def test_cov_cluster_2groups():
#comparing cluster robust standard errors to Peterson
#requires Petersen's test_data
#http://www.kellogg.northwestern.edu/faculty/petersen/htm/papers/se/test_data.txt
import os
cur_dir = os.path.abspath(os.path.dirname(__file__))
fpath = os.path.join(cur_dir,"test_data.txt")
pet = np.genfromtxt(fpath)
endog = pet[:,-1]
group = pet[:,0].astype(int)
time = pet[:,1].astype(int)
exog = add_constant(pet[:,2])
res = OLS(endog, exog).fit()
cov01, covg, covt = sw.cov_cluster_2groups(res, group, group2=time)
#Reference number from Petersen
#http://www.kellogg.northwestern.edu/faculty/petersen/htm/papers/se/test_data.htm
bse_petw = [0.0284, 0.0284]
bse_pet0 = [0.0670, 0.0506]
bse_pet1 = [0.0234, 0.0334] #year
bse_pet01 = [0.0651, 0.0536] #firm and year
bse_0 = sw.se_cov(covg)
bse_1 = sw.se_cov(covt)
bse_01 = sw.se_cov(cov01)
#print res.HC0_se, bse_petw - res.HC0_se
#print bse_0, bse_0 - bse_pet0
#print bse_1, bse_1 - bse_pet1
#print bse_01, bse_01 - bse_pet01
assert_almost_equal(bse_petw, res.HC0_se, decimal=4)
assert_almost_equal(bse_0, bse_pet0, decimal=4)
assert_almost_equal(bse_1, bse_pet1, decimal=4)
assert_almost_equal(bse_01, bse_pet01, decimal=4)
def test_hac(self):
res = self.res
#> nw = NeweyWest(fm, lag = 4, prewhite = FALSE, verbose=TRUE)
#> nw2 = NeweyWest(fm, lag=10, prewhite = FALSE, verbose=TRUE)
#> mkarray(nw, "cov_hac_4")
cov_hac_4 = np.array([1.385551290884014, -0.3133096102522685,
-0.0597207976835705, -0.3133096102522685, 0.1081011690351306,
0.000389440793564336, -0.0597207976835705, 0.000389440793564339,
0.0862118527405036]).reshape(3,3, order='F')
#> mkarray(nw2, "cov_hac_10")
cov_hac_10 = np.array([1.257386180080192, -0.2871560199899846,
-0.03958300024627573, -0.2871560199899845, 0.1049107028987101,
0.0003896205316866944, -0.03958300024627578, 0.0003896205316866961,
0.0985539340694839]).reshape(3,3, order='F')
cov = sw.cov_hac_simple(res, nlags=4, use_correction=False)
bse_hac = sw.se_cov(cov)
assert_almost_equal(cov, cov_hac_4, decimal=14)
assert_almost_equal(bse_hac, np.sqrt(np.diag(cov)), decimal=14)
cov = sw.cov_hac_simple(res, nlags=10, use_correction=False)
bse_hac = sw.se_cov(cov)
assert_almost_equal(cov, cov_hac_10, decimal=14)
assert_almost_equal(bse_hac, np.sqrt(np.diag(cov)), decimal=14)
def test_hac_simple():
from statsmodels.datasets import macrodata
d2 = macrodata.load().data
g_gdp = 400 * np.diff(np.log(d2['realgdp']))
g_inv = 400 * np.diff(np.log(d2['realinv']))
exogg = add_constant(np.c_[g_gdp, d2['realint'][:-1]], prepend=True)
res_olsg = OLS(g_inv, exogg).fit()
#> NeweyWest(fm, lag = 4, prewhite = FALSE, sandwich = TRUE, verbose=TRUE, adjust=TRUE)
#Lag truncation parameter chosen: 4
# (Intercept) ggdp lint
cov1_r = [
[1.40643899878678802, -0.3180328707083329709, -0.060621111216488610],
[-0.31803287070833292, 0.1097308348999818661, 0.000395311760301478],
[-0.06062111121648865, 0.0003953117603014895, 0.087511528912470993]
]
#> NeweyWest(fm, lag = 4, prewhite = FALSE, sandwich = TRUE, verbose=TRUE, adjust=FALSE)
#Lag truncation parameter chosen: 4
# (Intercept) ggdp lint
cov2_r = [
[1.3855512908840137, -0.313309610252268500, -0.059720797683570477],
[-0.3133096102522685, 0.108101169035130618, 0.000389440793564339],
[-0.0597207976835705, 0.000389440793564336, 0.086211852740503622]
]
cov1 = sw.cov_hac_simple(res_olsg, nlags=4, use_correction=True)
se1 = sw.se_cov(cov1)
cov2 = sw.cov_hac_simple(res_olsg, nlags=4, use_correction=False)
se2 = sw.se_cov(cov2)
assert_almost_equal(cov1, cov1_r, decimal=14)
assert_almost_equal(cov2, cov2_r, decimal=14)
def test_hac(self):
res = self.res
#> nw = NeweyWest(fm, lag = 4, prewhite = FALSE, verbose=TRUE)
#> nw2 = NeweyWest(fm, lag=10, prewhite = FALSE, verbose=TRUE)
#> mkarray(nw, "cov_hac_4")
cov_hac_4 = np.array([
1.385551290884014, -0.3133096102522685, -0.0597207976835705,
-0.3133096102522685, 0.1081011690351306, 0.000389440793564336,
-0.0597207976835705, 0.000389440793564339, 0.0862118527405036
]).reshape(3, 3, order='F')
#> mkarray(nw2, "cov_hac_10")
cov_hac_10 = np.array([
1.257386180080192, -0.2871560199899846, -0.03958300024627573,
-0.2871560199899845, 0.1049107028987101, 0.0003896205316866944,
-0.03958300024627578, 0.0003896205316866961, 0.0985539340694839
]).reshape(3, 3, order='F')
cov = sw.cov_hac_simple(res, nlags=4, use_correction=False)
bse_hac = sw.se_cov(cov)
assert_almost_equal(cov, cov_hac_4, decimal=14)
assert_almost_equal(bse_hac, np.sqrt(np.diag(cov)), decimal=14)
cov = sw.cov_hac_simple(res, nlags=10, use_correction=False)
bse_hac = sw.se_cov(cov)
assert_almost_equal(cov, cov_hac_10, decimal=14)
assert_almost_equal(bse_hac, np.sqrt(np.diag(cov)), decimal=14)
def test_hac_simple():
from statsmodels.datasets import macrodata
d2 = macrodata.load().data
g_gdp = 400*np.diff(np.log(d2['realgdp']))
g_inv = 400*np.diff(np.log(d2['realinv']))
exogg = add_constant(np.c_[g_gdp, d2['realint'][:-1]])
res_olsg = OLS(g_inv, exogg).fit()
#> NeweyWest(fm, lag = 4, prewhite = FALSE, sandwich = TRUE, verbose=TRUE, adjust=TRUE)
#Lag truncation parameter chosen: 4
# (Intercept) ggdp lint
cov1_r = [[ 1.40643899878678802, -0.3180328707083329709, -0.060621111216488610],
[ -0.31803287070833292, 0.1097308348999818661, 0.000395311760301478],
[ -0.06062111121648865, 0.0003953117603014895, 0.087511528912470993]]
#> NeweyWest(fm, lag = 4, prewhite = FALSE, sandwich = TRUE, verbose=TRUE, adjust=FALSE)
#Lag truncation parameter chosen: 4
# (Intercept) ggdp lint
cov2_r = [[ 1.3855512908840137, -0.313309610252268500, -0.059720797683570477],
[ -0.3133096102522685, 0.108101169035130618, 0.000389440793564339],
[ -0.0597207976835705, 0.000389440793564336, 0.086211852740503622]]
cov1 = sw.cov_hac_simple(res_olsg, nlags=4, use_correction=True)
se1 = sw.se_cov(cov1)
cov2 = sw.cov_hac_simple(res_olsg, nlags=4, use_correction=False)
se2 = sw.se_cov(cov2)
assert_almost_equal(cov1, cov1_r, decimal=14)
assert_almost_equal(cov2, cov2_r, decimal=14)
def test_cov_cluster_2groups():
#comparing cluster robust standard errors to Peterson
#requires Petersen's test_data
#http://www.kellogg.northwestern.edu/faculty/petersen/htm/papers/se/test_data.txt
import os
cur_dir = os.path.abspath(os.path.dirname(__file__))
