
def test_alt_cov(data, cov_type):
mod = PooledOLS(data.y, data.x)
res = mod.fit(cov_type=cov_type)
res_def = mod.fit()
assert not np.all(np.isclose(res.cov, res_def.cov))
if cov_type.startswith("a"):
cov_name = "Autocorrelation Rob. Cov."
else:
cov_name = "Driscoll-Kraay"
assert cov_name in str(res.summary)
def test_cov_equiv(data):
mod = PooledOLS(data.y, data.x)
res = mod.fit(cov_type='robust', debiased=False)
y = mod.dependent.dataframe.copy()
x = mod.exog.dataframe.copy()
y.index = np.arange(len(y))
x.index = y.index
res2 = IV2SLS(y, x, None, None).fit(cov_type='robust')
assert_results_equal(res, res2)
res3 = mod.fit(cov_type='heteroskedastic', debiased=False)
assert_results_equal(res, res3)
def test_pooled_ols(data):
mod = PooledOLS(data.y, data.x)
res = mod.fit(debiased=False)
y = mod.dependent.dataframe.copy()
x = mod.exog.dataframe.copy()
y.index = np.arange(len(y))
x.index = y.index
res2 = IV2SLS(y, x, None, None).fit(cov_type="unadjusted")
assert_results_equal(res, res2)
res3 = mod.fit(cov_type="homoskedastic", debiased=False)
assert_results_equal(res, res3)
def test_cov_equiv_weighted(data):
mod = PooledOLS(data.y, data.x, weights=data.w)
res = mod.fit(cov_type="robust", debiased=False)
y = mod.dependent.dataframe.copy()
x = mod.exog.dataframe.copy()
w = mod.weights.dataframe.copy()
y.index = np.arange(len(y))
w.index = x.index = y.index
res2 = IV2SLS(y, x, None, None, weights=w).fit(cov_type="robust")
assert_results_equal(res, res2)
res3 = mod.fit(cov_type="heteroskedastic", debiased=False)
assert_results_equal(res, res3)
def test_results_access(data):
mod = PooledOLS(data.y, data.x)
res = mod.fit(debiased=False)
access_attributes(res)
mod = PooledOLS(data.y, data.x)
res = mod.fit(debiased=True)
access_attributes(res)
if not isinstance(data.x, pd.DataFrame):
return
x = data.y.copy()
x.iloc[:, :] = 1
mod = PooledOLS(data.y, x)
res = mod.fit(debiased=False)
access_attributes(res)
def test_pooled_ols_weighted(data):
mod = PooledOLS(data.y, data.x, weights=data.w)
res = mod.fit(debiased=False)
y = mod.dependent.dataframe
x = mod.exog.dataframe
w = mod.weights.dataframe
y.index = np.arange(len(y))
w.index = x.index = y.index
res2 = IV2SLS(y, x, None, None, weights=w).fit(cov_type='unadjusted')
assert_results_equal(res, res2)
def test_cov_equiv_cluster_weighted(data):
mod = PooledOLS(data.y, data.x, weights=data.w)
res = mod.fit(cov_type='clustered', clusters=data.vc1, debiased=False)
y = mod.dependent.dataframe.copy()
x = mod.exog.dataframe.copy()
w = mod.weights.dataframe
y.index = np.arange(len(y))
w.index = x.index = y.index
clusters = mod.reformat_clusters(data.vc1)
ols_mod = IV2SLS(y, x, None, None, weights=w)
res2 = ols_mod.fit(cov_type='clustered', clusters=clusters.dataframe)
assert_results_equal(res, res2)
def test_cov_equiv_cluster(data):
mod = PooledOLS(data.y, data.x)
res = mod.fit(cov_type='clustered', cluster_entity=True, debiased=False)
y = PanelData(data.y)
clusters = pd.DataFrame(y.entity_ids, index=y.index)
res2 = mod.fit(cov_type='clustered', clusters=clusters, debiased=False)
assert_results_equal(res, res2)
res = mod.fit(cov_type='clustered', cluster_time=True, debiased=False)
clusters = pd.DataFrame(y.time_ids, index=y.index)
res2 = mod.fit(cov_type='clustered', clusters=clusters, debiased=False)
assert_results_equal(res, res2)
res = mod.fit(cov_type='clustered', clusters=data.vc1, debiased=False)
