Scribd
Upload
191 views14 pages

Manual For SOA Exam MLC.: Chapter 11. Poisson Processes. Section 11.5. Nonhomogenous Poisson Processes

This document contains an excerpt from a manual for Exam MLC of the Society of Actuaries. It defines a nonhomogeneous Poisson process as a counting process where the increments are independent but not necessarily stationary, and the mean is determined by a time-varying intensity function. Examples are provided to illustrate calculating probabilities for such processes.

Uploaded by

Amit Patil
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
191 views14 pages

Manual For SOA Exam MLC.: Chapter 11. Poisson Processes. Section 11.5. Nonhomogenous Poisson Processes

This document contains an excerpt from a manual for Exam MLC of the Society of Actuaries. It defines a nonhomogeneous Poisson process as a counting process where the increments are independent but not necessarily stationary, and the mean is determined by a time-varying intensity function. Examples are provided to illustrate calculating probabilities for such processes.

Uploaded by

Amit Patil
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/ 14

Chapter 11. Poisson processes.

Manual for SOA Exam MLC.


Chapter 11. Poisson processes.
Section 11.5. Nonhomogenous Poisson processes
c
2009.
Miguel A. Arcones. All rights reserved.

Extract from:
Arcones Manual for SOA Exam MLC. Fall 2009 Edition,
available at http://www.actexmadriver.com/

1/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

Nonhomogenous Poisson processes


Definition 1
The counting process {N(t) : t 0} is said to be a
nonhomogenous Poisson process with intensity function (t),
t 0, if
(i) N(0) = 0.
(ii) For each
R t t > 0, N(t) has a Poisson distribution with mean
m(t) = 0 (s) ds.
(iii) For each 0 t1 < t2 < < tm ,
N(t1 ), N(t2 ) N(t1 ), . . . , N(tm ) N(tm1 ) are independent r.v.s.

2/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

Nonhomogenous Poisson processes


Definition 1
The counting process {N(t) : t 0} is said to be a
nonhomogenous Poisson process with intensity function (t),
t 0, if
(i) N(0) = 0.
(ii) For each
R t t > 0, N(t) has a Poisson distribution with mean
m(t) = 0 (s) ds.
(iii) For each 0 t1 < t2 < < tm ,
N(t1 ), N(t2 ) N(t1 ), . . . , N(tm ) N(tm1 ) are independent r.v.s.
I

An nonhomogeneous Poisson process with (t) = , for each


t 0, is a regular Poisson process.

3/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

Nonhomogenous Poisson processes


Definition 1
The counting process {N(t) : t 0} is said to be a
nonhomogenous Poisson process with intensity function (t),
t 0, if
(i) N(0) = 0.
(ii) For each
R t t > 0, N(t) has a Poisson distribution with mean
m(t) = 0 (s) ds.
(iii) For each 0 t1 < t2 < < tm ,
N(t1 ), N(t2 ) N(t1 ), . . . , N(tm ) N(tm1 ) are independent r.v.s.
I

An nonhomogeneous Poisson process with (t) = , for each


t 0, is a regular Poisson process.

m(t) is the mean value function of the non homogeneous


Poisson process.
4/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

The increments of an nonhomogeneous Poisson process are


independent, but not necessarily stationary.

5/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

The increments of an nonhomogeneous Poisson process are


independent, but not necessarily stationary.

A nonhomogeneous Poisson process is a Markov process.

6/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

The increments of an nonhomogeneous Poisson process are


independent, but not necessarily stationary.

A nonhomogeneous Poisson process is a Markov process.

For each 0 s < t, N(t)


R t N(s) has Poisson distribution with
mean m(t) m(s) = s (x) dx.

7/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

The increments of an nonhomogeneous Poisson process are


independent, but not necessarily stationary.

A nonhomogeneous Poisson process is a Markov process.

For each 0 s < t, N(t)


R t N(s) has Poisson distribution with
mean m(t) m(s) = s (x) dx.

