The mean square error, MSE sub s and a is defined as the sum of 2 quantities. The first quantity is the square of the difference of 2 parts. Part 1 is defined as the logarithm of the ratio of P sub s and a, and 1 minus P sub s and a. Part 2 is defined as the logarithm of the ratio of Theta sub s and a, and 1 minus Theta sub s and a. The second quantity is the posterior variance of the logarithm of the ratio of P sub s and a, and 1 minus P sub s and a.