def test_panel_effects_sanity(data):
mod = PanelOLS(data.y, data.x, entity_effects=True)
res = mod.fit(auto_df=False, count_effects=False)
fitted = mod.exog.values2d @ res.params.values[:, None]
expected = fitted
expected += res.resids.values[:, None]
expected += res.estimated_effects.values
assert_allclose(mod.dependent.values2d, expected)
mod = PanelOLS(data.y, data.x, entity_effects=True, time_effects=True)
res = mod.fit(auto_df=False, count_effects=False)
fitted = mod.exog.values2d @ res.params.values[:, None]
expected = fitted
expected += res.resids.values[:, None]
expected += res.estimated_effects.values
assert_allclose(mod.dependent.values2d, expected)
mod = PanelOLS(data.y, data.x, weights=data.w, entity_effects=True)
res = mod.fit(auto_df=False, count_effects=False)
fitted = mod.exog.values2d @ res.params.values[:, None]
expected = fitted
expected += res.resids.values[:, None]
expected += res.estimated_effects.values
assert_allclose(mod.dependent.values2d, expected)
mod = PanelOLS(data.y,
data.x,
weights=data.w,
entity_effects=True,
time_effects=True)
res = mod.fit(auto_df=False, count_effects=False)
fitted = mod.exog.values2d @ res.params.values[:, None]
expected = fitted
expected += res.resids.values[:, None]
expected += res.estimated_effects.values
assert_allclose(mod.dependent.values2d, expected)
def test_cluster_smoke(data):
mod = PanelOLS(data.y, data.x, entity_effects=True)
mod.fit(cov_type="clustered", cluster_time=True, debiased=False)
mod.fit(cov_type="clustered", cluster_entity=True, debiased=False)
c2 = PanelData(data.vc2)
c1 = PanelData(data.vc1)
mod.fit(cov_type="clustered", clusters=c2, debiased=False)
mod.fit(cov_type="clustered",
cluster_entity=True,
clusters=c1,
debiased=False)
mod.fit(cov_type="clustered",
cluster_time=True,
clusters=c1,
debiased=False)
with pytest.raises(ValueError):
mod.fit(cov_type="clustered",
cluster_time=True,
clusters=c2,
debiased=False)
with pytest.raises(ValueError):
mod.fit(cov_type="clustered",
cluster_entity=True,
clusters=c2,
debiased=False)
with pytest.raises(ValueError):
mod.fit(
cov_type="clustered",
cluster_entity=True,
cluster_time=True,
clusters=c1,
debiased=False,
)
with pytest.raises(ValueError):
clusters = c1.dataframe.iloc[:c1.dataframe.shape[0] // 2]
mod.fit(cov_type="clustered", clusters=clusters, debiased=False)
def test_other_weighted_smoke(data):
mod = PanelOLS(data.y, data.x, weights=data.w, other_effects=data.c)
mod.fit(debiased=False)
def test_too_many_effects(data):
with pytest.raises(ValueError):
PanelOLS(data.y, data.x, entity_effect=True, time_effect=True, other_effects=data.c)
def test_alt_rsquared_weighted(data):
mod = PanelOLS(data.y, data.x, entity_effects=True, weights=data.w)
res = mod.fit(debiased=False)
assert_allclose(res.rsquared, res.rsquared_within)
def test_panel_no_effects(data):
res = PanelOLS(data.y, data.x).fit()
res2 = PooledOLS(data.y, data.x).fit()
assert_results_equal(res, res2)
def test_panel_time_lsdv(large_data):
mod = PanelOLS(large_data.y, large_data.x, time_effects=True)
res = mod.fit(auto_df=False, count_effects=False, debiased=False)
y = mod.dependent.dataframe
x = mod.exog.dataframe
d = mod.dependent.dummies("time", drop_first=mod.has_constant)
d_cols = list(d.columns)
d = d.values
if mod.has_constant:
z = np.ones_like(y)
d = d - z @ lstsq(z, d, rcond=None)[0]
xd = np.c_[x.values, d]
xd = pd.DataFrame(xd, index=x.index, columns=list(x.columns) + d_cols)
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 = 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_other_lsdv(data):
mod = PanelOLS(data.y, data.x, other_effects=data.c)
assert "Num Other Effects: 2" in str(mod)
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 @ lstsq(z, d, rcond=None)[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(cov_type="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(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_lsdv(data):
mod = PanelOLS(data.y, data.x, entity_effects=True)
y, x = mod.dependent.dataframe, mod.exog.dataframe
res = mod.fit()
expected = lsdv(y, x, has_const=False, entity=True)
assert_allclose(res.params.squeeze(), expected)
mod = PanelOLS(data.y, data.x, time_effects=True)
res = mod.fit()
