# There are two complementary approaches for dealing

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 2 3 + X2 2 = 4 9 + E [X 2 ] 4 = 35 72 . MSE for L∗ (X ) = Thus, 1 35 1 − =. 2 72 72 1 Note that (MSE using g ∗ (X ) = 96 ) ≤ (MSE using L∗ = are ordered in accordance with (4.36). 4.11 1 72 ) ≤ (Var(Y ) = 1 18 ), so the three MSEs Joint Gaussian distribution Recall that Gaussian distributions often arise in practice; this fact is explained by the CLT. The CLT can be extended to two, or even more, correlated random variables. For example, suppose (U1 , V1 ), (U2 , V2 ), · · · are independent, identically distributed pairs of random variables. For example, Ui might be the height, and Vi the weight, of the ith student to enroll at a university. Suppose ···+ ···+ for convenience that they have mean zero. Then as n → ∞, the pair U1 +√n Un , V1 +√n Vn has a limiting bivariate distribution, where “bivariate” means the limit distribution is a joint distribution of two random variables. Suppose X and Y have such a limit distribution. Then X and Y must each be Gaussian random var...
View Full Document

## This note was uploaded on 02/09/2014 for the course ISYE 2027 taught by Professor Zahrn during the Spring '08 term at Georgia Institute of Technology.

Ask a homework question - tutors are online