final_practice_2009

2 solutions fall 2001 b x ay issued for some a b

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: andom variable and Y knowledge of Y PROCESSES X (and vice versa). Suppose weProblem Set X based on knowledge of Y using an aﬃne estimator want to estimate No. 2 Solutions Fallˆ 2001 + b X = aY Issued: for some a, b Wednesday,to be 12, 2001 constants Sep. determined. Due: Friday, Sep. 21, 2001 Problem 2.1 (a) Find expressions for a,variables X and E [X ] = jointE [Y ] = function is ,given , CY X , Cx,Y ).(where CAB = E [(A − b in terms of Y whose µX , density µY , CXX CXY by p ( Y y For each of Consider the random X,Y ˆ E [AtheB − E [Bchoices of thethe mean squared error Ebelow determineminimized. and Y are uncorrelated,)( possible ])]) so that joint density function given [(X − X )2 ] is i) whether X ii) whether X and Y are independent, and iii) specify the corresponding covariance matrix: (b) For each of the following joint distributions shown below, what are the resulting a, b and estimators? In ˆ each case graph the function X on the plot of theσjoint σXY . What observations can you make? When does density. XX ΣXY = σ knowledge of Y not aﬀect the aﬃne estimate of X ? XY σY Y Y p X ,Y p Y ( x ,y ) = 2 X ,Y p ( x ,y ) = 1 /2 Y 1 1 X ,Y ( x ,y ) = 1 1 0 -1 0 pX,Y (x, y ) = 1 X 1 -1 X x, y ≥ 0 & x+y ≤1 0 otherwise 2 pX,Y (x, y ) = (a) 0...
View Full Document

This note was uploaded on 01/08/2013 for the course ECE 531 taught by Professor Natasha during the Spring '10 term at Ill. Chicago.

Ask a homework question - tutors are online