def test_original_unmodified(data):
pre_y = data.y.copy()
pre_x = data.x.copy()
pre_w = data.w.copy()
mod = PanelOLS(data.y, data.x, weights=data.w)
mod.fit(debiased=True)
if isinstance(data.y, (DataFrame)):
for after, before in ((data.y, pre_y), (data.x, pre_x), (data.w,
pre_w)):
assert_frame_equal(before, after)
mi_df_y = PanelData(data.y).dataframe
mi_df_x = PanelData(data.x).dataframe
mi_df_y.index.names = ["firm", "period"]
mi_df_x.index.names = ["firm", "period"]
mi_df_w = PanelData(data.w).dataframe
pre_y = mi_df_y.copy()
pre_x = mi_df_x.copy()
pre_w = mi_df_w.copy()
mod = PanelOLS(mi_df_y, mi_df_x, weights=mi_df_w)
mod.fit(debiased=True)
assert_frame_equal(mi_df_w, pre_w)
assert_frame_equal(mi_df_y, pre_y)
assert_frame_equal(mi_df_x, pre_x)
elif isinstance(data.y, np.ndarray):
assert_allclose(data.y, pre_y)
assert_allclose(data.x, pre_x)
assert_allclose(data.w, pre_w)
else:
xr.testing.assert_identical(data.y, pre_y)
xr.testing.assert_identical(data.w, pre_w)
xr.testing.assert_identical(data.x, pre_x)
def const_data(request):
missing, datatype = request.param
data = generate_data(missing, datatype, ntk=(91, 7, 1))
y = PanelData(data.y).dataframe
x = y.copy()
x.iloc[:, :] = 1
x.columns = ['Const']
return AttrDict(y=y, x=x, w=PanelData(data.w).dataframe)
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)
ntk=(n, 3, 5),
other_effects=1,
const=False,
rng=rs)
mo, fo = options[key]
mod_type, cluster_type = key.split(':')
y = PanelData(data.y)
random_effects = np.random.randint(0,
n // 3,
size=y.dataframe.shape)
other_random = np.random.randint(0, n // 5, size=y.dataframe.shape)
if mod_type == 'random':
effects = y.copy()
effects.dataframe.iloc[:, :] = random_effects
mo['other_effects'] = effects
if cluster_type in ('random', 'other-random', 'entity-nested',
'random-nested'):
clusters = y.copy()
if cluster_type == 'random':
clusters.dataframe.iloc[:, :] = random_effects
elif cluster_type == 'other-random':
clusters.dataframe.iloc[:, :] = other_random
elif cluster_type == 'entity_nested':
eid = y.entity_ids
clusters.dataframe.iloc[:, :] = eid // 3
elif cluster_type == 'random-nested':
clusters.dataframe.iloc[:, :] = random_effects // 2
