Sie sind auf Seite 1von 58

CT6 Online Classroom Questions Handout

Page 1

Subject CT6
Statistical Methods
CT6 Online Classroom Questions Handout
Decision theory
1

ActEd
For each of the zero-sum game payoff matrices below determine the minimax solution:
(i)
A
I
-1
0

1
2

II
5
6
[2]

(ii)
I
1
0
2

1
2
3

A
II
5
3
4

III
2
1
5
[2]

(iii)
A
B

1
2

I
1
3

II
2
-4
[4]
[Total 8]

The Actuarial Education Company

IFE: 2014 Examinations

Page 2

CT6 Online Classroom Questions Handout

Subject 106, April 2003, Question 4


The loss function under a decision problem is given by:

Q1

Q2

Q3

D1

23

34

16

D2

30

19

18

D3

23

27

20

D4

32

19

19

(i)

State which decision can be discounted immediately and explain why.

[2]

(ii)

Determine the minimax solution to the problem.

[2]

(iii)

Given the following distribution P(Q1 ) = 0.25 , P (Q2 ) = 0.15 , P (Q3 ) = 0.60 ,
determine the Bayes criterion solution to the problem.

[2]
[Total 6]

ActEd
A statistician is trying to decide whether a coin is fair or biased towards tails. The
decision is to be made on whether a tail is obtained on one toss of the coin.
(i)

List the 4 possible decision functions.

[1]

If the coin is biased, the probability of obtaining a tail is 0.75. The loss function is:

statistician
(ii)

(iii)

loss
biased
fair

nature
biased
fair
2
-1
1
0

(a)

Determine the risk function for each of the 4 decision functions.

(b)

Which decision function is inadmissible?

(a)

Determine the solution using the minimax criterion.

(b)

[3]
Determine the solution using Bayes criterion, if P (fair coin) = 0.8 .
[Total 9]

IFE: 2014 Examinations

[5]

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 3

Subject CT6, April 2007, Question 4


A casino operator moving into a country for the first time must apply to the casino
regulator for a licence. There are three types of licence to choose from slots, dice and
cards each with different running costs. The casino operator has to pay a fixed
amount annually (1,300,000) to the regulator, plus a variable annual licence cost.
The variable licence cost and expected revenue per customer for each type of game are
as follows:
Variable
Licence cost

Slots
Dice
Cards

250,000
550,000
1,150,000

Expected
Revenue
per customer

60
120
160

The casino operator is uncertain about the number of customers and decides to prepare a
profit forecast based on cautious, best estimate and optimistic numbers of customers.
The figures are 14,000, 20,000 and 23,000 respectively.
(i)

Determine the annual profits under each possible combination.

[2]

(ii)

Determine the minimax solution for optimising the profits.

[2]

(iii)

Determine the Bayes criterion solution based on the annual profit given the
probability distribution:

and

P (cautious) = 0.2
P (best estimate) = 0.7
P (optimistic) = 0.1 .

The Actuarial Education Company

[2]
[Total 6]

IFE: 2014 Examinations

Page 4

CT6 Online Classroom Questions Handout

Bayesian statistics
1

Subject C2, September 1995, Question 3 (adapted)


The number of claims arising in a year from a group of policies follows a Poisson
distribution with mean m . The prior distribution for m is gamma with parameters
a = 10 and l = 2 .
Given that 8 claims arose in the last year, determine the posterior distribution for m . [4]

Subject 106, September 2001, Question 8


The number of claims per month are independent Poisson random variables with mean
l , and the prior distribution for l is exponential with mean 0.2.
(i)

Determine the posterior distribution for l given the observed values x1, , xn
of the number of claims in each of n months.

(ii)

Determine the Bayesian estimator of l


(a)
(b)

(iii)

[2]

under quadratic loss


under all-or-nothing loss

If n = 5 and

[3]

xi = 1 , calculate to 2 significant figures the Bayesian estimate of


1

l under absolute error loss.

