Bartlett's Chi-square for Canonical Correlation

Tests for independence between two sets of Number - Multi questions, containing $p$ and $q$ variables respectively. The test statistic is:

$V=-((n-1.5)-(p+q)/2.0)\sum _{i=1}^m\log (1-r_i^2)$

where

$n$ is the Effective Sample Size,

$p\approx \mathrm{Pr}({\chi }_{pq}^2\ge \mathrm{\Lambda })$.

See also

Multivariate Tests