Scribd
Upload
88 views2 pages

Tutorial 3

This document contains 6 problems related to risk theory and probability distributions. Problem 1 asks to calculate the expected value of a prize amount that follows a mixed Poisson distribution. Problem 2 asks to find the expected value of a random variable with a mixed binomial distribution. Problem 3 asks to calculate the median lifetime for a population with a Weibull distribution and gamma-distributed frailty. The remaining problems involve additional concepts relating to mixed distributions, moment generating functions, and deriving properties of distributions.

Uploaded by

richardchan001
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
88 views2 pages

Tutorial 3

This document contains 6 problems related to risk theory and probability distributions. Problem 1 asks to calculate the expected value of a prize amount that follows a mixed Poisson distribution. Problem 2 asks to find the expected value of a random variable with a mixed binomial distribution. Problem 3 asks to calculate the median lifetime for a population with a Weibull distribution and gamma-distributed frailty. The remaining problems involve additional concepts relating to mixed distributions, moment generating functions, and deriving properties of distributions.

Uploaded by

richardchan001
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

The University of Hong Kong

Department of Statistics and Actuarial Science

STAT3810/3906 Risk Theory I Tutorial 3


13th/14th Feb 2017
1. Bob is a carnival operator of a game in which a player receives a prize worth W = 2N if the player
has N successes, N = 0, 1, 2, . . . Bob models the probability of success for a player as follows:

Conditional on = , N has a Poisson distribution with mean


has a uniform distribution on the interval (0, 4)

Calculate E (W ).
Hint: for X Poi (), we have
MX (t) = e(e 1) .
t

2. The random variable N has a mixed distribution

with probability p, N has a binomial distribution with q = 0.5 and m = 2;


with probability 1 p, N has a binomial distribution with q = 0.5 and m = 4;

It is given that Var (N ) = 0.8125. Find E (N ).

3. (Optional) Survival time X for a population of lives follows a Weibull distribution with the
following hazard rate function
1
hX| (x|) = x2/3
3
varies over the population with a gamma distribution having parameters = 5, = 0.5.
Calculate the median future lifetime for the population.
Hint: for X (, ), we have
x/
(x/) e ,x > 0
fX (x) = x ()
0 , otherwise

MX (t) = (1 t) , t < 1/

4. Fix s 0, and define an Esscher-transformed frailty random variable s with probability density
function s
e f () , 0
fs () = M (s)
0 , otherwise

(a) Show that s has moment generating function

M (t s)
Ms (t) =
M (s)

1
(b) Define the cumulant generating function of to be

c (t) = ln [M (t)]

and use (a) to prove that

c0 (s) = E (s ) and c00 (s) = Var (s )

(c) (Optional) For the frailty model, prove that the associated hazard rate may be expressed as

hX (x) = a (x) c0 [A (x)]

where c is defined in (b). Hence, show that

h0 (x) = a0 (x) c0 [A (x)] [a (x)]2 c00 [A (x)]

(d) (Optional) Using (c), prove that if h0X| (x|) 0, then h0X (x) 0.

5. Let N have a Poisson distribution with random mean . Let the distribution of the random
variable have probability density function
(
2 ( + 1)1 ( + 1) e , > 0
u () =
0 , otherwise

(a) Obtain the unconditional probability mass function for the mixed Poisson random variable N .
(b) i. Find P (z).
ii. Hence, find PN (z).

6. [Adapted from STAT3810 Spring 2011 Exam]


Suppose that N | = Poi( + 0.5), and that the MGF of is given by
1
M (t) = .
(1 2t)3

Let pn = Pr(N = n), n = 0, 1, 2, . . ., and PN (t) be the probability generating function of N .

(a) Find PN (t).


(b) Find p0 .
(c) By considering the derivative of PN (t), derive a recursive formula that expresses pn+1 in terms
of pn and pn1 for n = 1, 2, . . ..
(d) Find p1 , p2 , p3 and p4 .

You might also like