Should there be covariance terms for the second formula? V(x1 + x2) = V(x1) + V(x2) + 2COV(x1, x2)?
Can we think of the variance as an average of the derivatives at each point?
Should there be covariance terms for the second formula? V(x1 + x2) = V(x1) + V(x2) + 2COV(x1, x2)?
Can we think of the variance as an average of the derivatives at each point?