fpath = os.path.join(cur_dir,"test_data.txt")
pet = np.genfromtxt(fpath)
endog = pet[:,-1]
group = pet[:,0].astype(int)
time = pet[:,1].astype(int)
exog = add_constant(pet[:,2])
res = OLS(endog, exog).fit()
cov01, covg, covt = sw.cov_cluster_2groups(res, group, group2=time)
#Reference number from Petersen
#http://www.kellogg.northwestern.edu/faculty/petersen/htm/papers/se/test_data.htm
bse_petw = [0.0284, 0.0284]
bse_pet0 = [0.0670, 0.0506]
bse_pet1 = [0.0234, 0.0334] #year
bse_pet01 = [0.0651, 0.0536] #firm and year
bse_0 = sw.se_cov(covg)
bse_1 = sw.se_cov(covt)
bse_01 = sw.se_cov(cov01)
#print res.HC0_se, bse_petw - res.HC0_se
#print bse_0, bse_0 - bse_pet0
#print bse_1, bse_1 - bse_pet1
#print bse_01, bse_01 - bse_pet01
assert_almost_equal(bse_petw, res.HC0_se, decimal=4)
assert_almost_equal(bse_0, bse_pet0, decimal=4)
assert_almost_equal(bse_1, bse_pet1, decimal=4)
assert_almost_equal(bse_01, bse_pet01, decimal=4)
def setup(self):
res_ols = self.res1.get_robustcov_results(
"cluster",
groups=(self.groups, self.time),
use_correction=True,
use_t=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_2groups(self.res1,
self.groups,
group2=self.time,
use_correction=True)[0]
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_cluster_2groups_small
self.rtol = (
0.35 # only f_pvalue and confint for constant differ >rtol=0.05
)
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.model.fit(
cov_type="nw-panel",
cov_kwds=dict(
groups=self.groups,
maxlags=4,
use_correction="hac",
use_t=True,
df_correction=False,
),
)
self.res3 = self.res1
self.res1 = res_ols
self.bse_robust = res_ols.bse
self.cov_robust = res_ols.cov_params()
cov1 = sw.cov_nw_panel(self.res1, 4, self.tidx)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_nw_panel4
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.model.fit(
cov_type="nw-groupsum",
cov_kwds=dict(time=self.time,
maxlags=4,
use_correction=False,
use_t=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_nw_groupsum(self.res1,
4,
self.time,
use_correction=False)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_nw_groupsum4
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
model = OLS(self.res1.model.endog, self.res1.model.exog)
# res_ols = self.res1.model.fit(cov_type='cluster',
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
self.small = False
self.res2 = res2.results_cluster_large
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def cov_hac_simple(results,
nlags=None,
weights_func=weights_bartlett,
use_correction=True):
c = cov_hac(results,
nlags=nlags,
weights_func=weights_func,
use_correction=use_correction)
return c, se_cov(c)
def setup(self):
res_ols = self.res1
cov1 = sw.cov_hac_simple(res_ols, nlags=4, use_correction=False)
se1 = sw.se_cov(cov1)
self.bse_robust = se1
self.cov_robust = cov1
self.small = False
self.res2 = res.results_ivhac4_large
def test_hac_simple():
from statsmodels.datasets import macrodata
d2 = macrodata.load_pandas().data
g_gdp = 400 * np.diff(np.log(d2['realgdp'].values))
g_inv = 400 * np.diff(np.log(d2['realinv'].values))
exogg = add_constant(np.c_[g_gdp, d2['realint'][:-1].values])
res_olsg = OLS(g_inv, exogg).fit()
# > NeweyWest(fm, lag = 4, prewhite = FALSE, sandwich = TRUE,
# verbose=TRUE, adjust=TRUE)
# Lag truncation parameter chosen: 4
# (Intercept) ggdp lint
cov1_r = [
[+1.40643899878678802, -0.3180328707083329709, -0.060621111216488610],
[-0.31803287070833292, 0.1097308348999818661, +0.000395311760301478],
[-0.06062111121648865, 0.0003953117603014895, +0.087511528912470993]
]
# > NeweyWest(fm, lag = 4, prewhite = FALSE, sandwich = TRUE,
# verbose=TRUE, adjust=FALSE)
# Lag truncation parameter chosen: 4
# (Intercept) ggdp lint
cov2_r = [
[+1.3855512908840137, -0.313309610252268500, -0.059720797683570477],
[-0.3133096102522685, +0.108101169035130618, +0.000389440793564339],
[-0.0597207976835705, +0.000389440793564336, +0.086211852740503622]
]
cov1 = sw.cov_hac_simple(res_olsg, nlags=4, use_correction=True)
se1 = sw.se_cov(cov1)
cov2 = sw.cov_hac_simple(res_olsg, nlags=4, use_correction=False)
se2 = sw.se_cov(cov2)
# Relax precision requirements for this test due to failure in NumPy 1.23
assert_allclose(cov1, cov1_r)
assert_allclose(cov2, cov2_r)
assert_allclose(np.sqrt(np.diag(cov1_r)), se1)
assert_allclose(np.sqrt(np.diag(cov2_r)), se2)
# compare default for nlags
cov3 = sw.cov_hac_simple(res_olsg, use_correction=False)
cov4 = sw.cov_hac_simple(res_olsg, nlags=4, use_correction=False)
assert_allclose(cov3, cov4)
def get_robust_clu(cls):
res1 = cls.res1
cov_clu = sc.cov_cluster(res1, group)
cls.bse_rob = sc.se_cov(cov_clu)
nobs, k_vars = res1.model.exog.shape
k_params = len(res1.params)
#n_groups = len(np.unique(group))
corr_fact = (nobs - 1.) / float(nobs - k_params)
# for bse we need sqrt of correction factor
cls.corr_fact = np.sqrt(corr_fact)
def get_robust_clu(cls):
res1 = cls.res1
cov_clu = sw.cov_cluster(res1, group)
cls.bse_rob = sw.se_cov(cov_clu)
nobs, k_vars = res1.model.exog.shape
k_params = len(res1.params)
#n_groups = len(np.unique(group))
corr_fact = (nobs-1.) / float(nobs - k_params)
# for bse we need sqrt of correction factor
cls.corr_fact = np.sqrt(corr_fact)
def setup(self):
res_ols = self.res1.get_robustcov_results("HAC", maxlags=4, use_correction=True, use_t=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_hac_simple(res_ols, nlags=4, use_correction=True)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res.results_ivhac4_small
def setup(self):
res_ols = self.res1.get_robustcov_results('HAC', maxlags=4,
use_correction=True, use_t=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_hac_simple(res_ols, nlags=4, use_correction=True)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res.results_ivhac4_small
def setup(self):
res_ols = self.res1.get_robustcov_results("cluster", groups=self.groups, use_correction=True, use_t=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=True)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_cluster_wls_small
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.model.fit(
cov_type="cluster", cov_kwds=dict(groups=self.groups, use_correction=True, use_t=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=True)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_cluster
