def test_het_arch(self):
# test het_arch and indirectly het_lm against R
# > library(FinTS)
# > at = ArchTest(residuals(fm), lags=4)
# > mkhtest(at, 'archtest_4', 'chi2')
archtest_4 = dict(statistic=3.43473400836259, pvalue=0.487871315392619, parameters=(4,), distr="chi2")
# > at = ArchTest(residuals(fm), lags=12)
# > mkhtest(at, 'archtest_12', 'chi2')
archtest_12 = dict(statistic=8.648320999014171, pvalue=0.732638635007718, parameters=(12,), distr="chi2")
at4 = smsdia.het_arch(self.res.resid, maxlag=4)
at12 = smsdia.het_arch(self.res.resid, maxlag=12)
compare_t_est(at4[:2], archtest_4, decimal=(12, 13))
compare_t_est(at12[:2], archtest_12, decimal=(12, 13))
def engle_test_resid(series, order = (1,1)):
model = smt.ARMA(series, order=order).fit(method='mle', trend='nc')
p_val = het_arch(model.resid)[1]
print(series.name + ' p-value Engle: ' + str(p_val))
with open(os.getcwd() + '/model_results/ARMA_'+ series.name + '.tex', "w") as text_file:
text_file.write(model.summary().as_latex())
return p_val
def MF_GARCHFit(y,preproc = None,P = 1,Q = 1):
y = (y - np.mean(y)) / np.std(y)
N = len(y)
outDict = {}
lm, lmpval,fval,fpval = het_arch(y)
outDict['lm'] = lm
outDict['lmpval'] = lmpval
outDict['fval'] = fval
outDict['fpval'] = fpval
model= arch.arch_model(y, vol='Garch', p=P, o=0, q=Q, dist='Normal')
results=model.fit()
#print(results.summary())
params = results._params
paraNames = results._names
outDict['logl'] = results._loglikelihood
outDict['success'] = results._optim_output['success']
for i in range(len(params)):
outDict[paraNames[i]] = params[i]
#pprint(vars(results))
return outDict
def print_analyse(self):
#计算标准残差序列，对其做arch检验。
log_sigma = self.model.predict(self.x)
sigma = np.sqrt(np.exp(log_sigma))
sigma = np.reshape(sigma, (-1))
std_res = self.y / sigma
#检验arch效应
arch_test = het_arch(std_res)
print("*" * 10, self.name, "*" * 10)
print("{}模型,最优的损失值{:.3f}".format(self.name, min(self.history)))
print("arch检验的统计量：{:.3f}，对应p值为:{:.4f}\n".format(
arch_test[0], arch_test[1]))
#绘制训练损失变化图
plt.plot(np.arange(1,101), self.history, color='black',marker = ',',markersize = 7,\
lw=1, label='{} best loss: {:.3f}'.format(self.name,min(self.history)))
plt.xlabel('interation')
plt.ylabel('Training Loss')
plt.title("{} Training loss with iteration".format(self.name))
plt.legend(loc="upper right")
#新建一个文件夹，存放所有训练时产生的损失图片。
if not os.path.exists("plot_images/traning_loss"):
os.mkdir("plot_images/traning_loss")
plt.savefig("plot_images/traning_loss/{}.png".format(self.name))
plt.show()
plt.close()
def conditional_heteroskedastic(self, significance=0.05) -> bool:
"""
Engles LM test H0 homoskedastic
:param significance: significance level
:return: True or False of CH
"""
return het_arch(self.model.resid, ddof=sum(
self.model.order))[2] < significance
def test_het_arch2(self):
#test autolag options, this also test het_lm
#unfortunately optimal lag=1 for this data
resid = self.res.resid
res1 = smsdia.het_arch(resid, maxlag=1, autolag=None, store=True)
rs1 = res1[-1]
res2 = smsdia.het_arch(resid, maxlag=5, autolag='aic', store=True)
rs2 = res2[-1]
assert_almost_equal(rs2.resols.params, rs1.resols.params, decimal=13)
assert_almost_equal(res2[:4], res1[:4], decimal=13)
#test that smallest lag, maxlag=1 works
res3 = smsdia.het_arch(resid, maxlag=1, autolag='aic')
assert_almost_equal(res3[:4], res1[:4], decimal=13)
def test_het_arch2(self):
#test autolag options, this also test het_lm
#unfortunately optimal lag=1 for this data
resid = self.res.resid
res1 = smsdia.het_arch(resid, maxlag=1, autolag=None, store=True)
rs1 = res1[-1]
res2 = smsdia.het_arch(resid, maxlag=5, autolag='aic', store=True)
rs2 = res2[-1]
