ps5 - n = 1 and n > 1 separately. Problem 4 -...

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

View Full Document Right Arrow Icon
EE 806, Detection and Estimation Theory May 12, 2008 OSU, Spring 2008 Due: May 19, 2008 Problem Set 5 Problem 1 Let Θ be a random variable with pdf w ( θ ) and let the conditional pdf of Θ given the observation ~ Y be w ( θ | ~ Y ). Show that the minimum mean absolute error (MMAE) estimate ˆ θ MMAE ( ~ y ) is the conditional median (as given in lecture notes) of w ( θ | ~ Y ). ( Hint: For a non-negative random variable X , E [ X ] = R 0 P ( X > x ) dx .) Problem 2 - (Poor, Ch. 4, Pr. 6) You don’t need to solve for ˆ θ MMAE in closed form. Problem 3 - (Poor, Ch. 4, Pr. 8) In part (c), consider the cases
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: n = 1 and n > 1 separately. Problem 4 - (Poor, Ch. 4, Pr. 11) Replace What happens when. .. with What happens when (i) n assuming | | < 1, (ii) q 2 , (iii) q 2 0. In many problems of this sort it is extremely important to consider the support of the various pdfs. I suggest using the indicator function notation I A ( x ) = ( 1 x A x / A for set A . For example, a unit-exponential r.v. Y has pdf f Y ( y ) = e-y I [0 , ) ( y ). 1...
View Full Document

This note was uploaded on 07/17/2008 for the course EE 806 taught by Professor Unknown during the Spring '08 term at Ohio State.

Ask a homework question - tutors are online