Thanks again!

So, if I want to disregard the imaginary number part for the covariance matrix by using the following code:

cv = Covariance[Table[u[i, t] - u[i, t - 1], {t, 1, 3}, {i, 1, 2}]];

m = Simplify[cv, Element[u[_, _], Reals]]

-> Then, is this "m" can be SAFELY assumed to be the resulting covariance matrix only on the real number environment

just like any normally pratical usage like in business?

Again, thank you very much!