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results(
"cluster", groups=(self.groups, self.time), use_correction=True, use_t=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_2groups(self.res1, self.groups, group2=self.time, use_correction=True)[0]
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_cluster_2groups_small
self.rtol = 0.35 # only f_pvalue and confint for constant differ >rtol=0.05
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results(
"cluster", groups=self.groups, use_correction=True, use_t=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=True)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_cluster_wls_small
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results("HC1", use_t=True)
self.res3 = self.res1
self.res1 = res_ols
self.bse_robust = res_ols.bse
self.cov_robust = res_ols.cov_params()
# TODO: check standalone function
# cov1 = sw.cov_cluster(self.res1, self.groups, use_correction=False)
cov1 = res_ols.cov_HC1
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_hc1_wls_small
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results(
"cluster", groups=(self.groups, self.time), use_correction=False, use_t=False # 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_2groups(self.res1, self.groups, group2=self.time, use_correction=False)[0]
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = False
self.res2 = res2.results_cluster_2groups_large
self.skip_f = True
self.rtol = 1e-7
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.model.fit(cov_type='cluster',
cov_kwds=dict(groups=self.groups,
use_correction=True,
use_t=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=True)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_cluster
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.model.fit(
cov_type="nw-groupsum", cov_kwds=dict(time=self.time, maxlags=4, use_correction=False, use_t=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_nw_groupsum(self.res1, 4, self.time, use_correction=False)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_nw_groupsum4
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results(
"nw-panel", time=self.time, maxlags=4, use_correction="hac", use_t=True, df_correction=False
)
self.res3 = self.res1
self.res1 = res_ols
self.bse_robust = res_ols.bse
self.cov_robust = res_ols.cov_params()
cov1 = sw.cov_nw_panel(self.res1, 4, self.tidx)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_nw_panel4
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results('HC1', use_t=True)
self.res3 = self.res1
self.res1 = res_ols
self.bse_robust = res_ols.bse
self.cov_robust = res_ols.cov_params()
#TODO: check standalone function
#cov1 = sw.cov_cluster(self.res1, self.groups, use_correction=False)
cov1 = res_ols.cov_HC1
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_hc1_wls_small
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results('cluster',
groups=(self.groups, self.time),
use_correction=False, #True,
use_t=False)
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_2groups(self.res1, self.groups, group2=self.time,
use_correction=False)[0]
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = False
self.res2 = res2.results_cluster_2groups_large
self.skip_f = True
self.rtol = 1e-7
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results('nw-groupsum',
time=self.time,
maxlags=4,
use_correction=False,
use_t=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_nw_groupsum(self.res1, 4, self.time, use_correction=False)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_nw_groupsum4
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results('cluster',
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
self.small = False
self.res2 = res2.results_cluster_large
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
model = OLS(self.res1.model.endog, self.res1.model.exog)
# res_ols = self.res1.model.fit(cov_type='cluster',
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
self.small = False
self.res2 = res2.results_cluster_large
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.model.fit(cov_type='nw-panel',
cov_kwds = dict(groups=self.groups,
maxlags=4,
use_correction='hac',
use_t=True,
df_correction=False))
self.res3 = self.res1
self.res1 = res_ols
self.bse_robust = res_ols.bse
self.cov_robust = res_ols.cov_params()
cov1 = sw.cov_nw_panel(self.res1, 4, self.tidx)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_nw_panel4
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
import pandas as pd
fat_array = self.groups.reshape(-1, 1)
fat_groups = pd.DataFrame(fat_array)
res_ols = self.res1.get_robustcov_results('cluster',
groups=fat_groups,
use_correction=True,
use_t=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=True)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_cluster
self.rtol = 1e-6
self.rtolh = 1e-10
def setup(self):
res_ols = self.res1.get_robustcov_results(
"nw-panel",
time=self.time,
maxlags=4,
use_correction="hac",
use_t=True,
df_correction=False,
)
self.res3 = self.res1
self.res1 = res_ols
self.bse_robust = res_ols.bse
self.cov_robust = res_ols.cov_params()
cov1 = sw.cov_nw_panel(self.res1, 4, self.tidx)
se1 = sw.se_cov(cov1)
self.bse_robust2 = se1
self.cov_robust2 = cov1
self.small = True
self.res2 = res2.results_nw_panel4
self.skip_f = True
self.rtol = 1e-6
self.rtolh = 1e-10
mask = (xx!=-999.0).all(1) #nan code in dta file
mask.shape
y = y[mask]
xx = xx[mask]
group = group[mask]
#run OLS
res_srs = sm.OLS(y, xx).fit()
print('params ', res_srs.params)
print('bse_OLS ', res_srs.bse)
#get cluster robust standard errors and compare with STATA
cov_cr = sw.cov_cluster(res_srs, group.astype(int))
bse_cr = sw.se_cov(cov_cr)
print('bse_rob ', bse_cr)
res_stata = np.rec.array(
[('growth', '|', -0.1027121, 0.22917029999999999, -0.45000000000000001, 0.65500000000000003, -0.55483519999999997, 0.34941109999999997),
('emer', '|', -5.4449319999999997, 0.72939690000000001, -7.46, 0.0, -6.8839379999999997, -4.0059269999999998),
('yr_rnd', '|', -51.075690000000002, 22.83615, -2.2400000000000002, 0.027, -96.128439999999998, -6.0229350000000004),
