I have:

E(X) = 10
E(Y) = 12
Var(X) = 4
Var(Y) = 9
covariance = 2

I know that for:

Var(X + Y) = Var(X) + Var(Y) + 2covariance

Which would be useful if I could do this:

Var(X - 2Y) = Var(X) + Var(-2Y) + 2*covar(X, -2Y)

But I do not have the variance of -2Y nor the covariance covar(X, -2Y).


The formula you have for the variance of $X+Y$ generalizes to the variance of the linear combination $\alpha X+\beta Y$. We have in general $$\text{Var}(\alpha X+\beta Y)=\alpha^2 \text{Var}(X)+\beta^2\text{Var}(Y) +2\alpha\beta\text{Cov}(X,Y).$$ The proof is essentially the same.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.