expected = lsdv(y, x, has_const=False, time=True)
assert_allclose(res.params.squeeze(), expected)
mod = PanelOLS(data.y, data.x, entity_effects=True, time_effects=True)
res = mod.fit()
expected = lsdv(y, x, has_const=False, entity=True, time=True)
assert_allclose(res.params.squeeze(), expected, rtol=1e-4)
other = y.copy()
other.iloc[:, :] = 0
other = other.astype(np.int64)
skip = other.shape[0] // 3
for i in range(skip):
other.iloc[i::skip] = i
mod = PanelOLS(y, x, other_effects=other)
res = mod.fit()
expected = lsdv(y, x, has_const=False, general=other.iloc[:, 0].values)
assert_allclose(res.params.squeeze(), expected, rtol=1e-4)
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)[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_valid_weight_shape(data):
# Same size
n = np.prod(data.y.shape)
weights = 1 + np.random.random_sample(n)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
missing = PanelData(data.y).isnull | PanelData(data.x).isnull
expected = weights[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
# Per time
if isinstance(data.x, pd.DataFrame):
n = len(data.y.index.levels[1])
k = len(data.y.index.levels[0])
elif isinstance(data.x, np.ndarray):
n = data.y.shape[0]
k = data.y.shape[1]
else:
n = data.y.shape[1]
k = data.y.shape[2]
weights = 1 + np.random.random_sample(n)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
expected = weights[:, None] @ np.ones((1, k))
expected = expected.T.ravel()
expected = expected[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
# Per entity
if isinstance(data.x, pd.DataFrame):
n = len(data.y.index.levels[0])
k = len(data.y.index.levels[1])
elif isinstance(data.x, np.ndarray):
n = data.y.shape[1]
k = data.y.shape[0]
else:
n = data.y.shape[2]
k = data.y.shape[1]
weights = 1 + np.random.random_sample(n)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
expected = np.ones((k, 1)) @ weights[None, :]
expected = expected.T.ravel()
expected = expected[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
weights = 1 + np.random.random_sample(data.y.shape)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
expected = weights.T.ravel()
expected = expected[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
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_results_access(data):
mod = PanelOLS(data.y, data.x, entity_effects=True)
res = mod.fit()
d = dir(res)
for key in d:
if not key.startswith('_'):
val = getattr(res, key)
if callable(val):
val()
mod = PanelOLS(data.y, data.x, other_effects=data.c)
res = mod.fit()
d = dir(res)
for key in d:
if not key.startswith('_'):
val = getattr(res, key)
if callable(val):
val()
mod = PanelOLS(data.y, data.x, time_effects=True, entity_effects=True)
res = mod.fit()
d = dir(res)
for key in d:
if not key.startswith('_'):
val = getattr(res, key)
if callable(val):
val()
mod = PanelOLS(data.y, data.x)
res = mod.fit()
d = dir(res)
for key in d:
if not key.startswith('_'):
val = getattr(res, key)
if callable(val):
val()
const = PanelData(data.y).copy()
const.dataframe.iloc[:, :] = 1
const.dataframe.columns = ['const']
mod = PanelOLS(data.y, const)
res = mod.fit()
d = dir(res)
for key in d:
if not key.startswith('_'):
val = getattr(res, key)
if callable(val):
val()
def test_lsdv_options(data):
mod = PanelOLS(data.y, data.x, weights=data.w)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, weights=data.w, entity_effects=True)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, time_effects=True)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, time_effects=True, entity_effects=True)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
c1 = PanelData(data.c).dataframe.iloc[:, [0]]
mod = PanelOLS(data.y, data.x, entity_effects=True, other_effects=c1)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, time_effects=True, other_effects=c1)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y,
data.x,
weights=data.w,
entity_effects=True,
other_effects=c1)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y,
data.x,
weights=data.w,
time_effects=True,
other_effects=c1)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
mod = PanelOLS(data.y, data.x, weights=data.w, other_effects=data.c)
res1 = mod.fit()
res2 = mod.fit(use_lsdv=True)
