nispace.stats.coloc.pearson

nispace.stats.coloc.pearson(x, y)[source]

Compute Pearson correlation for two 1D arrays.

Parameters:
  • x (np.ndarray, shape (n,), dtype float) – Numba-jitted: must be plain 1D np.ndarray instances of equal length. Does not handle NaN – callers must pre-mask (e.g. x[mask], y[mask]).

  • y (np.ndarray, shape (n,), dtype float) – Numba-jitted: must be plain 1D np.ndarray instances of equal length. Does not handle NaN – callers must pre-mask (e.g. x[mask], y[mask]).

Returns:

r – NaN if either array has zero variance.

Return type:

float

Notes

The workhorse of core/colocalize.py’s “pearson”/”spearman” colocalization path (Spearman is computed by ranking with rank2d first, then calling this function on the ranks) and of core/reduce_x.py/core/region_influence.py.