<p>均方差 =Mean Square Error</p><p>The MSE of an estimator <img class="tex" alt="\hat{\theta}" src="http://upload.wikimedia.org/math/7/4/4/744e7c77ccdce7b7aa6f9a75788ac57d.png"/> with respect to the estimated parameter <span class="texhtml">θ</span> is defined as</p><p><img class="tex" alt="\operatorname{MSE}(\hat{\theta})=\operatorname{E}((\hat{\theta}-\theta)^2)." src="http://upload.wikimedia.org/math/2/6/7/2677780081396b40a666e086ae963e55.png"/>
</p><p>The MSE can be written as the sum of the variance and the squared bias of the estimator</p><p><img class="tex" alt="\operatorname{MSE}(\hat{\theta})=\operatorname{Var}\left(\hat{\theta}\right)+ \left(\operatorname{Bias}(\hat{\theta},\theta)\right)^2." src="http://upload.wikimedia.org/math/2/d/5/2d50a42670f10b6a570404f1251d365b.png"/> </p>
|