This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: E4702. Statistical Inference for Financial Engineering. Professor S. Kou. Midterm, August 12, 2010. 11am1:30pm. Closed Book Exam . Total 40 pts. Note: For &true or falsequestions, simply answer &trueor &false. No explanation is needed. 1. (5 pts) The returns of these two managers are: A: p 1 & 60% + (1 p 1 ) & 15% : B: p 2 & 30% + (1 p 2 ) & 5% . When the Simpsons paradox appears, we must have p 1 & 60% + (1 p 1 ) & 15% < p 2 & 30% + (1 p 2 ) & 5% ; which gives us p 2 > 1 : 8 p 1 + 0 : 4 : Also, p 1 and p 2 must satisfy p 1 ;p 2 1 : 2. (10 pts) a. (5 pts) The likelihood is L ( & ) = n Y i =1 e & & & X i X i ! : Thus log( L ( & )) = ( n& ) + log( & ) n X i =1 X i n X i =1 log( X i !) : @ @& log( L ( & )) = n + 1 & n X i =1 X i : Thus, the MLE for ^ & is given by 0 = n + 1 ^ & n X i =1 X i ; i.e. ^ & = P n i =1 X i n = & X: By the invariance principle, the maximum likelihood estimator for = (1 + & ) e & & is given by ^ , where ^ = (1 + ^ & ) e & ^ & = (1 + & X ) e & & X : b. (5 pts) Since = (1 + & ) e & & = P ( X = 0) + P ( X = 1) ; an unbiased estimator for is given by ~ = 1 n n X i =1 ( I f X i = 0 g + I f X i = 1 g ) ; where I f A g = 1 if A is true and I f A g = 0 if A is false. Indeed, we haveis false....
View
Full
Document
This note was uploaded on 10/18/2010 for the course IEOR 4702 taught by Professor Kou during the Spring '10 term at Columbia.
 Spring '10
 kou
 Financial Engineering

Click to edit the document details