NOTE 19U: To see the relation between var(*d*_{ij}) and var(*x*_{i}), consider the deviation from the mean:

The expectation of the square of this deviation is found by summing the expectations of the squares of each term, because the *x*_{i} are independent of each other (i.e., *E*[*x*_{i}*x*_{j}] = 0, *E*[*x*_{i}^{2}] = var(*x*_{i})). So,