def test_combine_indices():
# Moved from grouputils __main__ section
np.random.seed(985367)
groups = np.random.randint(0, 2, size=(10, 2))
uv, ux, u, label = combine_indices(groups, return_labels=True)
uv, ux, u, label = combine_indices(groups,
prefix='g1,g2=',
sep=',',
return_labels=True)
group0 = np.array(['sector0', 'sector1'])[groups[:, 0]]
group1 = np.array(['region0', 'region1'])[groups[:, 1]]
uv, ux, u, label = combine_indices((group0, group1),
prefix='sector,region=',
sep=',',
return_labels=True)
uv, ux, u, label = combine_indices((group0, group1),
prefix='',
sep='.',
return_labels=True)
group_joint = np.array(label)[uv]
group_joint_expected = np.array([
'sector1.region0', 'sector0.region1', 'sector0.region0',
'sector0.region1', 'sector1.region1', 'sector0.region0',
'sector1.region0', 'sector1.region0', 'sector0.region1',
'sector0.region0'
],
dtype='|U15')
assert_equal(group_joint, group_joint_expected)
def cov_cluster_2groups(results, group, group2=None, use_correction=True):
'''cluster robust covariance matrix for two groups/clusters
Parameters
----------
results : result instance
result of a regression, uses results.model.exog and results.resid
TODO: this should use wexog instead
use_correction : bool
If true (default), then the small sample correction factor is used.
Returns
-------
cov_both : ndarray, (k_vars, k_vars)
cluster robust covariance matrix for parameter estimates, for both
clusters
cov_0 : ndarray, (k_vars, k_vars)
cluster robust covariance matrix for parameter estimates for first
cluster
cov_1 : ndarray, (k_vars, k_vars)
cluster robust covariance matrix for parameter estimates for second
cluster
Notes
-----
verified against Peterson's table, (4 decimal print precision)
'''
if group2 is None:
if group.ndim != 2 or group.shape[1] != 2:
raise ValueError(
'if group2 is not given, then groups needs to be ' +
'an array with two columns')
group0 = group[:, 0]
group1 = group[:, 1]
else:
group0 = group
group1 = group2
group = (group0, group1)
cov0 = cov_cluster(results, group0, use_correction=use_correction)
#[0] because we get still also returns bse
cov1 = cov_cluster(results, group1, use_correction=use_correction)
# cov of cluster formed by intersection of two groups
cov01 = cov_cluster(results,
combine_indices(group)[0],
use_correction=use_correction)
#robust cov matrix for union of groups
cov_both = cov0 + cov1 - cov01
#return all three (for now?)
return cov_both, cov0, cov1
def cov_cluster_2groups(results, group, group2=None, use_correction=True):
'''cluster robust covariance matrix for two groups/clusters
Parameters
----------
results : result instance
result of a regression, uses results.model.exog and results.resid
TODO: this should use wexog instead
use_correction : bool
If true (default), then the small sample correction factor is used.
Returns
-------
cov_both : ndarray, (k_vars, k_vars)
cluster robust covariance matrix for parameter estimates, for both
clusters
cov_0 : ndarray, (k_vars, k_vars)
cluster robust covariance matrix for parameter estimates for first
cluster
cov_1 : ndarray, (k_vars, k_vars)
cluster robust covariance matrix for parameter estimates for second
cluster
Notes
-----
verified against Peterson's table, (4 decimal print precision)
'''
if group2 is None:
if group.ndim !=2 or group.shape[1] != 2:
raise ValueError('if group2 is not given, then groups needs to be ' +
'an array with two columns')
group0 = group[:, 0]
group1 = group[:, 1]
else:
group0 = group
group1 = group2
group = (group0, group1)
cov0 = cov_cluster(results, group0, use_correction=use_correction)
#[0] because we get still also returns bse
cov1 = cov_cluster(results, group1, use_correction=use_correction)
# cov of cluster formed by intersection of two groups
cov01 = cov_cluster(results,
combine_indices(group)[0],
use_correction=use_correction)
#robust cov matrix for union of groups
cov_both = cov0 + cov1 - cov01
#return all three (for now?)
return cov_both, cov0, cov1
def test_combine_indices():
# Moved from grouputils __main__ section
np.random.seed(985367)
groups = np.random.randint(0, 2, size=(10, 2))
uv, ux, u, label = combine_indices(groups, return_labels=True)
uv, ux, u, label = combine_indices(groups, prefix='g1,g2=', sep=',',
return_labels=True)
group0 = np.array(['sector0', 'sector1'])[groups[:, 0]]
group1 = np.array(['region0', 'region1'])[groups[:, 1]]
uv, ux, u, label = combine_indices((group0, group1),
prefix='sector,region=',
sep=',',
return_labels=True)
uv, ux, u, label = combine_indices((group0, group1), prefix='', sep='.',
return_labels=True)
group_joint = np.array(label)[uv]
group_joint_expected = np.array(['sector1.region0', 'sector0.region1',
'sector0.region0', 'sector0.region1',
'sector1.region1', 'sector0.region0',
'sector1.region0', 'sector1.region0',
'sector0.region1', 'sector0.region0'],
dtype='|U15')
assert_equal(group_joint, group_joint_expected)