assert_almost_equal(rs2.resols.params, rs1.resols.params, decimal=13)
assert_almost_equal(res2[:4], res1[:4], decimal=13)
#test that smallest lag, maxlag=1 works
res3 = smsdia.het_arch(resid, maxlag=1, autolag='aic')
assert_almost_equal(res3[:4], res1[:4], decimal=13)
def test_het_arch(self):
#test het_arch and indirectly het_lm against R
#> library(FinTS)
#> at = ArchTest(residuals(fm), lags=4)
#> mkhtest(at, 'archtest_4', 'chi2')
archtest_4 = dict(statistic=3.43473400836259,
pvalue=0.487871315392619, parameters=(4,),
distr='chi2')
#> at = ArchTest(residuals(fm), lags=12)
#> mkhtest(at, 'archtest_12', 'chi2')
archtest_12 = dict(statistic=8.648320999014171,
pvalue=0.732638635007718, parameters=(12,),
distr='chi2')
at4 = smsdia.het_arch(self.res.resid, maxlag=4)
at12 = smsdia.het_arch(self.res.resid, maxlag=12)
compare_t_est(at4[:2], archtest_4, decimal=(12, 13))
compare_t_est(at12[:2], archtest_12, decimal=(12, 13))
def f_heterocerasticidad(df_indicador):
"""
Parameters
----------
df_indicador
Returns
-------
"""
arch = het_arch(df_indicador['Actual'])
return arch
def FitGARCH(series, p, q):
"""
:param series: series to fit on
:param p: lag length of residuals
:param q: lag length of variances
:return: dictionary of model configuration and result of arch-lm test
"""
am = arch_model(series, mean='Zero', vol='GARCH', p=p, q=q,
rescale=False).fit(disp='off')
# calculate standardized residuals
series_std = series / np.sqrt(am.conditional_volatility)
# append result of arch lm test with degrees of freedom of p+q to output
archresult = het_arch(series_std, nlags=20, ddof=p + q)[1]
return [(p, q), archresult]
def het_arch(resid: pd.Series, nlags=None, ddof=0):
"""
Engle’s Test for Autoregressive Conditional Heteroscedasticity (ARCH).
Null hypothesis:
No conditional heteroscedasticity
Note: This does not imply no serial correlation.
Alternative hypothesis:
Conditional heteroscedasticity exists
References:
* https://www.mathworks.com/help/econ/archtest.html
* https://www.mathworks.com/help/econ/engles-arch-test.html
Definition: Heteroscedasticity :=
Heteroscedasticity means that the variance of a time series
is not constant over time. Therefore the variance over sliding
window t,... t+i will differ from sliding window t+i+1,..t+j,
where t is the initial time index, i, j are integers.
Parameters
----------
resid : pd.Series
residuals from an estimation
nlags : int, default None
Highest lag to use.
ddof : int, default 0
If the residuals are from a regression, or ARMA estimation, then there
are recommendations to correct the degrees of freedom by the number
of parameters that have been estimated, for example ddof=p+q for an
ARMA(p,q).
Returns
-------
lm : float
Lagrange multiplier test statistic
lmpval : float
p-value for Lagrange multiplier test
"""
result = diagnostic.het_arch(resid, nlags=nlags, autolag=None, ddof=ddof)
HetArchResult = namedtuple('HetArchResult', 'statistic pvalue')
return HetArchResult(result[0], result[1])
def check_hetero(param_data):
"""
Funcion que verifica si los residuos de una estimacion son heterosedasticos
Parameters
---------
param_data: DataFrame: DataFrame que contiene residuales
---------
norm: boolean: indica true si los datos presentan heterodasticidad, o false si no la presentan.
Debuggin
---------
check_hetero(datos_residuales)
"""
# arch test
heterosced = het_arch(param_data)
alpha = .05 # intervalo de 95% de confianza
# si p-value menor a alpha se concluye que no hay heterodasticidad
heter = True if heterosced[1] > alpha else False
return heter
def get_engle_arch(errors, nlags):
'''
An uncorrelated time series can still be serially dependent due to a dynamic conditional variance process.