('_cons', '|', 740.3981, 13.460760000000001, 55.0, 0.0, 713.84180000000003, 766.95439999999996)],
dtype=[('exogname', '|S6'), ('del', '|S1'), ('params', 'float'),
('bse', 'float'), ('tvalues', 'float'), ('pvalues', 'float'),
('cilow', 'float'), ('ciupp', 'float')])
print('diff Stata', bse_cr - res_stata.bse)
assert_almost_equal(bse_cr, res_stata.bse, decimal=6)
#We see that in this case the robust standard errors of the parameter estimates
def cov_hac_simple(results, nlags=None, weights_func=weights_bartlett,
use_correction=True):
c = cov_hac(results, nlags=nlags, weights_func=weights_func,
use_correction=use_correction)
return c, se_cov(c)
def test_all(self):
d = macrodata.load().data
#import datasetswsm.greene as g
#d = g.load('5-1')
#growth rates
gs_l_realinv = 400 * np.diff(np.log(d['realinv']))
gs_l_realgdp = 400 * np.diff(np.log(d['realgdp']))
#simple diff, not growthrate, I want heteroscedasticity later for testing
endogd = np.diff(d['realinv'])
exogd = add_constant(np.c_[np.diff(d['realgdp']), d['realint'][:-1]],
prepend=True)
endogg = gs_l_realinv
exogg = add_constant(np.c_[gs_l_realgdp, d['realint'][:-1]],prepend=True)
res_ols = OLS(endogg, exogg).fit()
#print res_ols.params
mod_g1 = GLSAR(endogg, exogg, rho=-0.108136)
res_g1 = mod_g1.fit()
#print res_g1.params
mod_g2 = GLSAR(endogg, exogg, rho=-0.108136) #-0.1335859) from R
res_g2 = mod_g2.iterative_fit(maxiter=5)
#print res_g2.params
rho = -0.108136
# coefficient std. error t-ratio p-value 95% CONFIDENCE INTERVAL
partable = np.array([
[-9.50990, 0.990456, -9.602, 3.65e-018, -11.4631, -7.55670], # ***
[ 4.37040, 0.208146, 21.00, 2.93e-052, 3.95993, 4.78086], # ***
[-0.579253, 0.268009, -2.161, 0.0319, -1.10777, -0.0507346]]) # **
#Statistics based on the rho-differenced data:
result_gretl_g1 = dict(
endog_mean = ("Mean dependent var", 3.113973),
endog_std = ("S.D. dependent var", 18.67447),
ssr = ("Sum squared resid", 22530.90),
mse_resid_sqrt = ("S.E. of regression", 10.66735),
rsquared = ("R-squared", 0.676973),
rsquared_adj = ("Adjusted R-squared", 0.673710),
fvalue = ("F(2, 198)", 221.0475),
f_pvalue = ("P-value(F)", 3.56e-51),
resid_acf1 = ("rho", -0.003481),
dw = ("Durbin-Watson", 1.993858))
#fstatistic, p-value, df1, df2
reset_2_3 = [5.219019, 0.00619, 2, 197, "f"]
reset_2 = [7.268492, 0.00762, 1, 198, "f"]
reset_3 = [5.248951, 0.023, 1, 198, "f"]
#LM-statistic, p-value, df
arch_4 = [7.30776, 0.120491, 4, "chi2"]
#multicollinearity
vif = [1.002, 1.002]
cond_1norm = 6862.0664
determinant = 1.0296049e+009
reciprocal_condition_number = 0.013819244
#Chi-square(2): test-statistic, pvalue, df
normality = [20.2792, 3.94837e-005, 2]
#tests
res = res_g1 #with rho from Gretl
#basic
assert_almost_equal(res.params, partable[:,0], 4)
assert_almost_equal(res.bse, partable[:,1], 6)
assert_almost_equal(res.tvalues, partable[:,2], 2)
assert_almost_equal(res.ssr, result_gretl_g1['ssr'][1], decimal=2)
#assert_almost_equal(res.llf, result_gretl_g1['llf'][1], decimal=7) #not in gretl
#assert_almost_equal(res.rsquared, result_gretl_g1['rsquared'][1], decimal=7) #FAIL
#assert_almost_equal(res.rsquared_adj, result_gretl_g1['rsquared_adj'][1], decimal=7) #FAIL
assert_almost_equal(np.sqrt(res.mse_resid), result_gretl_g1['mse_resid_sqrt'][1], decimal=5)
assert_almost_equal(res.fvalue, result_gretl_g1['fvalue'][1], decimal=4)
assert_approx_equal(res.f_pvalue, result_gretl_g1['f_pvalue'][1], significant=2)
#assert_almost_equal(res.durbin_watson, result_gretl_g1['dw'][1], decimal=7) #TODO
#arch
#sm_arch = smsdia.acorr_lm(res.wresid**2, maxlag=4, autolag=None)
sm_arch = smsdia.het_arch(res.wresid, maxlag=4)
assert_almost_equal(sm_arch[0], arch_4[0], decimal=4)
assert_almost_equal(sm_arch[1], arch_4[1], decimal=6)
#tests
res = res_g2 #with estimated rho
#estimated lag coefficient
assert_almost_equal(res.model.rho, rho, decimal=3)
#basic
assert_almost_equal(res.params, partable[:,0], 4)
assert_almost_equal(res.bse, partable[:,1], 3)
assert_almost_equal(res.tvalues, partable[:,2], 2)
assert_almost_equal(res.ssr, result_gretl_g1['ssr'][1], decimal=2)
#assert_almost_equal(res.llf, result_gretl_g1['llf'][1], decimal=7) #not in gretl
#assert_almost_equal(res.rsquared, result_gretl_g1['rsquared'][1], decimal=7) #FAIL
#assert_almost_equal(res.rsquared_adj, result_gretl_g1['rsquared_adj'][1], decimal=7) #FAIL
assert_almost_equal(np.sqrt(res.mse_resid), result_gretl_g1['mse_resid_sqrt'][1], decimal=5)
assert_almost_equal(res.fvalue, result_gretl_g1['fvalue'][1], decimal=0)
assert_almost_equal(res.f_pvalue, result_gretl_g1['f_pvalue'][1], decimal=6)
#assert_almost_equal(res.durbin_watson, result_gretl_g1['dw'][1], decimal=7) #TODO
c = oi.reset_ramsey(res, degree=2)
compare_ftest(c, reset_2, decimal=(2,4))
c = oi.reset_ramsey(res, degree=3)
compare_ftest(c, reset_2_3, decimal=(2,4))
#arch
#sm_arch = smsdia.acorr_lm(res.wresid**2, maxlag=4, autolag=None)
sm_arch = smsdia.het_arch(res.wresid, maxlag=4)
assert_almost_equal(sm_arch[0], arch_4[0], decimal=1)
assert_almost_equal(sm_arch[1], arch_4[1], decimal=2)
'''
Performing iterative calculation of rho...
ITER RHO ESS
1 -0.10734 22530.9
2 -0.10814 22530.9
Model 4: Cochrane-Orcutt, using observations 1959:3-2009:3 (T = 201)
Dependent variable: ds_l_realinv
rho = -0.108136
coefficient std. error t-ratio p-value
-------------------------------------------------------------
const -9.50990 0.990456 -9.602 3.65e-018 ***
ds_l_realgdp 4.37040 0.208146 21.00 2.93e-052 ***
realint_1 -0.579253 0.268009 -2.161 0.0319 **
Statistics based on the rho-differenced data:
Mean dependent var 3.113973 S.D. dependent var 18.67447
Sum squared resid 22530.90 S.E. of regression 10.66735
R-squared 0.676973 Adjusted R-squared 0.673710
F(2, 198) 221.0475 P-value(F) 3.56e-51
rho -0.003481 Durbin-Watson 1.993858
'''
'''
RESET test for specification (squares and cubes)
Test statistic: F = 5.219019,
with p-value = P(F(2,197) > 5.21902) = 0.00619
RESET test for specification (squares only)
Test statistic: F = 7.268492,
with p-value = P(F(1,198) > 7.26849) = 0.00762
RESET test for specification (cubes only)
Test statistic: F = 5.248951,
with p-value = P(F(1,198) > 5.24895) = 0.023:
'''
'''
Test for ARCH of order 4
coefficient std. error t-ratio p-value
