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(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_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 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 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 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)
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) bse_w = sw.se_cov(sw.cov_white_simple(self, use_correction=False)) print bse_w #test White assert_almost_equal(bse_w, self.HC0_se, 15) bse_wc = sw.se_cov(sw.cov_white_simple(self, use_correction=True)) print bse_wc
def get_robustcov_results(self, cov_type='HC1', use_t=None, **kwds):
"""create new results instance with robust covariance as default
Parameters
----------
cov_type : string
the type of robust sandwich estimator to use. see Notes below
use_t : bool
If true, then the t distribution is used for inference.
If false, then the normal distribution is used.
kwds : depends on cov_type
Required or optional arguments for robust covariance calculation.
see Notes below
Returns
-------
results : results instance
This method creates a new results instance with the requested
robust covariance as the default covariance of the parameters.
Inferential statistics like p-values and hypothesis tests will be
based on this covariance matrix.
Notes
-----
Warning: Some of the options and defaults in cov_kwds may be changed in a
future version.
The covariance keywords provide an option 'scaling_factor' to adjust the
scaling of the covariance matrix, that is the covariance is multiplied by
this factor if it is given and is not `None`. This allows the user to
adjust the scaling of the covariance matrix to match other statistical
packages.
For example, `scaling_factor=(nobs - 1.) / (nobs - k_params)` provides a
correction so that the robust covariance matrices match those of Stata in
some models like GLM and discrete Models.
The following covariance types and required or optional arguments are
currently available:
- 'HC0', 'HC1', 'HC2', 'HC3' and no keyword arguments:
heteroscedasticity robust covariance
- 'HAC' and keywords
- `maxlag` integer (required) : number of lags to use
- `kernel` string (optional) : kernel, default is Bartlett
- `use_correction` bool (optional) : If true, use small sample
correction
- 'cluster' and required keyword `groups`, integer group indicator
- `groups` array_like, integer (required) :
index of clusters or groups
- `use_correction` bool (optional) :
If True the sandwich covariance is calulated with a small
sample correction.
If False the the sandwich covariance is calulated without
small sample correction.
- `df_correction` bool (optional)
If True (default), then the degrees of freedom for the
inferential statistics and hypothesis tests, such as
pvalues, f_pvalue, conf_int, and t_test and f_test, are
based on the number of groups minus one instead of the
total number of observations minus the number of explanatory
variables. `df_resid` of the results instance is adjusted.
If False, then `df_resid` of the results instance is not
adjusted.
- 'hac-groupsum' Driscoll and Kraay, heteroscedasticity and
autocorrelation robust standard errors in panel data
keywords
- `time` array_like (required) : index of time periods
- `maxlag` integer (required) : number of lags to use
- `kernel` string (optional) : kernel, default is Bartlett
- `use_correction` False or string in ['hac', 'cluster'] (optional) :
If False the the sandwich covariance is calulated without
small sample correction.
If `use_correction = 'cluster'` (default), then the same
small sample correction as in the case of 'covtype='cluster''
is used.
- `df_correction` bool (optional)
adjustment to df_resid, see cov_type 'cluster' above
#TODO: we need more options here
- 'hac-panel' heteroscedasticity and autocorrelation robust standard
errors in panel data.
The data needs to be sorted in this case, the time series for
each panel unit or cluster need to be stacked. The membership to
a timeseries of an individual or group can be either specified by
group indicators or by increasing time periods.
keywords
- either `groups` or `time` : array_like (required)
`groups` : indicator for groups
`time` : index of time periods
- `maxlag` integer (required) : number of lags to use
- `kernel` string (optional) : kernel, default is Bartlett
- `use_correction` False or string in ['hac', 'cluster'] (optional) :
If False the the sandwich covariance is calulated without
small sample correction.
- `df_correction` bool (optional)
adjustment to df_resid, see cov_type 'cluster' above
#TODO: we need more options here
Reminder:
`use_correction` in "hac-groupsum" and "hac-panel" is not bool,
needs to be in [False, 'hac', 'cluster']
TODO: Currently there is no check for extra or misspelled keywords,
except in the case of cov_type `HCx`
"""
import statsmodels.stats.sandwich_covariance as sw
#normalize names
if cov_type == 'nw-panel':
cov_type = 'hac-panel'
if cov_type == 'nw-groupsum':
cov_type = 'hac-groupsum'
if 'kernel' in kwds:
kwds['weights_func'] = kwds.pop('kernel')
# pop because HCx raises if any kwds
sc_factor = kwds.pop('scaling_factor', None)
# TODO: make separate function that returns a robust cov plus info
use_self = kwds.pop('use_self', False)
if use_self:
res = self
else:
# this doesn't work for most models, use raw instance instead from fit
res = self.__class__(self.model, self.params,
normalized_cov_params=self.normalized_cov_params,
scale=self.scale)
res.cov_type = cov_type
# use_t might already be defined by the class, and already set
if use_t is None:
use_t = self.use_t
res.cov_kwds = {'use_t':use_t} # store for information
res.use_t = use_t
adjust_df = False
if cov_type in ['cluster', 'hac-panel', 'hac-groupsum']:
df_correction = kwds.get('df_correction', None)
