arch.unitroot.cointegration.EngleGrangerTestResults

class arch.unitroot.cointegration.EngleGrangerTestResults(stat, pvalue, crit_vals, null='No Cointegration', alternative='Cointegration', trend='c', order=2, adf=None, xsection=None)

Results class for Engle-Granger cointegration tests.

Parameters

• stat (float) -- The Engle-Granger test statistic.

• pvalue (float) -- The pvalue of the Engle-Granger test statistic.

• crit_vals (Series) -- The critical values of the Engle-Granger specific to the sample size and model dimension.

• null (str) -- The null hypothesis.

• alternative (str) -- The alternative hypothesis.

• trend (str) -- The model's trend description.

• order (int) -- The number of stochastic trends in the null distribution.

• adf (ADF) -- The ADF instance used to perform the test and lag selection.

• xsection (RegressionResults) -- The OLS results used in the cross-sectional regression.

Methods

plot([axes, title])	Plot the cointegration residuals.
summary()	Summary of test, containing statistic, p-value and critical values

Properties

alternative_hypothesis	The alternative hypothesis
cointegrating_vector	The estimated cointegrating vector.
critical_values	Critical Values
distribution_order	The number of stochastic trends under the null hypothesis.
lags	The number of lags used in the Augmented Dickey-Fuller regression.
max_lags	The maximum number of lags used in the lag-length selection.
name	Sets or gets the name of the cointegration test
null_hypothesis	The null hypothesis
pvalue	The p-value of the test statistic.
resid	The residual from the cointegrating regression.
rho	The estimated coefficient in the Dickey-Fuller Test
stat	The test statistic.
trend	The trend used in the cointegrating regression