y = mod.dependent.dataframe.copy()
x = mod.exog.dataframe.copy()
y.index = np.arange(len(y))
x.index = y.index
clusters = mod.reformat_clusters(data.vc1)
ols_mod = IV2SLS(y, x, None, None)
res2 = ols_mod.fit(cov_type='clustered', clusters=clusters.dataframe, debiased=False)
assert_results_equal(res, res2)
def test_f_pooled(data):
mod = PanelOLS(data.y, data.x, entity_effects=True)
res = mod.fit(debiased=False)
if mod.has_constant:
mod2 = PooledOLS(data.y, data.x)
else:
exog = mod.exog.dataframe.copy()
exog['Intercept'] = 1.0
mod2 = PooledOLS(mod.dependent.dataframe, exog)
res2 = mod2.fit(debiased=False)
eps = res.resids.values
eps2 = res2.resids.values
v1 = res.df_model - res2.df_model
v2 = res.df_resid
f_pool = (eps2.T @ eps2 - eps.T @ eps) / v1
f_pool /= ((eps.T @ eps) / v2)
f_pool = float(f_pool)
assert_allclose(res.f_pooled.stat, f_pool)
assert res.f_pooled.df == v1
assert res.f_pooled.df_denom == v2
mod = PanelOLS(data.y, data.x, time_effects=True)
res = mod.fit(debiased=False)
eps = res.resids.values
eps2 = res2.resids.values
v1 = res.df_model - res2.df_model
v2 = res.df_resid
f_pool = (eps2.T @ eps2 - eps.T @ eps) / v1
f_pool /= ((eps.T @ eps) / v2)
f_pool = float(f_pool)
assert_allclose(res.f_pooled.stat, f_pool)
assert res.f_pooled.df == v1
assert res.f_pooled.df_denom == v2
mod = PanelOLS(data.y, data.x, entity_effects=True, time_effects=True)
res = mod.fit(debiased=False)
eps = res.resids.values
eps2 = res2.resids.values
v1 = res.df_model - res2.df_model
v2 = res.df_resid
f_pool = (eps2.T @ eps2 - eps.T @ eps) / v1
f_pool /= ((eps.T @ eps) / v2)
f_pool = float(f_pool)
assert_allclose(res.f_pooled.stat, f_pool)
assert res.f_pooled.df == v1
assert res.f_pooled.df_denom == v2
def test_fitted_effects_residuals(data):
mod = PooledOLS(data.y, data.x)
res = mod.fit()
expected = pd.DataFrame(res.resids.copy())
expected.columns = ['idiosyncratic']
assert_allclose(res.idiosyncratic, expected)
assert_frame_similar(res.idiosyncratic, expected)
expected = mod.dependent.values2d - res.resids.values[:, None]
expected = pd.DataFrame(expected, index=res.resids.index, columns=['fitted_values'])
assert_allclose(res.fitted_values, expected)
assert_frame_similar(res.fitted_values, expected)
expected.iloc[:, 0] = np.nan
expected.columns = ['estimated_effects']
assert_allclose(res.estimated_effects, expected)
assert_frame_similar(res.estimated_effects, expected)
def test_two_way_clustering(data):
mod = PooledOLS(data.y, data.x)
y = PanelData(data.y)
entity_clusters = pd.DataFrame(y.entity_ids, index=y.index)
vc1 = PanelData(data.vc1)
clusters = vc1.copy()
clusters.dataframe['var.cluster.entity'] = entity_clusters
clusters._frame = clusters._frame.astype(np.int64)
res = mod.fit(cov_type='clustered', clusters=clusters, debiased=False)
y = mod.dependent.dataframe.copy()
x = mod.exog.dataframe.copy()
y.index = np.arange(len(y))
x.index = y.index
clusters = mod.reformat_clusters(clusters)
ols_mod = IV2SLS(y, x, None, None)
ols_res = ols_mod.fit(cov_type='clustered', clusters=clusters.dataframe)
assert_results_equal(res, ols_res)
def test_alt_rsquared_weighted(data):
mod = PooledOLS(data.y, data.x, weights=data.w)
res = mod.fit(debiased=False)
assert_allclose(res.rsquared, res.rsquared_overall)
def test_extra_df(data):
mod = PooledOLS(data.y, data.x)
res = mod.fit()
res_extra = mod.fit(extra_df=10)
assert np.all(np.diag(res_extra.cov) > np.diag(res.cov))
