If one is willing to interpret Q [the Goldberger, Nagar, Odeh reduced form coefficient covariance estimate] as a covariance matrix of the random parameter @p around the constant @p, rather than as a covariance matrix of the random estimates @p, then using @p for @p and Q for Q [@p and Q are the mean and covariance matrix of the random parameter @p] will provide an approximate solution to the evaluation of expectations required in our optimal control problem [3, p. 641], italics added).