[patch #6650] one pass covariance algorithm

[Jason H Stover]

Follow-up Comment #16, patch #6650 (project pspp):

Two corrections to my previous post:

"The question of pairwise or listwise deletion is the most important question
when computing the covariance matrix, so this is a big improvement."

I meant the most important question about handling missing values.

"update_moments does not depend on a test that is invariant in the loops in
which it is called,..."

I meant that it's test does NOT depend on the loops.



    _______________________________________________________

Reply to this item at:

  <http://savannah.gnu.org/patch/?6650>

_______________________________________________
  Message sent via/by Savannah
  http://savannah.gnu.org/