0
$\begingroup$

Let $Z=(X+Y)/2$, where $X$ and $Y$ are independent normally-distributed random variables with known variances $\sigma^2_X$ and $\sigma^2_Y$ and unknown (and possibly different) means. Given a sample $x_1$ from $X$ and $y_1$ from $Y$, what is the minimum mean squared error estimator of the mean of $Z$? Is there a biased estimator with an MSE improved over the maximum likelihood estimator $\frac{x_1+y_1}{2}$? Can we generalize to $n$ mutually-independent random variables?

$\endgroup$
  • $\begingroup$ Maybe this should be tagged as homework? $\endgroup$ – whuber Nov 11 '10 at 13:30
1
$\begingroup$

Minimize SSE = Σi (zi-a)2 with respect to a and you get the average of the two sample means, so it looks like your MLE is also your minimum MSE estimator, whether you have one (x,y) pair or several. Not surprising, since the expression for the SSE and the log likelihood function are almost identical.

$\endgroup$

Your Answer

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