--------------------------------------------------------
alpha(0) 97.0386 20.3234 4.775 3.56e-06 ***
alpha(1) 0.176114 0.0714698 2.464 0.0146 **
alpha(2) -0.0488339 0.0724981 -0.6736 0.5014
alpha(3) -0.0705413 0.0737058 -0.9571 0.3397
alpha(4) 0.0384531 0.0725763 0.5298 0.5968
Null hypothesis: no ARCH effect is present
Test statistic: LM = 7.30776
with p-value = P(Chi-square(4) > 7.30776) = 0.120491:
'''
'''
Variance Inflation Factors
Minimum possible value = 1.0
Values > 10.0 may indicate a collinearity problem
ds_l_realgdp 1.002
realint_1 1.002
VIF(j) = 1/(1 - R(j)^2), where R(j) is the multiple correlation coefficient
between variable j and the other independent variables
Properties of matrix X'X:
1-norm = 6862.0664
Determinant = 1.0296049e+009
Reciprocal condition number = 0.013819244
'''
'''
Test for ARCH of order 4 -
Null hypothesis: no ARCH effect is present
Test statistic: LM = 7.30776
with p-value = P(Chi-square(4) > 7.30776) = 0.120491
Test of common factor restriction -
Null hypothesis: restriction is acceptable
Test statistic: F(2, 195) = 0.426391
with p-value = P(F(2, 195) > 0.426391) = 0.653468
Test for normality of residual -
Null hypothesis: error is normally distributed
Test statistic: Chi-square(2) = 20.2792
with p-value = 3.94837e-005:
'''
#no idea what this is
'''
Augmented regression for common factor test
OLS, using observations 1959:3-2009:3 (T = 201)
Dependent variable: ds_l_realinv
coefficient std. error t-ratio p-value
---------------------------------------------------------------
const -10.9481 1.35807 -8.062 7.44e-014 ***
ds_l_realgdp 4.28893 0.229459 18.69 2.40e-045 ***
realint_1 -0.662644 0.334872 -1.979 0.0492 **
ds_l_realinv_1 -0.108892 0.0715042 -1.523 0.1294
ds_l_realgdp_1 0.660443 0.390372 1.692 0.0923 *
realint_2 0.0769695 0.341527 0.2254 0.8219
Sum of squared residuals = 22432.8
Test of common factor restriction
Test statistic: F(2, 195) = 0.426391, with p-value = 0.653468
'''
################ with OLS, HAC errors
#Model 5: OLS, using observations 1959:2-2009:3 (T = 202)
#Dependent variable: ds_l_realinv
#HAC standard errors, bandwidth 4 (Bartlett kernel)
#coefficient std. error t-ratio p-value 95% CONFIDENCE INTERVAL
#for confidence interval t(199, 0.025) = 1.972
partable = np.array([
[-9.48167, 1.17709, -8.055, 7.17e-014, -11.8029, -7.16049], # ***
[4.37422, 0.328787, 13.30, 2.62e-029, 3.72587, 5.02258], #***
[-0.613997, 0.293619, -2.091, 0.0378, -1.19300, -0.0349939]]) # **
result_gretl_g1 = dict(
endog_mean = ("Mean dependent var", 3.257395),
endog_std = ("S.D. dependent var", 18.73915),
ssr = ("Sum squared resid", 22799.68),
mse_resid_sqrt = ("S.E. of regression", 10.70380),
rsquared = ("R-squared", 0.676978),
rsquared_adj = ("Adjusted R-squared", 0.673731),
fvalue = ("F(2, 199)", 90.79971),
f_pvalue = ("P-value(F)", 9.53e-29),
llf = ("Log-likelihood", -763.9752),
aic = ("Akaike criterion", 1533.950),
bic = ("Schwarz criterion", 1543.875),
hqic = ("Hannan-Quinn", 1537.966),
resid_acf1 = ("rho", -0.107341),
dw = ("Durbin-Watson", 2.213805))
linear_logs = [1.68351, 0.430953, 2, "chi2"]
#for logs: dropping 70 nan or incomplete observations, T=133
#(res_ols.model.exog <=0).any(1).sum() = 69 ?not 70
linear_squares = [7.52477, 0.0232283, 2, "chi2"]
#Autocorrelation, Breusch-Godfrey test for autocorrelation up to order 4
lm_acorr4 = [1.17928, 0.321197, 4, 195, "F"]
lm2_acorr4 = [4.771043, 0.312, 4, "chi2"]
acorr_ljungbox4 = [5.23587, 0.264, 4, "chi2"]
#break
cusum_Harvey_Collier = [0.494432, 0.621549, 198, "t"] #stats.t.sf(0.494432, 198)*2
#see cusum results in files
break_qlr = [3.01985, 0.1, 3, 196, "maxF"] #TODO check this, max at 2001:4
break_chow = [13.1897, 0.00424384, 3, "chi2"] # break at 1984:1
arch_4 = [3.43473, 0.487871, 4, "chi2"]
normality = [23.962, 0.00001, 2, "chi2"]
het_white = [33.503723, 0.000003, 5, "chi2"]
het_breush_pagan = [1.302014, 0.521520, 2, "chi2"] #TODO: not available
het_breush_pagan_konker = [0.709924, 0.701200, 2, "chi2"]
reset_2_3 = [5.219019, 0.00619, 2, 197, "f"]
reset_2 = [7.268492, 0.00762, 1, 198, "f"]
reset_3 = [5.248951, 0.023, 1, 198, "f"] #not available
cond_1norm = 5984.0525
determinant = 7.1087467e+008
reciprocal_condition_number = 0.013826504
vif = [1.001, 1.001]
names = 'date residual leverage influence DFFITS'.split()
cur_dir = os.path.abspath(os.path.dirname(__file__))
fpath = os.path.join(cur_dir, 'results/leverage_influence_ols_nostars.txt')
lev = np.genfromtxt(fpath, skip_header=3, skip_footer=1,
converters={0:lambda s: s})
#either numpy 1.6 or python 3.2 changed behavior
if np.isnan(lev[-1]['f1']):
lev = np.genfromtxt(fpath, skip_header=3, skip_footer=2,
converters={0:lambda s: s})
lev.dtype.names = names
res = res_ols #for easier copying
cov_hac = sw.cov_hac_simple(res, nlags=4, use_correction=False)
bse_hac = sw.se_cov(cov_hac)
assert_almost_equal(res.params, partable[:,0], 5)
assert_almost_equal(bse_hac, partable[:,1], 5)
#TODO
assert_almost_equal(res.ssr, result_gretl_g1['ssr'][1], decimal=2)
#assert_almost_equal(res.llf, result_gretl_g1['llf'][1], decimal=7) #not in gretl
assert_almost_equal(res.rsquared, result_gretl_g1['rsquared'][1], decimal=6) #FAIL
assert_almost_equal(res.rsquared_adj, result_gretl_g1['rsquared_adj'][1], decimal=6) #FAIL
assert_almost_equal(np.sqrt(res.mse_resid), result_gretl_g1['mse_resid_sqrt'][1], decimal=5)
#f-value is based on cov_hac I guess
#assert_almost_equal(res.fvalue, result_gretl_g1['fvalue'][1], decimal=0) #FAIL
#assert_approx_equal(res.f_pvalue, result_gretl_g1['f_pvalue'][1], significant=1) #FAIL
#assert_almost_equal(res.durbin_watson, result_gretl_g1['dw'][1], decimal=7) #TODO
c = oi.reset_ramsey(res, degree=2)
compare_ftest(c, reset_2, decimal=(6,5))
c = oi.reset_ramsey(res, degree=3)
compare_ftest(c, reset_2_3, decimal=(6,5))
linear_sq = smsdia.linear_lm(res.resid, res.model.exog)
assert_almost_equal(linear_sq[0], linear_squares[0], decimal=6)
assert_almost_equal(linear_sq[1], linear_squares[1], decimal=7)
hbpk = smsdia.het_breushpagan(res.resid, res.model.exog)
assert_almost_equal(hbpk[0], het_breush_pagan_konker[0], decimal=6)
assert_almost_equal(hbpk[1], het_breush_pagan_konker[1], decimal=6)
hw = smsdia.het_white(res.resid, res.model.exog)
assert_almost_equal(hw[:2], het_white[:2], 6)
