answersLogoWhite

0

I'd be inclined to say no, Im looking for the answer myself. But if you have Cov(A-B,A+B)=Cov(A,A)-Cov(B,B)-Cov(B,A)+Cov(A,B), then the last two will cancel but if Var(B)>Var(A) then we would get a negative covariance. [Cov(A,A)=Var(A)] So it looks possible because as far as I know there is no squaring of the coefficeients when you bring them out of the covariance so a negative answer is entirely possible.

User Avatar

Wiki User

14y ago

Still curious? Ask our experts.

Chat with our AI personalities

EzraEzra
Faith is not about having all the answers, but learning to ask the right questions.
Chat with Ezra
TaigaTaiga
Every great hero faces trials, and you—yes, YOU—are no exception!
Chat with Taiga
ViviVivi
Your ride-or-die bestie who's seen you through every high and low.
Chat with Vivi

Add your answer:

Earn +20 pts
Q: Can covariance be negative
Write your answer...
Submit
Still have questions?
magnify glass
imp