conditional_independence.partial_correlation_suffstat¶
-
conditional_independence.
partial_correlation_suffstat
(samples, invert=True) → Dict[source]¶ Return the sufficient statistics for partial correlation testing.
- Parameters
samples – (n x p) matrix, where n is the number of samples and p is the number of variables.
invert – if True, compute the inverse correlation matrix, and normalize it into the partial correlation matrix. This will generally speed up the gauss_ci_test if large conditioning sets are used.
- Returns
dictionary of sufficient statistics
- Return type
dict