#arch
#sm_arch = smsdia.acorr_lm(res.resid**2, maxlag=4, autolag=None)
sm_arch = smsdia.het_arch(res.resid, maxlag=4)
assert_almost_equal(sm_arch[0], arch_4[0], decimal=5)
assert_almost_equal(sm_arch[1], arch_4[1], decimal=6)
vif2 = [oi.variance_inflation_factor(res.model.exog, k) for k in [1,2]]
infl = oi.OLSInfluence(res_ols)
#print np.max(np.abs(lev['DFFITS'] - infl.dffits[0]))
#print np.max(np.abs(lev['leverage'] - infl.hat_matrix_diag))
#print np.max(np.abs(lev['influence'] - infl.influence)) #just added this based on Gretl
#just rough test, low decimal in Gretl output,
assert_almost_equal(lev['residual'], res.resid, decimal=3)
assert_almost_equal(lev['DFFITS'], infl.dffits[0], decimal=3)
assert_almost_equal(lev['leverage'], infl.hat_matrix_diag, decimal=3)
assert_almost_equal(lev['influence'], infl.influence, decimal=4)
group = pet[:,0].astype(int)
time = pet[:,1].astype(int)
exog = sm.add_constant(pet[:,2])
res = sm.OLS(endog, exog).fit()
cov01, covg, covt = sw.cov_cluster_2groups(res, group, group2=time)
#Reference number from Petersen
#http://www.kellogg.northwestern.edu/faculty/petersen/htm/papers/se/test_data.htm
bse_petw = [0.0284, 0.0284]
bse_pet0 = [0.0670, 0.0506]
bse_pet1 = [0.0234, 0.0334] #year
bse_pet01 = [0.0651, 0.0536] #firm and year
bse_0 = sw.se_cov(covg)
bse_1 = sw.se_cov(covt)
bse_01 = sw.se_cov(cov01)
print('OLS ', res.bse)
print('het HC0 ', res.HC0_se, bse_petw - res.HC0_se)
print('het firm ', bse_0, bse_0 - bse_pet0)
print('het year ', bse_1, bse_1 - bse_pet1)
print('het firm & year', bse_01, bse_01 - bse_pet01)
print('relative difference standard error het firm & year to OLS')
print(' ', bse_01 / res.bse)
#From the last line we see that the cluster and year robust standard errors
#are approximately twice those of OLS
def test_all(self):
d = macrodata.load().data
#import datasetswsm.greene as g
#d = g.load('5-1')
#growth rates
gs_l_realinv = 400 * np.diff(np.log(d['realinv']))
gs_l_realgdp = 400 * np.diff(np.log(d['realgdp']))
#simple diff, not growthrate, I want heteroscedasticity later for testing
endogd = np.diff(d['realinv'])
exogd = add_constant(np.c_[np.diff(d['realgdp']), d['realint'][:-1]])
endogg = gs_l_realinv
exogg = add_constant(np.c_[gs_l_realgdp, d['realint'][:-1]])
res_ols = OLS(endogg, exogg).fit()
#print res_ols.params
mod_g1 = GLSAR(endogg, exogg, rho=-0.108136)
res_g1 = mod_g1.fit()
#print res_g1.params
mod_g2 = GLSAR(endogg, exogg, rho=-0.108136) #-0.1335859) from R
res_g2 = mod_g2.iterative_fit(maxiter=5)
#print res_g2.params
rho = -0.108136
# coefficient std. error t-ratio p-value 95% CONFIDENCE INTERVAL
partable = np.array([
[-9.50990, 0.990456, -9.602, 3.65e-018, -11.4631, -7.55670], # ***
[ 4.37040, 0.208146, 21.00, 2.93e-052, 3.95993, 4.78086], # ***
[-0.579253, 0.268009, -2.161, 0.0319, -1.10777, -0.0507346]]) # **
#Statistics based on the rho-differenced data:
result_gretl_g1 = dict(
endog_mean = ("Mean dependent var", 3.113973),
endog_std = ("S.D. dependent var", 18.67447),
ssr = ("Sum squared resid", 22530.90),
mse_resid_sqrt = ("S.E. of regression", 10.66735),
rsquared = ("R-squared", 0.676973),
rsquared_adj = ("Adjusted R-squared", 0.673710),
fvalue = ("F(2, 198)", 221.0475),
f_pvalue = ("P-value(F)", 3.56e-51),
resid_acf1 = ("rho", -0.003481),
dw = ("Durbin-Watson", 1.993858))
#fstatistic, p-value, df1, df2
reset_2_3 = [5.219019, 0.00619, 2, 197, "f"]
reset_2 = [7.268492, 0.00762, 1, 198, "f"]
reset_3 = [5.248951, 0.023, 1, 198, "f"]
#LM-statistic, p-value, df
arch_4 = [7.30776, 0.120491, 4, "chi2"]
#multicollinearity
vif = [1.002, 1.002]
cond_1norm = 6862.0664
determinant = 1.0296049e+009
reciprocal_condition_number = 0.013819244
#Chi-square(2): test-statistic, pvalue, df
normality = [20.2792, 3.94837e-005, 2]
#tests
res = res_g1 #with rho from Gretl
#basic
assert_almost_equal(res.params, partable[:,0], 4)
assert_almost_equal(res.bse, partable[:,1], 6)
assert_almost_equal(res.tvalues, partable[:,2], 2)
assert_almost_equal(res.ssr, result_gretl_g1['ssr'][1], decimal=2)
#assert_almost_equal(res.llf, result_gretl_g1['llf'][1], decimal=7) #not in gretl
#assert_almost_equal(res.rsquared, result_gretl_g1['rsquared'][1], decimal=7) #FAIL
#assert_almost_equal(res.rsquared_adj, result_gretl_g1['rsquared_adj'][1], decimal=7) #FAIL
assert_almost_equal(np.sqrt(res.mse_resid), result_gretl_g1['mse_resid_sqrt'][1], decimal=5)
assert_almost_equal(res.fvalue, result_gretl_g1['fvalue'][1], decimal=4)
assert_approx_equal(res.f_pvalue, result_gretl_g1['f_pvalue'][1], significant=2)
#assert_almost_equal(res.durbin_watson, result_gretl_g1['dw'][1], decimal=7) #TODO
#arch
#sm_arch = smsdia.acorr_lm(res.wresid**2, maxlag=4, autolag=None)
sm_arch = smsdia.het_arch(res.wresid, maxlag=4)
assert_almost_equal(sm_arch[0], arch_4[0], decimal=4)
assert_almost_equal(sm_arch[1], arch_4[1], decimal=6)
#tests
res = res_g2 #with estimated rho
#estimated lag coefficient
assert_almost_equal(res.model.rho, rho, decimal=3)
#basic
assert_almost_equal(res.params, partable[:,0], 4)
assert_almost_equal(res.bse, partable[:,1], 3)
assert_almost_equal(res.tvalues, partable[:,2], 2)
assert_almost_equal(res.ssr, result_gretl_g1['ssr'][1], decimal=2)
#assert_almost_equal(res.llf, result_gretl_g1['llf'][1], decimal=7) #not in gretl
#assert_almost_equal(res.rsquared, result_gretl_g1['rsquared'][1], decimal=7) #FAIL
#assert_almost_equal(res.rsquared_adj, result_gretl_g1['rsquared_adj'][1], decimal=7) #FAIL
assert_almost_equal(np.sqrt(res.mse_resid), result_gretl_g1['mse_resid_sqrt'][1], decimal=5)
assert_almost_equal(res.fvalue, result_gretl_g1['fvalue'][1], decimal=0)
assert_almost_equal(res.f_pvalue, result_gretl_g1['f_pvalue'][1], decimal=6)
#assert_almost_equal(res.durbin_watson, result_gretl_g1['dw'][1], decimal=7) #TODO
c = oi.reset_ramsey(res, degree=2)
compare_ftest(c, reset_2, decimal=(2,4))
c = oi.reset_ramsey(res, degree=3)
compare_ftest(c, reset_2_3, decimal=(2,4))
#arch
#sm_arch = smsdia.acorr_lm(res.wresid**2, maxlag=4, autolag=None)
sm_arch = smsdia.het_arch(res.wresid, maxlag=4)
assert_almost_equal(sm_arch[0], arch_4[0], decimal=1)
assert_almost_equal(sm_arch[1], arch_4[1], decimal=2)
'''
Performing iterative calculation of rho...
