Solution_Assignment1

Solution_Assignment1 - STAT 333 Spring 2009 Solutions to Assignment 1 By Juan Manuel Martinez e-mail:[email protected] June 3 2009 Type I

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: STAT 333 Spring 2009 Solutions to Assignment 1 By Juan Manuel Martinez e-mail:[email protected] June 3, 2009 Type I Problems Problem 1 a) Here T has an exponential distribution with parameter λ = 2. Its cumulative distribution function is therefore given by: F T ( t ) = 1- e- 2 t We conclude that Pr( T > 1 2 ) = 1 - Pr( T ≤ 1 2 ) = 1 - F T ( 1 2 ) = 1 - (1 - e- 1 ) = e- 1 b) We make use of the memoryless property of the exponential distribution. For any positive real numbers s and t: Pr ( T > s + t | T > s ) = Pr ( T > t ) Therefore, Pr( T > 12 . 5 | T > 12 ) = Pr( T > 1 2 ) = e- 1 Problem 2 Let: • F = event that fair coin is picked up • T = event that two-headed coin is picked up • B = event that biased coin is picked up • H = event that coin picked up shows head Clearly, Pr ( H | B ) = 0.75, Pr ( H | T ) = 1 and Pr ( H | F ) = 0 . 5 . Since any coin is equally likely to be picked up, Pr(T) = Pr(F) = Pr(B) = 1 3 The problem asks for Pr ( T | H ) . For this we make use of Bayes’ Rule: Pr ( T | H ) = Pr ( T,H ) Pr ( H ) = Pr ( H | T ) Pr ( T ) Pr ( H | T ) Pr ( T ) + Pr ( H | B ) Pr ( B ) + Pr ( H | F ) Pr ( F ) 1 = (1)( 1 3 ) 1 3 (1 + 0 . 75 + 0 . 5) = 4 9 Problem 3 We have Pr ( Y > n ) = Pr ( FF...F bracehtipupleft bracehtipdownrightbracehtipdownleft bracehtipupright ntimes ) = (1- p 1 )(1- p 2 ) ... (1- p n ) (because the trials are independent) = producttext n i =1 (1- p i ) Letting n → ∞ , we have Pr ( Y = ∞ ) = f( ∞ ) = producttext ∞ i =1 (1- p i ) . To determine whether or not Y is a proper random variable, we make use of the Sum-Product lemma, which states that ∞ productdisplay i =1 (1- p i ) > ⇔ ∞ summationdisplay i =1 p i < ∞ Therefore, the problem boils down to determining whether or not the infinite series converges or diverges. i) Here, p n = 4- n . To determine if Y is proper, we must determine if ∑ ∞ i =1 ( 1 4 ) i converges or not. Observe that: ∞ summationdisplay i =1 parenleftbigg 1 4 parenrightbigg i = ∞ summationdisplay i =0 parenleftbigg 1 4 parenrightbigg i- 1 = 1 1- 1 4- 1 = 1 3 < ∞ Thus, the series converges, and by the Sum-Product lemma, Y is not a proper random variable. ii) Here, p n = 1- e- 1 n . To determine if ∑ ∞ i =1 (1- e- 1 i ) converges, we apply the Limit Comparison Test with the harmonic series ∑ ∞ i =1 ( 1 i ) . Then: lim n →∞ 1 n 1- e- 1 n = lim n →∞- 1 n 2 e- 1 n * 1 n 2 = lim n →∞ e 1 n = 1 < ∞ Where we used l’Hopital’s rule to go from the first to the second equality. By the Limit Comparison Test, ∑ ∞ i =1 (1- e- 1 i ) diverges, and by the Sum-Product lemma, Y is a proper random variable. 2 Problem 4 Since the X prime i s are independent and identically distributed (i.i.d.) we must have that for any integers i, j, i negationslash = j , Pr ( X i < X j ) = Pr ( X i > X j ) = 1 2 . Therefore, the value of Pr ( X 1 < X 2 < X 4 < X 3 ) is independent of the order of the 4 variables. All we care about is the number of different ways to arrange the random variables in ascending order. There arevariables....
View Full Document

This note was uploaded on 01/16/2011 for the course STAT 333 taught by Professor Chisholm during the Spring '08 term at Waterloo.

Page1 / 9

Solution_Assignment1 - STAT 333 Spring 2009 Solutions to Assignment 1 By Juan Manuel Martinez e-mail:[email protected] June 3 2009 Type I

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online