[4]
[Total 9]

Subject C2, April 1995, Question 3 (adapted)

The number of claims registered per week has a Poisson distribution for which the
mean, l , is either 1 or 2. The prior distribution for l is given by:
P ( l = 1) = 0.4

P ( l = 2) = 0.6

Given that three claims are registered in a particular week, calculate the Bayesian
estimate of l under squared error loss, and under zero-one loss.
[4]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 5

Subject C2, September 1999, Question 12 (corrected)

The number of claims arising each month from a general insurance portfolio has a
Poisson distribution, with unknown Poisson parameter l . Claims are monitored over a
period of 50 months, and an average of 210 claims per month are observed.
(i)

It is suggested, based on knowledge gained from similar portfolios, that a


suitable prior distribution for l has mean 250 and variance 45. Using the
conjugate prior distribution, determine the posterior distribution of l and the
[6]
Bayesian estimate of l under quadratic loss.

(ii)

An alternative suggestion for estimating l is to use the number of claims


occurring on a single day, which is assumed to have a Poisson distribution with
mean l / 30 . It is suggested that the following prior distribution for l should
be used:
230 with probability 0.2

l = 250 with probability 0.5

270 with probability 0.3

If 7 claims were recorded on the most recent day for which data are available,
determine the posterior distribution for l , and hence find the Bayesian estimate
[6]
of l under quadratic loss.
(iii)

Discuss briefly the differences between the estimators in (i) and (ii), indicating
which you think is preferable.
[2]
[Total 14]

The Actuarial Education Company

IFE: 2014 Examinations

Page 6

CT6 Online Classroom Questions Handout

Estimation
1

Subject 106, April 2002, Question 10 (part)

The most recent ten claims under a particular class of insurance policy were:
35 111 201 309 442 617 843 1,330 2, 368 4, 685

(i)

Assuming that the claims came from a lognormal distribution with parameters
m and s , derive the formula for the maximum likelihood estimates of these
parameters and estimate the parameters based on the observed data.
[5]

(ii)

Assuming that the claims come from a Pareto distribution with parameters a
[3]
and l , use the method of moments to estimate these parameters.

(iii)

Assuming that the claims come from a Weibull distribution with parameters c
and g , use the method of percentiles (based on the 25th and 75th percentiles) to
estimate these parameters.
[5]
[Total 13]

ActEd

In a portfolio of motor policies, the annual number of claims for a single policy has a
Poisson distribution with parameter l . The parameter l is not the same for all policies
in the portfolio, but is modelled as a random variable with density:

g (l ) = 25l e-5l , l > 0


(i)

Show that the probability of n claims in a year, on a policy picked at random


from the portfolio, is given by:
n

G (n + 2) 1 5
P ( N = n) =
, n = 0,1, 2,3,
G (n + 1)G (2) 6 6
(ii)

[3]

Hence, obtain the mean and variance of the number of claims per annum.
[2]
[Total 5]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 7

Reinsurance
1

ActEd

Claims from a certain portfolio have a Pareto distribution with parameters = 3 and
= 500 . A retention limit of 400 is in force, with the excess of this amount on any
claim being paid by a reinsurer.

(i)

What proportion of claims involve the reinsurer?

[2]

(ii)

What is the mean amount paid by the reinsurer on all claims?

[4]

(iii)

What is the mean amount paid by the reinsurer on all claims in which it is
involved?
[2]
[Total 8]

ActEd

(i)

An insurer effects excess of loss reinsurance with retention limit M . Obtain the
distribution of the claim amounts paid by the reinsurer given that they are
referred to the reinsurer if claims amounts have an exponential distribution with
[2]
parameter l .

(ii)

An insurer introduces a policy excess (deductible) of E . Obtain the distribution


of the claim amounts now paid by the insurer if the total claim amounts have a
[2]
Pareto distribution with parameters a and l .
[Total 4]

The Actuarial Education Company

IFE: 2014 Examinations

Page 8

CT6 Online Classroom Questions Handout

Subject C2, April 1999, Question 12 (modified)

(i)

The random variable X has the lognormal distribution with density function
f ( x ) and parameters m and s . Show that for any positive integer k :
U

k
k m + k
x f ( x) dx = e

s2

[F(U k ) - F( Lk )]

where Lk =
(ii)

ln L - m

- ks and U k =

- ks .