ITER RHO ESS
1 -0.10734 22530.9
2 -0.10814 22530.9
Model 4: Cochrane-Orcutt, using observations 1959:3-2009:3 (T = 201)
Dependent variable: ds_l_realinv
rho = -0.108136
coefficient std. error t-ratio p-value
-------------------------------------------------------------
const -9.50990 0.990456 -9.602 3.65e-018 ***
ds_l_realgdp 4.37040 0.208146 21.00 2.93e-052 ***
realint_1 -0.579253 0.268009 -2.161 0.0319 **
Statistics based on the rho-differenced data:
Mean dependent var 3.113973 S.D. dependent var 18.67447
Sum squared resid 22530.90 S.E. of regression 10.66735
R-squared 0.676973 Adjusted R-squared 0.673710
F(2, 198) 221.0475 P-value(F) 3.56e-51
rho -0.003481 Durbin-Watson 1.993858
'''
'''
RESET test for specification (squares and cubes)
Test statistic: F = 5.219019,
with p-value = P(F(2,197) > 5.21902) = 0.00619
RESET test for specification (squares only)
Test statistic: F = 7.268492,
with p-value = P(F(1,198) > 7.26849) = 0.00762
RESET test for specification (cubes only)
Test statistic: F = 5.248951,
with p-value = P(F(1,198) > 5.24895) = 0.023:
'''
'''
Test for ARCH of order 4
coefficient std. error t-ratio p-value
--------------------------------------------------------
alpha(0) 97.0386 20.3234 4.775 3.56e-06 ***
alpha(1) 0.176114 0.0714698 2.464 0.0146 **
alpha(2) -0.0488339 0.0724981 -0.6736 0.5014
alpha(3) -0.0705413 0.0737058 -0.9571 0.3397
alpha(4) 0.0384531 0.0725763 0.5298 0.5968
Null hypothesis: no ARCH effect is present
Test statistic: LM = 7.30776
with p-value = P(Chi-square(4) > 7.30776) = 0.120491:
'''
'''
Variance Inflation Factors
Minimum possible value = 1.0
Values > 10.0 may indicate a collinearity problem
ds_l_realgdp 1.002
realint_1 1.002
VIF(j) = 1/(1 - R(j)^2), where R(j) is the multiple correlation coefficient
between variable j and the other independent variables
Properties of matrix X'X:
1-norm = 6862.0664
Determinant = 1.0296049e+009
Reciprocal condition number = 0.013819244
'''
'''
Test for ARCH of order 4 -
Null hypothesis: no ARCH effect is present
Test statistic: LM = 7.30776
with p-value = P(Chi-square(4) > 7.30776) = 0.120491
Test of common factor restriction -
Null hypothesis: restriction is acceptable
Test statistic: F(2, 195) = 0.426391
with p-value = P(F(2, 195) > 0.426391) = 0.653468
Test for normality of residual -
Null hypothesis: error is normally distributed
Test statistic: Chi-square(2) = 20.2792
with p-value = 3.94837e-005:
'''
#no idea what this is
'''
Augmented regression for common factor test
OLS, using observations 1959:3-2009:3 (T = 201)
Dependent variable: ds_l_realinv
coefficient std. error t-ratio p-value
---------------------------------------------------------------
const -10.9481 1.35807 -8.062 7.44e-014 ***
ds_l_realgdp 4.28893 0.229459 18.69 2.40e-045 ***
realint_1 -0.662644 0.334872 -1.979 0.0492 **
ds_l_realinv_1 -0.108892 0.0715042 -1.523 0.1294
ds_l_realgdp_1 0.660443 0.390372 1.692 0.0923 *
realint_2 0.0769695 0.341527 0.2254 0.8219
Sum of squared residuals = 22432.8
Test of common factor restriction
Test statistic: F(2, 195) = 0.426391, with p-value = 0.653468
'''
################ with OLS, HAC errors
#Model 5: OLS, using observations 1959:2-2009:3 (T = 202)
#Dependent variable: ds_l_realinv
#HAC standard errors, bandwidth 4 (Bartlett kernel)
#coefficient std. error t-ratio p-value 95% CONFIDENCE INTERVAL
#for confidence interval t(199, 0.025) = 1.972
partable = np.array([
[-9.48167, 1.17709, -8.055, 7.17e-014, -11.8029, -7.16049], # ***
[4.37422, 0.328787, 13.30, 2.62e-029, 3.72587, 5.02258], #***
[-0.613997, 0.293619, -2.091, 0.0378, -1.19300, -0.0349939]]) # **
result_gretl_g1 = dict(
endog_mean = ("Mean dependent var", 3.257395),
endog_std = ("S.D. dependent var", 18.73915),
ssr = ("Sum squared resid", 22799.68),
mse_resid_sqrt = ("S.E. of regression", 10.70380),
rsquared = ("R-squared", 0.676978),
rsquared_adj = ("Adjusted R-squared", 0.673731),
fvalue = ("F(2, 199)", 90.79971),
f_pvalue = ("P-value(F)", 9.53e-29),
llf = ("Log-likelihood", -763.9752),
aic = ("Akaike criterion", 1533.950),
bic = ("Schwarz criterion", 1543.875),
hqic = ("Hannan-Quinn", 1537.966),
resid_acf1 = ("rho", -0.107341),
dw = ("Durbin-Watson", 2.213805))
linear_logs = [1.68351, 0.430953, 2, "chi2"]
#for logs: dropping 70 nan or incomplete observations, T=133
#(res_ols.model.exog <=0).any(1).sum() = 69 ?not 70
linear_squares = [7.52477, 0.0232283, 2, "chi2"]
#Autocorrelation, Breusch-Godfrey test for autocorrelation up to order 4
lm_acorr4 = [1.17928, 0.321197, 4, 195, "F"]
lm2_acorr4 = [4.771043, 0.312, 4, "chi2"]
acorr_ljungbox4 = [5.23587, 0.264, 4, "chi2"]
#break
cusum_Harvey_Collier = [0.494432, 0.621549, 198, "t"] #stats.t.sf(0.494432, 198)*2
#see cusum results in files
break_qlr = [3.01985, 0.1, 3, 196, "maxF"] #TODO check this, max at 2001:4
break_chow = [13.1897, 0.00424384, 3, "chi2"] # break at 1984:1
arch_4 = [3.43473, 0.487871, 4, "chi2"]
normality = [23.962, 0.00001, 2, "chi2"]
het_white = [33.503723, 0.000003, 5, "chi2"]
het_breusch_pagan = [1.302014, 0.521520, 2, "chi2"] #TODO: not available
het_breusch_pagan_konker = [0.709924, 0.701200, 2, "chi2"]
reset_2_3 = [5.219019, 0.00619, 2, 197, "f"]
reset_2 = [7.268492, 0.00762, 1, 198, "f"]
reset_3 = [5.248951, 0.023, 1, 198, "f"] #not available
cond_1norm = 5984.0525
determinant = 7.1087467e+008
reciprocal_condition_number = 0.013826504
vif = [1.001, 1.001]
names = 'date residual leverage influence DFFITS'.split()
cur_dir = os.path.abspath(os.path.dirname(__file__))
fpath = os.path.join(cur_dir, 'results/leverage_influence_ols_nostars.txt')
lev = np.genfromtxt(fpath, skip_header=3, skip_footer=1,
converters={0:lambda s: s})
#either numpy 1.6 or python 3.2 changed behavior
if np.isnan(lev[-1]['f1']):
lev = np.genfromtxt(fpath, skip_header=3, skip_footer=2,
converters={0:lambda s: s})
lev.dtype.names = names
res = res_ols #for easier copying
cov_hac = sw.cov_hac_simple(res, nlags=4, use_correction=False)
bse_hac = sw.se_cov(cov_hac)
assert_almost_equal(res.params, partable[:,0], 5)
assert_almost_equal(bse_hac, partable[:,1], 5)
#TODO
assert_almost_equal(res.ssr, result_gretl_g1['ssr'][1], decimal=2)
assert_almost_equal(res.llf, result_gretl_g1['llf'][1], decimal=4) #not in gretl
assert_almost_equal(res.rsquared, result_gretl_g1['rsquared'][1], decimal=6) #FAIL
assert_almost_equal(res.rsquared_adj, result_gretl_g1['rsquared_adj'][1], decimal=6) #FAIL
assert_almost_equal(np.sqrt(res.mse_resid), result_gretl_g1['mse_resid_sqrt'][1], decimal=5)