For each 0 t1 < t2 < < tm and each integers


k1 , . . . , km 0,
P{N(t1 ) = k1 , N(t2 ) = k2 , . . . , N(tm ) = km }
= P{N(t1 ) = k1 , N(t2 ) N(t1 ) = k1 k1 , . . . ,
N(tm ) N(tm1 ) = km km1 }
=

e m(t1 ) (m(t1 ))k1 e (m(t2 )m(t1 )) (m(t2 )(m(t1 ))k2 k1


k1 !
(k2 k1 )!
e (m(tm )m(tm1 )) (m(tm )m(tm1 ))km km1
,
(km km1 )!

8/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

Example 1
For a nonhomogenous Poisson process the intensity function is
given by
(
5 if t is in (1, 2], (3, 4], . . .
(t) =
3 if t is in (0, 1], (2, 3], . . .
Find the probability that the number number of observed
occurrences in the time period (1.25, 3] is more than two.

9/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

Example 1
For a nonhomogenous Poisson process the intensity function is
given by
(
5 if t is in (1, 2], (3, 4], . . .
(t) =
3 if t is in (0, 1], (2, 3], . . .
Find the probability that the number number of observed
occurrences in the time period (1.25, 3] is more than two.
Solution: N(3) N(1.25) has a Poisson distribution with mean
Z 3
Z 2
Z 3
m(3) m(1.25) =
(t) dt =
5 dt +
3 dt = 6.75.
1.25

1.25

Hence,
P{N(3) N(1.25) > 2} = 1 e 6.75 (1 + 6.75 + (6.75)2 /2)
=0.9642515816.
10/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

Let Sn be the time of the nth occurrence. Sn is an extended r.v.


with values in [0, ]. Then,
P
e m(t) (m(t))j
P{Sn > t} = P{N(t) n 1} = n1
j=0
j!
= P{Gamma(n, 1) m(t)}.
If lim m(t) = , then
t

P{Sn = } = lim P{Sn > t} = P{Gamma(n, 1) lim m(t)} = 0


t

and Sn is a r.v. The density of Sn is


fSn (t) = e m(t)

(m(t))n1 m0 (t)
(m(t))n1 (t)
= e m(t)
, t 0.
(n 1)!
(n 1)!

If lim m(t) < , then Sn is a mixed r.v. with


t

P{Sn = } = P{Gamma(n, 1) lim m(t)} > 0


t

and density of its continuous part fSn (t) =


c
2009.
Miguel A. Arcones. All rights reserved.

e m(t) (m(t))n1 (t)


,
(n1)!

Manual for SOA Exam MLC.

t 0.
11/14

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

Let Tn = Sn Sn1 be the nth interarrival time. For a


nonhomogeneous Poisson process {Tn }
n=1 are not necessarily
independent r.v.s. For 0 s t,
P{Tn+1 > t|Sn = s} = P{Sn+1 > s + t|Sn = t}
=P{N(s + t) = n + 1|Sn = t} = P{N(s + t) N(s) = 1|Sn = t}
=P{N(s + t) N(s) = 1} = e (m(s+t)m(s)) .
Notice Sn = t depends on the nonhomogeneous Poisson process
until time t. Hence, {N(s + t) N(s) = 1} and {Sn = t} are
independent.

12/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

Example 2
For a nonhomogenous Poisson process, the intensity function is
given by
(
t for 0 < t 4,
(t) =
4 for 10 < t.
If S5 = 2, calculate the probability that S6 > 5.

13/14

c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

Chapter 11. Poisson processes.

Section 11.5. Nonhomogenous Poisson processes.

Example 2
For a nonhomogenous Poisson process, the intensity function is
given by
(
t for 0 < t 4,
(t) =
4 for 10 < t.
If S5 = 2, calculate the probability that S6 > 5.
Solution: We have that
P{S6 > 5|S5 = 2} = P{N(5) = 5|S5 = 2}
= P{N(5) N(2) = 0|S5 = 2} = P{N(5) N(2) = 0}
and
Z
m(5) m(2) =

Z
t dt +

(t) dt =
2

4 dt = 10.
4

Hence, P{S6 > 5|S5 = 2} = P{N(5) N(2) = 0} = e 10 .


c
2009.
Miguel A. Arcones. All rights reserved.

Manual for SOA Exam MLC.

14/14

You might also like