assert_results_equal(res1, res2)
def test_const_data_only_weights(const_data):
y, x = const_data.y, const_data.x
mod = PanelOLS(y, x, weights=const_data.w)
res = mod.fit(debiased=False)
res2 = IV2SLS(y, x, None, None, weights=const_data.w).fit()
assert_allclose(res.params, res2.params)
def test_panel_ols(data):
PanelOLS(data.y, data.x).fit()
PanelOLS(data.y, data.x, entity_effects=True).fit()
PanelOLS(data.y, data.x, time_effects=True).fit()
def test_absorbed_option(data):
mod = PanelOLS(data.y, data.x, entity_effects=True, drop_absorbed=True)
res = mod.fit(auto_df=False, count_effects=False, debiased=False)
mod = PanelOLS(data.y, data.x, entity_effects=True, drop_absorbed=False)
res_false = mod.fit(auto_df=False, count_effects=False, debiased=False)
assert_results_equal(res, res_false)
def test_valid_weight_shape(data):
# Same size
n = np.prod(data.y.shape)
weights = 1 + np.random.random_sample(n)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
missing = PanelData(data.y).isnull | PanelData(data.x).isnull
expected = weights[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
# Per time
n = data.y.shape[0]
weights = 1 + np.random.random_sample(n)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
expected = weights[:, None] @ np.ones((1, data.y.shape[1]))
expected = expected.T.ravel()
expected = expected[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
# Per entity
n = data.y.shape[1]
weights = 1 + np.random.random_sample(n)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
expected = np.ones((data.y.shape[0], 1)) @ weights[None, :]
expected = expected.T.ravel()
expected = expected[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
weights = 1 + np.random.random_sample(data.y.shape)
mod = PanelOLS(data.y, data.x, weights=weights)
mod.fit()
w = mod.weights.values2d
expected = weights.T.ravel()
expected = expected[~missing.squeeze()][:, None]
expected = expected / expected.mean()
assert_equal(w, expected)
def test_panel_no_effects_weighted(data):
res = PanelOLS(data.y, data.x, weights=data.w).fit()
res2 = PooledOLS(data.y, data.x, weights=data.w).fit()
assert_results_equal(res, res2)
def test_results_access(data):
mod = PanelOLS(data.y, data.x, entity_effects=True)
res = mod.fit()
access_attributes(res)
mod = PanelOLS(data.y, data.x, other_effects=data.c)
res = mod.fit()
access_attributes(res)
mod = PanelOLS(data.y, data.x, time_effects=True, entity_effects=True)
res = mod.fit()
access_attributes(res)
mod = PanelOLS(data.y, data.x)
res = mod.fit()
access_attributes(res)
const = PanelData(data.y).copy()
const.dataframe.iloc[:, :] = 1
const.dataframe.columns = ["const"]
mod = PanelOLS(data.y, const)
res = mod.fit()
access_attributes(res)
def test_panel_both_lsdv_weighted(data):
mod = PanelOLS(data.y,
data.x,
entity_effects=True,
time_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
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)
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(d1.columns) +
list(d2.columns))
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)
from linearmodels.panel.model import PanelOLS
import statsmodels.api as sm
Data = Data.set_index(["id", "Age"])
# Create the variables they actually use
Data["ExpBin"] = 0
Data.loc[Data["ExpIncChange"] > 0, "ExpBin"] = 1
Data.loc[Data["ExpIncChange"] < 0, "ExpBin"] = -1
Data["ChangeBin"] = 0
Data.loc[Data["Y_change"] > 0, "ChangeBin"] = 1
Data.loc[Data["Y_change"] < 0, "ChangeBin"] = -1
mod = PanelOLS(Data.ExpBin,
sm.add_constant(Data.ChangeBin),
entity_effects=True)
fe_res = mod.fit()
print(fe_res)
# %% [markdown]
# The estimated $\hat{\gamma}_{1}$ is negative because in usual life-cycle calibrations, transitory shocks are volatile enough that mean reversion of transitory fluctuations is a stronger force than persistent trends in income age-profiles.
#
# However, with less volatile transitory shocks, the regression coefficient would be positive. We demonstrate this by shutting off transitory shocks, simulating another population of agents, and re-running the regression.
# %% tags=[]
# %%capture
params_no_transitory = copy(params)
params_no_transitory.update({"TranShkStd": [0.0] * len(params["TranShkStd"])})
# Create agent