#f-value is based on cov_hac I guess
#res2 = res.get_robustcov_results(cov_type='HC1')
# TODO: fvalue differs from Gretl, trying any of the HCx
#assert_almost_equal(res2.fvalue, result_gretl_g1['fvalue'][1], decimal=0) #FAIL
#assert_approx_equal(res.f_pvalue, result_gretl_g1['f_pvalue'][1], significant=1) #FAIL
#assert_almost_equal(res.durbin_watson, result_gretl_g1['dw'][1], decimal=7) #TODO
c = oi.reset_ramsey(res, degree=2)
compare_ftest(c, reset_2, decimal=(6,5))
c = oi.reset_ramsey(res, degree=3)
compare_ftest(c, reset_2_3, decimal=(6,5))
linear_sq = smsdia.linear_lm(res.resid, res.model.exog)
assert_almost_equal(linear_sq[0], linear_squares[0], decimal=6)
assert_almost_equal(linear_sq[1], linear_squares[1], decimal=7)
hbpk = smsdia.het_breuschpagan(res.resid, res.model.exog)
assert_almost_equal(hbpk[0], het_breusch_pagan_konker[0], decimal=6)
assert_almost_equal(hbpk[1], het_breusch_pagan_konker[1], decimal=6)
hw = smsdia.het_white(res.resid, res.model.exog)
assert_almost_equal(hw[:2], het_white[:2], 6)
#arch
#sm_arch = smsdia.acorr_lm(res.resid**2, maxlag=4, autolag=None)
sm_arch = smsdia.het_arch(res.resid, maxlag=4)
assert_almost_equal(sm_arch[0], arch_4[0], decimal=5)
assert_almost_equal(sm_arch[1], arch_4[1], decimal=6)
vif2 = [oi.variance_inflation_factor(res.model.exog, k) for k in [1,2]]
infl = oi.OLSInfluence(res_ols)
#print np.max(np.abs(lev['DFFITS'] - infl.dffits[0]))
#print np.max(np.abs(lev['leverage'] - infl.hat_matrix_diag))
#print np.max(np.abs(lev['influence'] - infl.influence)) #just added this based on Gretl
#just rough test, low decimal in Gretl output,
assert_almost_equal(lev['residual'], res.resid, decimal=3)
assert_almost_equal(lev['DFFITS'], infl.dffits[0], decimal=3)
assert_almost_equal(lev['leverage'], infl.hat_matrix_diag, decimal=3)
assert_almost_equal(lev['influence'], infl.influence, decimal=4)
mask = (xx!=-999.0).all(1) #nan code in dta file
mask.shape
y = y[mask]
xx = xx[mask]
group = group[mask]
#run OLS
res_srs = sm.OLS(y, xx).fit()
print 'params ', res_srs.params
print 'bse_OLS ', res_srs.bse
#get cluster robust standard errors and compare with STATA
cov_cr = sw.cov_cluster(res_srs, group.astype(int))
bse_cr = sw.se_cov(cov_cr)
print 'bse_rob ', bse_cr
res_stata = np.rec.array(
[ ('growth', '|', -0.1027121, 0.22917029999999999, -0.45000000000000001, 0.65500000000000003, -0.55483519999999997, 0.34941109999999997),
('emer', '|', -5.4449319999999997, 0.72939690000000001, -7.46, 0.0, -6.8839379999999997, -4.0059269999999998),
('yr_rnd', '|', -51.075690000000002, 22.83615, -2.2400000000000002, 0.027, -96.128439999999998, -6.0229350000000004),
('_cons', '|', 740.3981, 13.460760000000001, 55.0, 0.0, 713.84180000000003, 766.95439999999996)],
dtype=[('exogname', '|S6'), ('del', '|S1'), ('params', '<f8'),
('bse', '<f8'), ('tvalues', '<f8'), ('pvalues', '<f8'),
('cilow', '<f8'), ('ciupp', '<f8')])
print 'diff Stata', bse_cr - res_stata.bse
assert_almost_equal(bse_cr, res_stata.bse, decimal=6)
#We see that in this case the robust standard errors of the parameter estimates
#import statsmodels.sandbox.panel.sandwich_covariance_generic as swg nobs = 100 kvars = 4 #including constant x = np.random.randn(nobs, kvars-1) exog = sm.add_constant(x, prepend=True) params_true = np.ones(kvars) y_true = np.dot(exog, params_true) sigma = 0.1 + np.exp(exog[:,-1]) endog = y_true + sigma * np.random.randn(nobs) self = sm.OLS(endog, exog).fit() print self.HC3_se print sw.se_cov(sw.cov_hc3(self)) #test standalone refactoring assert_almost_equal(sw.se_cov(sw.cov_hc0(self)), self.HC0_se, 15) assert_almost_equal(sw.se_cov(sw.cov_hc1(self)), self.HC1_se, 15) assert_almost_equal(sw.se_cov(sw.cov_hc2(self)), self.HC2_se, 15) assert_almost_equal(sw.se_cov(sw.cov_hc3(self)), self.HC3_se, 15) print self.HC0_se print sw.se_cov(sw.cov_hac_simple(self, nlags=0, use_correction=False)) #test White as HAC with nlags=0, same as nlags=1 ? bse_hac0 = sw.se_cov(sw.cov_hac_simple(self, nlags=0, use_correction=False)) assert_almost_equal(bse_hac0, self.HC0_se, 15) print bse_hac0 #test White as HAC with nlags=0, same as nlags=1 ? bse_hac0c = sw.se_cov(sw.cov_hac_simple(self, nlags=0, use_correction=True)) assert_almost_equal(bse_hac0c, self.HC1_se, 15)
# res.resid is of transformed model
# np.corrcoef(res.resid.reshape(-1,n_groups, order='F'))
y_pred = np.dot(mod.exog, res.params)
resid = y - y_pred
print np.corrcoef(resid.reshape(-1, n_groups, order="F"))
print resid.std()
err = y_pred - dgp.y_true
print err.std()
# OLS standard errors are too small
mod.res_pooled.params
mod.res_pooled.bse
# heteroscedasticity robust doesn't help
mod.res_pooled.HC1_se
# compare with cluster robust se
print sw.se_cov(sw.cov_cluster(mod.res_pooled, dgp.groups.astype(int)))
# not bad, pretty close to panel estimator
# and with Newey-West Hac
print sw.se_cov(sw.cov_nw_panel(mod.res_pooled, 4, mod.group.groupidx))
# too small, assuming no bugs,
# see Peterson assuming it refers to same kind of model
print dgp.cov
mod2 = ShortPanelGLS(y, dgp.exog, dgp.groups)
res2 = mod2.fit_iterative(2)
print res2.params
print res2.bse
# both implementations produce the same results:
from numpy.testing import assert_almost_equal
assert_almost_equal(res.params, res2.params, decimal=12)
#res.resid is of transformed model
#np.corrcoef(res.resid.reshape(-1,n_groups, order='F'))
y_pred = np.dot(mod.exog, res.params)
resid = y - y_pred
print(np.corrcoef(resid.reshape(-1, n_groups, order='F')))
print(resid.std())
err = y_pred - dgp.y_true
print(err.std())
#OLS standard errors are too small
mod.res_pooled.params
mod.res_pooled.bse
#heteroscedasticity robust doesn't help
mod.res_pooled.HC1_se
#compare with cluster robust se
print(sw.se_cov(sw.cov_cluster(mod.res_pooled, dgp.groups.astype(int))))
#not bad, pretty close to panel estimator
#and with Newey-West Hac
print(sw.se_cov(sw.cov_nw_panel(mod.res_pooled, 4, mod.group.groupidx)))
#too small, assuming no bugs,
#see Peterson assuming it refers to same kind of model
print(dgp.cov)
mod2 = ShortPanelGLS(y, dgp.exog, dgp.groups)
res2 = mod2.fit_iterative(2)
print(res2.params)
print(res2.bse)
#both implementations produce the same results:
from numpy.testing import assert_almost_equal
assert_almost_equal(res.params, res2.params, decimal=12)
assert_almost_equal(res.bse, res2.bse, decimal=13)
def get_robust_clu(cls):
res1 = cls.res1
cov_clu = sw.cov_cluster(res1, group)
cls.bse_rob = sw.se_cov(cov_clu)
cls.corr_fact = cls.get_correction_factor(res1)
