statsmodels.stats.contingency_tables.cochrans_q#

statsmodels.stats.contingency_tables.cochrans_q(x, return_object=None)[source]#

Cochran’s Q test for identical binomial proportions

Parameters:

xarray_like, 2d (N, k): data with N cases and k variables
return_objectbool, optional: No longer used. cochrans_q always returns a CochransQResult, which supports both the attribute access of the bunch that return_object=True used to produce and the positional unpacking of the (statistic, pvalue, df) tuple that return_object=False used to produce.

Deprecated since version 0.15.0: return_object no longer affects the return value and will be removed in statsmodels 0.16.0. Passing it raises a FutureWarning; simply stop passing it.

Returns:

CochransQResult

A NamedTuple with fields:

statisticfloat: test statistic
pvaluefloat: pvalue from the chisquare distribution
dfint: degrees of freedom of the chisquare distribution

CochransQResult unpacks and indexes exactly like the (statistic, pvalue, df) tuple that return_object=False returned, and exposes the same statistic, pvalue and df attributes as the bunch that return_object=True returned. See CochransQResult.

Notes

Cochran’s Q is a k-sample extension of the McNemar test. If there are only two groups, then Cochran’s Q test and the McNemar test are equivalent.

The procedure tests that the probability of success is the same for every group. The alternative hypothesis is that at least two groups have a different probability of success.

In Wikipedia terminology, rows are blocks and columns are treatments. The number of rows N, should be large for the chisquare distribution to be a good approximation.

The Null hypothesis of the test is that all treatments have the same effect.

References

https://en.wikipedia.org/wiki/Cochran_test SAS Manual for NPAR TESTS