We know that covariance matrix is symmetrical. I have a vague intuition that there may be some other redundancies beyond that. For example, if A is correlated to B and B is correlated to C then A and C must be somehow correlated, thus the correlation coefficient for A and C might somehow be constrained by the first two. I am sure that this question has already been researched - I'd like some guidance, please.
$\begingroup$
$\endgroup$
Add a comment
|