[6]

The amount, X , of a claim, in thousands of pounds, from an insurance portfolio


has the lognormal distribution with mean 12.2 and standard deviation 16.
Consider an excess of loss reinsurance policy with a retention of 28,000 so that
the claim paid by the insurer (000) is given by X I, where:
X
XI =
28

ln U - m

X 28
X > 28

(a)

Determine the probability that a claim involves the reinsurer.

(b)

Calculate the mean and variance of the claims paid by the insurer.

(c)

Given that a claim is referred to the reinsurer, what is the conditional


expected value paid by the reinsurer?
[14]
[Total 20]

Subject 106, April 2004, Question 1

The loss severity distribution for a portfolio of household insurance policies is assumed
to be Pareto with parameters a = 3.5 , l = 1,000 .
Next year, losses are expected to increase by 5%, and the insurer has decided to
introduce a policyholder excess of 100.
Calculate the probability that a loss next year is borne entirely by the policyholder.

IFE: 2014 Examinations

[3]

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 9

Subject 106, September 2001, Question 3

A specialist motor insurer writes policies with individual excesses of 500 per claim.
The insurer has taken out a reinsurance policy whereby the insurer pays out a maximum
of 4,500 in respect of each individual claim, the rest being paid by the reinsurer. The
individual claims, gross of reinsurance and the excess, are believed to follow an
exponential distribution with parameter l .
Over the last year, the insurer has gathered the following data:
There were 5 claims which were not processed because the loss was less than the
excess.
There were 11 claims where the insurer paid out 4,500 and the reinsurer the remainder.
There were 26 other claims in respect of which the insurer paid out a total of 76,457.
Derive the loglikelihood function of l .

The Actuarial Education Company

[6]

IFE: 2014 Examinations

Page 10

CT6 Online Classroom Questions Handout

Credibility theory
1

Subject 106, September 2001, Question 7 (adapted)

Claim amounts under a particular insurance portfolio are believed to follow a Normal
distribution with variance s 12 and an unknown mean q . The insurer observes a sample
of n policies that have given rise to a claim for which the mean amount is a . The prior
distribution of q is assumed to be Normal with mean m and variance s 22 .
(i)

(ii)

(a)

State the posterior mean for q .

(b)

Show that the posterior mean of q can be expressed as a weighted


average of the prior mean and the sample mean, and derive an expression
for the weight placed on the sample mean.
[3]

An insurer believes that individual claim amounts follow a Normal distribution


with an unknown mean and a standard deviation of 210. Prior information
suggests that the mean should be assumed to follow a Normal distribution with
mean = 155 and standard deviation = 84. Over the previous year, the insurer
collected data from 15 claims where the total amount paid out was 2,456.
Calculate the credibility factor placed on the sample mean and hence, given that
the insurer wishes to add a 30% loading for profit and expenses, calculate the
premium the insurer should charge.
[2]

(iii)

Determine the limiting value of the credibility factor as each of n , s 12 and s 22


increases and briefly describe how it is affected by the insurers assumptions and
the observed data.
[3]
[Total 8]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 11

Subject 106, September 2003, Question 7 (adapted)

In a portfolio of property insurance policies, let q denote the proportion of policies on


which claims are made in the year. The value of q is unknown and is assumed to have
a beta prior distribution with parameters a and b .
Let x be the number of policies on which claims are made from a sample of n policies.
(i)

Show that the posterior mean of q can be expressed as:

Z .( x n) + (1 - Z ).m
where m is the mean of the beta prior distribution and express Z as a function
[3]
of a , b and n .
A claims analyst estimates that the mean and standard deviation of the prior distribution
of q are 0.20 and 0.25 respectively.
(ii)

Determine the values of the parameters, a and b .

[3]

From a random sample of 50 policies, a claim is made on 24% of them during the year.
(iii)

(a)

Calculate the value of Z in this case and explain what it represents.

(b)

Without performing any further calculations, explain how you would


expect the value of Z to change if:

(c)

(1)

The analyst now believes the standard deviation, s , of the prior


distribution to be 0.50.

(2)

The sample size, n , was 400.

