statsmodels.stats.multivariate_tools.cc_ranktest#

statsmodels.stats.multivariate_tools.cc_ranktest(x1, x2, demean=True, fullrank=False, return_object=False)[source]#

Rank tests based on smallest canonical correlation coefficients

Anderson canonical correlations test (LM test) and Cragg-Donald test (Wald test) Assumes homoskedasticity and independent observations, overrejects if there is heteroscedasticity or autocorrelation.

The Null Hypothesis is that the rank is k - 1, the alternative hypothesis is that the rank is at least k.

Parameters:

x1, x2array_like, 2-D: Two 2-dimensional data arrays, observations in rows, variables in columns.
demeanbool, optional: If demean is true, then the mean is subtracted from each variable.
fullrankbool, optional: If true, then only the test that the matrix has full rank is returned. If false, the test for all possible ranks are returned. However, the p-values are not corrected for the multiplicity of tests.
return_objectbool, optional: If False (default), the results are returned as a plain tuple (statistic, pvalue, df, ccorr, wald_statistic, wald_pvalue), the legacy return format of this function. If True, a CCRankTestResult instance is returned instead, which exposes the same values as named attributes and still unpacks as the same 6-tuple.

Returns:

tuple or CCRankTestResult: By default, the tuple (statistic, pvalue, df, ccorr, wald_statistic, wald_pvalue). If return_object is True, a CCRankTestResult with the same values as attributes.