# TODO: check also use_correction, do I need all combinations?
if df_correction is not False: # i.e. in [None, True]:
# user didn't explicitely set it to False
adjust_df = True
res.cov_kwds['adjust_df'] = adjust_df
# verify and set kwds, and calculate cov
# TODO: this should be outsourced in a function so we can reuse it in
# other models
# TODO: make it DRYer repeated code for checking kwds
if cov_type.upper() in ('HC0', 'HC1', 'HC2', 'HC3'):
if kwds:
raise ValueError('heteroscedasticity robust covarians ' +
'does not use keywords')
res.cov_kwds['description'] = ('Standard Errors are heteroscedasticity ' +
'robust ' + '(' + cov_type + ')')
res.cov_params_default = getattr(self, 'cov_' + cov_type.upper(), None)
if res.cov_params_default is None:
# results classes that don't have cov_HCx attribute
res.cov_params_default = sw.cov_white_simple(self,
use_correction=False)
elif cov_type.lower() == 'hac':
maxlags = kwds['maxlags'] # required?, default in cov_hac_simple
res.cov_kwds['maxlags'] = maxlags
weights_func = kwds.get('weights_func', sw.weights_bartlett)
res.cov_kwds['weights_func'] = weights_func
use_correction = kwds.get('use_correction', False)
res.cov_kwds['use_correction'] = use_correction
res.cov_kwds['description'] = ('Standard Errors are heteroscedasticity ' +
'and autocorrelation robust (HAC) using %d lags and %s small ' +
'sample correction') % (maxlags, ['without', 'with'][use_correction])
res.cov_params_default = sw.cov_hac_simple(self, nlags=maxlags,
weights_func=weights_func,
use_correction=use_correction)
elif cov_type.lower() == 'cluster':
#cluster robust standard errors, one- or two-way
groups = kwds['groups']
if not hasattr(groups, 'shape'):
groups = np.asarray(groups).T
if groups.ndim >= 2:
groups = groups.squeeze()
res.cov_kwds['groups'] = groups
use_correction = kwds.get('use_correction', True)
res.cov_kwds['use_correction'] = use_correction
if groups.ndim == 1:
if adjust_df:
# need to find number of groups
# duplicate work
self.n_groups = n_groups = len(np.unique(groups))
res.cov_params_default = sw.cov_cluster(self, groups,
use_correction=use_correction)
elif groups.ndim == 2:
if hasattr(groups, 'values'):
groups = groups.values
if adjust_df:
# need to find number of groups
# duplicate work
n_groups0 = len(np.unique(groups[:,0]))
n_groups1 = len(np.unique(groups[:, 1]))
self.n_groups = (n_groups0, n_groups1)
n_groups = min(n_groups0, n_groups1) # use for adjust_df
# Note: sw.cov_cluster_2groups has 3 returns
res.cov_params_default = sw.cov_cluster_2groups(self, groups,
use_correction=use_correction)[0]
else:
raise ValueError('only two groups are supported')
res.cov_kwds['description'] = ('Standard Errors are robust to' +
'cluster correlation ' + '(' + cov_type + ')')
elif cov_type.lower() == 'hac-panel':
#cluster robust standard errors
res.cov_kwds['time'] = time = kwds.get('time', None)
res.cov_kwds['groups'] = groups = kwds.get('groups', None)
#TODO: nlags is currently required
#nlags = kwds.get('nlags', True)
#res.cov_kwds['nlags'] = nlags
#TODO: `nlags` or `maxlags`
res.cov_kwds['maxlags'] = maxlags = kwds['maxlags']
use_correction = kwds.get('use_correction', 'hac')
res.cov_kwds['use_correction'] = use_correction
weights_func = kwds.get('weights_func', sw.weights_bartlett)
res.cov_kwds['weights_func'] = weights_func
# TODO: clumsy time index in cov_nw_panel
if groups is not None:
groups = np.asarray(groups)
tt = (np.nonzero(groups[:-1] != groups[1:])[0] + 1).tolist()
nobs_ = len(groups)
elif time is not None:
# TODO: clumsy time index in cov_nw_panel
time = np.asarray(time)
tt = (np.nonzero(time[1:] < time[:-1])[0] + 1).tolist()
nobs_ = len(time)
else:
raise ValueError('either time or groups needs to be given')
groupidx = lzip([0] + tt, tt + [nobs_])
self.n_groups = n_groups = len(groupidx)
res.cov_params_default = sw.cov_nw_panel(self, maxlags, groupidx,
weights_func=weights_func,
use_correction=use_correction)
res.cov_kwds['description'] = ('Standard Errors are robust to' +
'cluster correlation ' + '(' + cov_type + ')')
elif cov_type.lower() == 'hac-groupsum':
# Driscoll-Kraay standard errors
res.cov_kwds['time'] = time = kwds['time']
#TODO: nlags is currently required
#nlags = kwds.get('nlags', True)
#res.cov_kwds['nlags'] = nlags
#TODO: `nlags` or `maxlags`
res.cov_kwds['maxlags'] = maxlags = kwds['maxlags']
use_correction = kwds.get('use_correction', 'cluster')
res.cov_kwds['use_correction'] = use_correction
weights_func = kwds.get('weights_func', sw.weights_bartlett)
res.cov_kwds['weights_func'] = weights_func
if adjust_df:
# need to find number of groups
tt = (np.nonzero(time[1:] < time[:-1])[0] + 1)
self.n_groups = n_groups = len(tt) + 1
res.cov_params_default = sw.cov_nw_groupsum(self, maxlags, time,
weights_func=weights_func,
use_correction=use_correction)
res.cov_kwds['description'] = (
'Driscoll and Kraay Standard Errors are robust to ' +
'cluster correlation ' + '(' + cov_type + ')')
else:
raise ValueError('cov_type not recognized. See docstring for ' +
'available options and spelling')
# generic optional factor to scale covariance
res.cov_kwds['scaling_factor'] = sc_factor
if sc_factor is not None:
res.cov_params_default *= sc_factor
if adjust_df:
# Note: df_resid is used for scale and others, add new attribute
res.df_resid_inference = n_groups - 1
return res
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)