State the limiting value of Z as s and n increase and explain what this
means.
[4]
[Total 10]

The Actuarial Education Company

IFE: 2014 Examinations

Page 12

CT6 Online Classroom Questions Handout

EBCT
1

Subject 106, April 2004, Question 7 (part)

The total amount claimed for a particular risk in a portfolio is observed for each of 5
consecutive years. An insurer decides to use Empirical Bayes Credibility, Model 1,
where the credibility premium combines the mean for the particular risk with the
estimated value of E ( m(q )) . Data from 3 risks in this portfolio over 5 years are
available. Let X ij be the claim for Risk i in year j . The table shows various
summary statistics for the observed data.
5

Risk 1
Risk 2
Risk 3

Xi

( X ij - X i )2

122
164
106

2,848
1,628
1,887

j =1

Calculate the estimated credibility factor, and calculate the credibility premium for
Risk 1.
[4]

ActEd

The table below shows the total aggregate claims, Yij , and the corresponding risk
volumes, Pij , over the past six years for the three types of pet insurance offered by a
small company:
6

Risk

Pij

54,278
68,861
1,689

362
485
78

j =1

Cat
Dog
Stick insect

Yij

j =1

(i)

Using EBCT Model 2, the credibility premium per unit of risk volume for the
coming year for cats is 148.357. Calculate the credibility premium per unit of
risk volume for the coming year for dogs and stick insects.
[7]

(ii)

Comment on the values of the credibility factors.

IFE: 2014 Examinations

[2]
[Total 9]

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 13

Subject 106, September 2002, Question 9 (part (iii))

An insurance company has insured a fleet of cars for the last four years. For year j (
j = 1,..., 4 ), let Y j and Pj be the total amount claimed and the number of cars in the

fleet, respectively. Let X j = Y j / Pj be the average amount claimed per car in year j .
Assume that the distribution of X j depends on a risk parameter q and that the
conditions of Empirical Bayes Credibility Theory Model 2 are satisfied.
The company has insured ten similar fleets over the last four years. Using the data from
these years, E[ m(q )] , E[ s 2 (q )] and V [ m(q )] are estimated to be 62.8, 106.32 and 5.8
respectively.
(a)

Calculate next years credibility premium for a fleet of cars with claims over the
last four years given below, if the fleet will have 16 cars next year.
Year
Total amount claimed
Number of cars

(b)

1
1,000
15

2
1,200
16

3
1,500
18

4
1,400
15

Explain how and why the credibility factor would be affected if the estimate of
[5]
V [ m(q )] increases, and comment on the effect on the credibility premium.
[Total 8]

The Actuarial Education Company

IFE: 2014 Examinations

Page 14

CT6 Online Classroom Questions Handout

Subject C2, April 1997, Question 13 (part (ii))

For the past five years an insurance company has insured 15 different chains of
newsagents shops against damage to their premises and stock from any cause. For
chain i , i = 1,2,,15 , and year j , j = 1,2, ,5 , the random variable Yij represents the
annual claims and Pij represents the number of shops in the chain. The sequence

RSnY ; P s UV
T
W
5

ij

ij

15

j =1 i =1

satisfies all the assumptions for Empirical Bayes Credibility Theory

Model 2. The data for the first three chains in this collective are shown in the table
below. Also shown for each of the first two chains is the credibility premium per shop
for the coming year.
Yij ; Pij
Chain

j =1

1
2
3

450; 2
2500; 3
4950; 9

220; 2
1140; 4
39600; 9

3700; 2
3600; 4
14850; 11

250; 2
3900; 4
29700; 12

380; 2
860; 5
9900; 14

Credibility
premium per
shop
750
733

(a)

Calculate the credibility premium per shop for the coming year for Chain
number 3.

(b)

Explain carefully why the credibility premium per shop for the coming year is
higher for Chain 1 than for Chain 2 even though the average annual claim per
shop is lower for Chain 1 than for Chain 2.
[11]
[Total 17]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 15

Risk models 1
1

Subject 106, September 2004, Question 2

The number of claims arising from a hurricane in a particular region has a Poisson
distribution with mean l . The claim severity distribution has mean 0.5 and variance 1.