A time series exhibiting conditional heteroscedasticity—or autocorrelation in the squared series—is
said to have autoregressive conditional heteroscedastic (ARCH) effects.
Engle’s ARCH test is a Lagrange multiplier test to assess the significance of ARCH effects Rober, Engle (1982).
H0: process is not autocorrelated in the squared residuals
H1: process is autocorrelated in the squared residuals
Large critical value of the F-statistic proves rejection of the null
'''
arch_lm = het_arch(errors.dropna(), nlags=nlags)
print("Engle's Test for Autoregressive conditional Heteroscedasticity")
print("Number of Lags: {}".format(nlags))
print('LM test-stat:{}'.format(arch_lm[0]))
print('P-val for LM:{}'.format(arch_lm[1]))
print('F-statistic:{}'.format(arch_lm[2]))
print('P-value for F-stat:{}'.format(arch_lm[3]))
def f_hetero(param_data):
"""
Parameters
----------
param_data : DataFrame con los datos del precio del indicador
Returns
-------
heterokedasticity : valores para vereficar la heterocedasticidad de la serie
Debugging
---------
param_data = df_data
"""
data = param_data['actual']
# hetero = sm.OLS(data, sm.add_constant(data.index)).fit()
# res = hetero.resid
# bp_test = smd.het_breuschpagan(res, hetero.model.exog)
bp_test = smd.het_arch(data)
labels = [
'LM Statistic', 'LM-Test p-value', 'F-Statistic', 'F-Test p-value'
]
heterokedasticity = [dict(zip(labels, bp_test))]
return heterokedasticity
def arch(
other_args: List[str],
residuals: List[float],
):
"""Autoregressive conditional heteroscedasticity with Engle's test
Parameters
----------
other_args : str
Command line arguments to be processed with argparse
residuals : List[float]
Residuals data
"""
parser = argparse.ArgumentParser(
add_help=False,
prog="arch",
description="""
Autoregressive conditional heteroscedasticity with Engle's test
""",
)
try:
ns_parser = parse_known_args_and_warn(parser, other_args)
if not ns_parser:
return
# Engle's Test for Autoregressive Conditional Heteroscedasticity (ARCH)
lm, lmpval, fval, fpval = het_arch(residuals)
print("Lagrange multiplier test statistic")
print("Statistic: %.4f" % lm)
print("p-value: %.4f" % lmpval)
print("")
print("fstatistic for F test")
print("Statistic: %.4f" % fval)
print("p-value: %.4f" % fpval)
print("")
except Exception as e:
print(e, "\n")
return
#当i=n-2length,j=0是，代表计算最后一个样本，前1日滞后的方差，根据 n-1-length到n-1的值计算。
end = i + 2 * length - j - 1
start = i + length - j - 1
tmp_var[length - j - 1] = np.log(np.var(x[start:end]))
x_var.append(tmp_var)
#转换成array。
x_data, y_data, x_var = np.array(x_data), np.array(y_data), np.array(x_var)
x_data_square = x_data**2
return x_data, x_data_square, x_var, y_data
if __name__ == "__main__":
data = pd.read_csv("intermediate/arma_residual.csv")
data.columns = ["residual"]
arch_test = het_arch(data['residual'].values)
print("残差数据，arch检验的统计量：{:.3f}，对应p值为:{:.4f}".format(arch_test[0],
arch_test[1]))
#生成只包含滞后值的样本。
x_data, y_data, x_var = generate_data_lag(data['residual'].values,
length=20)
x_data = np.concatenate([x_data, x_var], axis=-1)
#开始训练模型.
