A4-S-431F08

# A4-S-431F08 - SOLUTIONS TO ASSIGNMENT 4 ACTSC 431/831, FALL...

This preview shows pages 1–2. Sign up to view the full content.

SOLUTIONS TO ASSIGNMENT 4 – ACTSC 431/831, FALL 2008 1. The conditional distribution of X , given Θ = θ , is a Poisson distribution with mean λθ . The pgf of X is given by P X ( z ) = M Θ ( λ ( z - 1)) , where M Θ ( t ) is the mgf of Θ. Since Θ is inﬁnitely divisible, for any n = 1 , 2 ,..., there exists a mgf M n ( t ) so that M Θ ( t ) = [ M n ( t )] n . Thus, P X ( z ) = [ M n ( λ ( z - 1))] n . Since M n ( λ ( z - 1)) is still a pgf that is the pgf of a mixed Poisson distribution, in which the mixing distribution has the mgf M n ( t ). Hence, X is inﬁnitely divisible. 2. (a) Let v = Pr { X j 50 } and let I j = 1 if X j 50 and 0 if X j > 50. Note that N P * = I 1 + ... + I N L . If N L is inﬁnitely divisible, then for any n = 1 , 2 ,..., there exists a pgf P n ( z ) so that P N L ( z ) = [ P n ( z )] n . Thus, the pgf of N P * is P N P * ( z ) = P N L (1 + v ( z - 1)) = [ P n (1 + v ( z - 1))] n , which means that N P * is also inﬁnitely divisible since P n (1+ v ( z - 1)) is still a pgf that is the pgf of a compound frequency model, in which P n ( z ) is the pgf of the primary distribution and the secondary distribution is the Bernoulli distribution

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

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

## This note was uploaded on 02/02/2010 for the course ACTSC 331 taught by Professor David during the Fall '09 term at Waterloo.

### Page1 / 3

A4-S-431F08 - SOLUTIONS TO ASSIGNMENT 4 ACTSC 431/831, FALL...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online