def test_3d_error(self):
data = np.array(2)
with pytest.raises(ValueError):
tsatools.lagmat2ds(data, 5)
data = np.zeros((100, 2, 2))
with pytest.raises(ValueError):
tsatools.lagmat2ds(data, 5)
def test_lagmat2ds_numpy(self):
data = self.macro_df
npdata = data.values
lagmat = tsatools.lagmat2ds(npdata, 2)
expected = self._prepare_expected(npdata, 2)
assert_array_equal(lagmat, expected)
lagmat = tsatools.lagmat2ds(npdata[:, :2], 3)
expected = self._prepare_expected(npdata[:, :2], 3)
assert_array_equal(lagmat, expected)
npdata = self.series.values
lagmat = tsatools.lagmat2ds(npdata, 5)
expected = self._prepare_expected(npdata[:, None], 5)
assert_array_equal(lagmat, expected)
def test_lagmat2ds_pandas(self):
data = self.macro_df
lagmat = tsatools.lagmat2ds(data, 2)
expected = self._prepare_expected(data.values, 2)
assert_array_equal(lagmat, expected)
lagmat = tsatools.lagmat2ds(data.iloc[:, :2], 3, trim='both')
expected = self._prepare_expected(data.values[:, :2], 3)
expected = expected[3:]
assert_array_equal(lagmat, expected)
data = self.series
lagmat = tsatools.lagmat2ds(data, 5)
expected = self._prepare_expected(data.values[:, None], 5)
assert_array_equal(lagmat, expected)
def test_lagmat2ds_use_pandas(self):
data = self.macro_df
lagmat = tsatools.lagmat2ds(data, 2, use_pandas=True)
expected = self._prepare_expected(data.values, 2)
cols = []
for c in data:
for lags in range(3):
if lags == 0:
cols.append(c)
else:
cols.append(c + '.L.' + str(lags))
expected = pd.DataFrame(expected, index=data.index, columns=cols)
tm.assert_frame_equal(lagmat, expected)
lagmat = tsatools.lagmat2ds(data.iloc[:, :2],
3,
use_pandas=True,
trim='both')
expected = self._prepare_expected(data.values[:, :2], 3)
cols = []
for c in data.iloc[:, :2]:
for lags in range(4):
if lags == 0:
cols.append(c)
else:
cols.append(c + '.L.' + str(lags))
expected = pd.DataFrame(expected, index=data.index, columns=cols)
expected = expected.iloc[3:]
tm.assert_frame_equal(lagmat, expected)
data = self.series
lagmat = tsatools.lagmat2ds(data, 5, use_pandas=True)
expected = self._prepare_expected(data.values[:, None], 5)
cols = []
c = data.name
for lags in range(6):
if lags == 0:
cols.append(c)
else:
cols.append(c + '.L.' + str(lags))
expected = pd.DataFrame(expected, index=data.index, columns=cols)
tm.assert_frame_equal(lagmat, expected)
def grangercausalitytests(x, maxlag, addconst=True, verbose=True):
"""four tests for granger non causality of 2 timeseries
all four tests give similar results
`params_ftest` and `ssr_ftest` are equivalent based on F test which is
identical to lmtest:grangertest in R
Parameters
----------
x : array, 2d
data for test whether the time series in the second column Granger
causes the time series in the first column
maxlag : integer
the Granger causality test results are calculated for all lags up to
maxlag
verbose : bool
print results if true
Returns
-------
results : dictionary
all test results, dictionary keys are the number of lags. For each
lag the values are a tuple, with the first element a dictionary with
teststatistic, pvalues, degrees of freedom, the second element are
the OLS estimation results for the restricted model, the unrestricted
model and the restriction (contrast) matrix for the parameter f_test.
Notes
-----
TODO: convert to class and attach results properly
The Null hypothesis for grangercausalitytests is that the time series in
the second column, x2, does NOT Granger cause the time series in the first
column, x1. Grange causality means that past values of x2 have a
statistically significant effect on the current value of x1, taking past
values of x1 into account as regressors. We reject the null hypothesis
that x2 does not Granger cause x1 if the pvalues are below a desired size
of the test.
The null hypothesis for all four test is that the coefficients
corresponding to past values of the second time series are zero.
'params_ftest', 'ssr_ftest' are based on F distribution
'ssr_chi2test', 'lrtest' are based on chi-square distribution
References
----------
http://en.wikipedia.org/wiki/Granger_causality
Greene: Econometric Analysis
"""
if verbose: # pragma: no cover
raise NotImplementedError("Option `verbose` from upstream is "
"not supported")
x = np.asarray(x)
if x.shape[0] <= 3 * maxlag + int(addconst):
raise ValueError(
"Insufficient observations. Maximum allowable "
"lag is {0}".format(int((x.shape[0] - int(addconst)) / 3) - 1))
resli = {}
for mlg in range(1, maxlag + 1):
result = {}
mxlg = mlg
# create lagmat of both time series
dta = lagmat2ds(x, mxlg, trim='both', dropex=1)
if addconst:
dtaown = add_constant(dta[:, 1:(mxlg + 1)], prepend=False)
dtajoint = add_constant(dta[:, 1:], prepend=False)
else:
# TODO: Whats intended here?
raise NotImplementedError
# dtaown = dta[:, 1:mxlg]
# dtajoint = dta[:, 1:]
# Run ols on both models without and with lags of second variable
res2down = OLS(dta[:, 0], dtaown).fit()
res2djoint = OLS(dta[:, 0], dtajoint).fit()
# for ssr based tests see:
# http://support.sas.com/rnd/app/examples/ets/granger/index.htm
# the other tests are made-up
# Granger Causality test using ssr (F statistic)
fgc1 = ((res2down.ssr - res2djoint.ssr) / res2djoint.ssr / mxlg *
res2djoint.df_resid)
result['ssr_ftest'] = (fgc1, stats.f.sf(fgc1, mxlg,
res2djoint.df_resid),
res2djoint.df_resid, mxlg)
# Granger Causality test using ssr (ch2 statistic)
fgc2 = res2down.nobs * (res2down.ssr - res2djoint.ssr) / res2djoint.ssr
result['ssr_chi2test'] = (fgc2, stats.chi2.sf(fgc2, mxlg), mxlg)
# likelihood ratio test pvalue:
lr = -2 * (res2down.llf - res2djoint.llf)
result['lrtest'] = (lr, stats.chi2.sf(lr, mxlg), mxlg)
# F test that all lag coefficients of exog are zero
rconstr = np.column_stack((np.zeros(
(mxlg, mxlg)), np.eye(mxlg, mxlg), np.zeros((mxlg, 1))))
ftres = res2djoint.f_test(rconstr)
result['params_ftest'] = (np.squeeze(ftres.fvalue)[()],
np.squeeze(ftres.pvalue)[()], ftres.df_denom,
ftres.df_num)
resli[mxlg] = (result, [res2down, res2djoint, rconstr])
return resli