fcnn_model = GARCH_DNN(build_fcnn_model(x_data.shape[-1]),
name="simple_FCNN_GARCH",
x=x_data,
y=y_data)
fcnn_model.fit()
fcnn_model.print_analyse()
test_jb[2],
' ',
name_jb[3],
' ',
test_jb[3],
)
print(' ')
# Lets try some more test_result --- TEST FOR HETEROSCEDASTICITY "WHITE's test"
print('WHITE TEST')
white_t = ssd.het_white(model.resid, model.model.exog, retres=False)
print(white_t[1])
stat_1 = white_t[1]
print('Whites test for hetero using lm test: ', stat_1,
'Whites test for hetero using F-Stat :', white_t[3])
print(' ')
#Next test :ARCH For heteroscedasticity
print('ARCH TEST')
arch = ssd.het_arch(model.resid,
maxlag=2,
autolag=None,
store=False,
regresults=False,
ddof=0)
print('LM test stat:', arch[0], 'LM P value:', arch[1], 'F test stat:',
arch[2], 'F P value', arch[3])
print(' ')
#Next test : RESET
print('Ramsey RESET test')
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)
## Teste de Durbin-Watson para autocorrelação dos resíduos. H_0: resíduos não têm autocorrelação com o seu 1o lag
#from statsmodels.stats.stattools import durbin_watson
#DW = durbin_watson(resid)
#print("\n", 'Teste de Durbin-Watson de independência dos resíduos:', DW[0])
# Teste de Breush-Godfrey para autocorrelação dos resíduos. H_0: resíduos não têm correlação com os seus "n" lags (neste caso definimos n = 10)
from statsmodels.stats.diagnostic import acorr_breusch_godfrey
bg = acorr_breusch_godfrey(model_output, nlags=10)
print(
"\n", 'Teste de Breush-Godfrey de independência dos resíduos:', bg
) # P-value (2o valor dos 4 apresentados) < 0.05 => existe autocorrelação dos resíduos
# Teste de heterocedasticidade ARCH. H_0: variância é constante. O segundo valor é o p-value
from statsmodels.stats.diagnostic import het_arch
archTest = het_arch(resid[0], maxlag=5, autolag=None)
print("\n", 'Teste ARCH de heterocedasticidade:', archTest[1]
) # P-value < 0.05 => rejeita-se H_0 => variância não é constante
### GJR-GARCH Model ### AR(2) + GJR-GARCH(1,1)
from arch import arch_model
gjrGarch = arch_model(tsReturns, mean="ARX", lags=2,
o=1) # importa as 3 equações ao mesmo tempo
model_gjrGarch = gjrGarch.fit(update_freq=5)
print("\n", model_gjrGarch.summary())
### EGARCH Model ### AR(2) + EGARCH(1,1)
from arch import arch_model
egarch = arch_model(tsReturns, mean="ARX", lags=2, vol="EGARCH",
df_atip = fn.df_boxplot()
df_atip
#%%
import statsmodels.stats.diagnostic as stm #import arch_test
data_DGO = pd.read_csv("../Proyecto_Equipo_3-master/Indice")
df_DGO = pd.DataFrame(data_DGO)
df_DGO.sort_index(ascending = False, inplace = True)
df_DGO60 = df_DGO['Actual']
arc = stm.het_arch(df_DGO60)
#%%
arch1 = arc.fit()
print(arch1.summary())
#%%
p_arch = fn.df_parch()
p_arch
#%%
plt.plot(df_DGO['Actual'])
plt.show()
#%% Intento b
def engle(data, lags=12):
arch = het_arch(data, nlags=lags)
print("Lagrange multiplier test")
print(f"Chi-squared: {round(arch[0], 4)}", end=", ")
print(f"p-value: {arch[1]}")
#stocks.to_csv('GSPC.csv')
#stocks = pd.DataFrame.from_csv('GSPC.csv')
#key symbols '^GSPC', '^DJI', '^VIX' 'DNKN''AAPL'
# find returns
ret_Stock = stocks['Adj Close'].pct_change().dropna()
# ACF (autocorrelation function)
# acf and pacf from statsmodels
from statsmodels.tsa.stattools import acf
ac = acf(ret_Stock,nlags=250)
ac2 = acf(np.square(ret_Stock),nlags=200)
#from statsmodels.graphics.tsaplots import plot_acf
#plot_acf(ret_Stock)
# Ljung-Box Test for 20 lags
# statsmodels.stats.diagnostic.acorr_ljungbox
import statsmodels.stats.diagnostic as ssd
lags = 10;
qstat, pval = ssd.acorr_ljungbox(ret_Stock,lags)
qstat2, pval2 =ssd.acorr_ljungbox(np.square(ret_Stock),lags)
# Engle LM test for heteroskedasticity consistent
# statsmodels.sandbox.stats.diagnostic.acorr_lm het_arch
lmstat = ssd.het_arch(ret_Stock,lags)
lmstat2 = ssd.het_arch(np.square(ret_Stock),lags)
def engle_test_series(data, Returns):
products = sorted(data.keys())
