def setup_class(cls):
mod1 = cls.model_cls(endog, exog, **cls.mod_kwargs)
cls.res1 = mod1.fit(disp=False, **cls.fit_kwargs)
mod2 = OLS(endog, exog)
cls.res2 = mod2.fit(disp=False, **cls.fit_kwargs)
# for debugging
cls.res3 = mod2.fit(cov_type=cls.cov_type, cov_kwds={'maxlags': 2})
def setup_class(cls):
mod1 = cls.model_cls(endog, exog, **cls.mod_kwargs)
cls.res1 = mod1.fit(disp=False, **cls.fit_kwargs)
cls.res1b = mod1.fit(disp=False, **cls.fit_kwargs)
mod2 = OLS(endog, exog)
cls.res2 = mod2.fit(disp=False, **cls.fit_kwargs)
def setup_class(cls):
mod1 = cls.model_cls(endog, exog, **cls.mod_kwargs)
cls.res1 = mod1.fit(disp=False, **cls.fit_kwargs)
cls.res1b = mod1.fit(cov_type='nw-panel', cov_kwds=cls.cov_kwds)
mod2 = OLS(endog, exog)
cls.res2 = mod2.fit(disp=False, **cls.fit_kwargs)
def setup_class(cls):
mod1 = cls.model_cls(endog, exog, **cls.mod_kwargs)
cls.res1 = mod1.fit(**cls.fit_kwargs)
mod2 = OLS(endog, exog)
# check kernel as string
kwds2 = {'kernel': 'uniform', 'maxlags': 2}
cls.res2 = mod2.fit(cov_type=cls.cov_type, cov_kwds=kwds2)
def setup_class(cls):
# check kernel specified as string
mod1 = cls.model_cls(endog, exog, **cls.mod_kwargs)
cls.res1 = mod1.fit(disp=False, **cls.fit_kwargs)
mod2 = OLS(endog, exog)
cls.res2 = mod2.fit(disp=False,
cov_type=cls.cov_type,
cov_kwds={'maxlags': 2})
def setup(self):
model = OLS(self.res1.model.endog, self.res1.model.exog)
res_ols = model.fit(cov_type='cluster',
cov_kwds=dict(groups=self.groups,
use_correction=False,
use_t=False,
df_correction=True))
self.res3 = self.res1
self.res1 = res_ols
self.bse_robust = res_ols.bse
self.cov_robust = res_ols.cov_params()
cov1 = sw.cov_cluster(self.res1, self.groups, use_correction=False)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
def test_regularized_refit():
n = 100
p = 5
np.random.seed(3132)
xmat = np.random.normal(size=(n, p))
# covariates 0 and 2 matter
yvec = xmat[:, 0] + xmat[:, 2] + np.random.normal(size=n)
model1 = OLS(yvec, xmat)
result1 = model1.fit_regularized(alpha=2., L1_wt=0.5, refit=True)
model2 = OLS(yvec, xmat[:, [0, 2]])
result2 = model2.fit()
ii = [0, 2]
assert_allclose(result1.params[ii], result2.params)
assert_allclose(result1.bse[ii], result2.bse)
def setup_class(cls):
data = datasets.longley.load(as_pandas=False)
data.exog = add_constant(data.exog, prepend=False)
cls.res1 = OLS(data.endog, data.exog).fit()
#cls.res2.wresid = cls.res1.wresid # workaround hack
res_qr = OLS(data.endog, data.exog).fit(method="qr")
model_qr = OLS(data.endog, data.exog)
Q, R = np.linalg.qr(data.exog)
model_qr.exog_Q, model_qr.exog_R = Q, R
model_qr.normalized_cov_params = np.linalg.inv(np.dot(R.T, R))
model_qr.rank = np.linalg.matrix_rank(R)
res_qr2 = model_qr.fit(method="qr")
cls.res_qr = res_qr
cls.res_qr_manual = res_qr2
def setup_class(cls): # TODO: Why does upstream copy endog/exog?
mod1 = cls.model_cls(endog, exog, **cls.mod_kwargs)
cls.res1 = mod1.fit(disp=False, **cls.fit_kwargs)
mod2 = OLS(endog, exog)
cls.res2 = mod2.fit(disp=False, **cls.fit_kwargs)
def setup_class(cls): # TODO: de-dup with other setup_classes
mod1 = cls.model_cls(endog, exog, **cls.mod_kwargs)
cls.res1 = mod1.fit(disp=False, **cls.fit_kwargs)
mod2 = OLS(endog, exog)
cls.res2 = mod2.fit(disp=False, **cls.fit_kwargs)