for p in products:
print(p + ': p-value Engle: ' + str(het_arch(Returns[p])[1]))
u_hat = series - y_hat_arima
#generate plot of residuals
plt.plot(u_hat)
plt.savefig('../../manuscript/src/latexGraphics/u_hat_houstmw.png')
#plt.show()
plt.close()
#generate acf plot of squared residuals
plot_acf(u_hat**2, lags=100)
plt.savefig('../../manuscript/src/latexGraphics/acf_u_hat_sq_houstmw.png')
plt.close()
#arch-lm test
#https://www.statsmodels.org/stable/generated/statsmodels.stats.diagnostic.het_arch.html
dct_tex['archlmresult'] = np.round(het_arch(u_hat, nlags=3, ddof=6)[1], 4)
####select optimal GARCH Model according to arch lm test result of standardized residuals
#define grid of model parameters:
ls_params = [(p, q) for p in range(1, 20) for q in range(1, 20)]
ls_out = []
if multiproc == True:
ls_out = Parallel(n_jobs=-1)(
delayed(FitGARCH)(*[u_hat, param[0], param[1]])
for param in ls_params)
else:
for param in tqdm(ls_params):
ls_out.append(FitGARCH(u_hat, param[0], param[1]))
modelos_AR = dict()
for i in data.columns:
print(f"Modelo arima para {i}"
f"##############################################"
f"##############################################")
# Fit auto_arima function to AirPassengers dataset
modelos_AR[i] = ARIMA(data[i].dropna(), order = (1,0,0)).fit() # set to stepwise
# To print the summary
print(modelos_AR[i].summary())
"""
#VERIFICAR ARCH
for i in data.columns:
print(f"ARCHTest para resíduos de {i}")
print(het_arch(modelos[i].arima_res_.resid,nlags=6))
print("Time Series")
print(het_arch(data[i].dropna(),nlags=6))
#FAZER MODELOS GARCH
modelos_garch = dict()
for i in data.columns:
print(f"Modelo GARCH para {i}"
f"##############################################"
f"##############################################")
# Fit auto_arima function to AirPassengers dataset
modelos_garch[i] = arch.arch_model(modelos[i].arima_res_.resid, vol = "GARCH", rescale= True).fit() # set to stepwise
# To print the summary
print(modelos_garch[i].summary())
#收益率平稳性检验结果为1阶弱平稳
#adftest(df2)
#参数选择为(0,1)
params_select(df1)
print(acorr_ljungbox(df1, lags=1))
#系数估计------------------------------------------------
model = sm.tsa.ARMA(df2, (0, 1)).fit()
print(model.summary())
print('----------------------------------------')
print(model.params)
#--------------------------------------------------------
#收益率残差自相关性检验-----------------------------------
resid = model.resid
print(sm.stats.durbin_watson(resid.values))
#检验残差arch效应-----------------------------------------
*_, fpvalue = diagnostic.het_arch(resid)
if fpvalue < 0.05:
print('异方差性显著', fpvalue)
else:
print('异方差性不显著', fpvalue)
#建立arch模型-----------------------------------------------
#模型预测
model = sm.tsa.ARMA(df2, (0, 1)).fit()
arch_mod = ConstantMean(df2)
arch_mod.volatility = GARCH(1, 0, 1)
arch_mod.distribution = StudentsT()
res = arch_mod.fit(update_freq=5, disp='off')
mu = model.params[0]
theta = model.params[1]
omega = res.params[1]
from util import energy_return_data
import numpy as np
from scipy.stats import kurtosis, skew
from statsmodels.stats.diagnostic import het_arch, acorr_ljungbox
windowed, np_data, scaler1 = energy_return_data(window=25)
y = np_data[:, :-1].reshape(-1)
print('mean', np.mean(y))
print('max', np.max(y))
print('min', np.min(y))
print('median', np.median(y))
print('S.D.', np.std(y))
print('Skewness', skew(y))
print('Excess kurtosis', kurtosis(y) - 3)
print('Ljung-Box test of autocorrelation in residuals',
acorr_ljungbox(y, lags=[25])[1])
print('Engle’s Test for Autoregressive Conditional Heteroscedasticity (ARCH)',
het_arch(y)[1])
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)
def het_arch(self, timeseries):
model, model_result = self.generate_model(timeseries)
result = diagnostic.het_arch(model_result)
HetArchResult = namedtuple('HetArchResult', 'statistic pvalue')
return HetArchResult(result[0], result[1])