(i)

Determine the mean and variance of the total amount of claims arising from a
hurricane.
[2]

(ii)

The number of hurricanes in this region in one year has a Poisson distribution
with mean m . Determine the mean and variance of the total amount claimed
from all the hurricanes in this region in one year.
[3]
[Total 5]

Subject 106, April 2004, Question 4 (part (ii))

A portfolio consists of two types of policies. For type 1, the number of claims in a year
has a Poisson distribution with mean 1.5 and the claim sizes are exponentially
distributed with mean 5. For type 2, the number of claims in a year has a Poisson
distribution with mean 2 and the claim sizes are exponentially distributed with mean 4.
Let S be the total amount claimed on the whole portfolio in one year. All policies are
assumed to be independent.
Derive the MGF of S and show that S has a compound Poisson distribution.

The Actuarial Education Company

[4]

IFE: 2014 Examinations

Page 16

CT6 Online Classroom Questions Handout

Subject CT6, April 2008, Question 10 (corrected)

A bicycle wheel manufacturer claims that its products are virtually indestructible in
accidents and therefore offers a guarantee to purchasers of pairs of its wheels. There are
250 bicycles covered, each of which has a probability p of being involved in an
accident (independently) in a year. Despite the manufacturers publicity, if a bicycle is
involved in an accident, there is in fact a probability of 0.1 for each wheel
(independently) that the wheel will need to be replaced at a cost of 100. Let S denote
the total cost of replacement wheels in a year.
(i)

Show that the MGF of S is given by:


pe200t + 18 pe100t + 81 p

M S (t ) =
+ 1 - p
100

(ii)

250

Show that E ( S ) = 5,000 p and var( S ) = 550,000 p - 100,000 p 2 .

[4]

[6]

Suppose instead that the manufacturer models the cost of replacement wheels as a
random variable T based on a portfolio of 500 wheels, each of which (independently)
has a probability of 0.1p of requiring replacement.
(iii)

Derive expressions for E (T ) and var(T ) in terms of p .

(iv)

Suppose p = 0.05 .
(a)

Calculate the mean and variance of S and T .

(b)

Calculate the probabilities that S and T exceed 500.

(c)

Comment on the differences.

IFE: 2014 Examinations

[2]

[5]
[Total 17]

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 17

Risk models 2
1

Subject CT6, September 2007, Question 8

The total claim amount, S , on a portfolio of insurance policies has a compound Poisson
distribution with Poisson parameter 50. Individual loss amounts have an exponential
distribution with mean 75. However, the terms of the policies mean that the maximum
sum payable by the insurer in respect of a single claim is 100.
(i)

Find E ( S ) and var( S ) .

(ii)

Use the method of moments to fit as an approximation to S :


(a)
(b)

(iii)

a normal distribution
a log-normal distribution

For each fitted distribution, calculate P ( S > 3,000) .

[7]

[3]
[3]
[Total 13]

Subject CT6, April 2007, Question 7

The total claims arising from a certain portfolio of insurance policies over a given
month is represented by

N
X
S = i =1 i

if

N >0

if N = 0

where N has a Poisson distribution with mean 2 and X1, X 2 , , X N is a sequence of


independent and identically distributed random variables that are also independent of N.
Their distribution is such that P( X i = 1) = 1/ 3 and P (X i = 2) = 2 / 3 . An aggregate
reinsurance contract has been arranged such that the amount paid by the reinsurer is
S - 3 (if S > 3) and zero otherwise.
The aggregate claims paid by the direct insurer and the reinsurer are denoted by
S I and S R , respectively.
Calculate E ( S I ) and E ( S R ) .

The Actuarial Education Company

[8]

IFE: 2014 Examinations

Page 18

CT6 Online Classroom Questions Handout

Subject 106, September 2004, Question 9 (part)

A general insurance company has a portfolio of fire insurance policies, which offer
cover for just one fire each year.
Within the portfolio, there are three types of buildings for which the average cost of a
claim and probability of a claim are given in the table below.
Type of
building

Number of Risks
Covered

Small
Medium
Large

147
218
21

Average Cost
of a Claim
(000s)
12.4
27.8
130.3

Probability
of a Claim
0.031
0.028
0.017

It is assumed that the cost of a claim has an exponential distribution, and that all the
buildings in the portfolio represent independent risks for this insurance cover.
(i)

Show that the mean and standard deviation of annual aggregate claims from this
portfolio of insurance policies are 272,715 and 150,671, respectively and
obtain the cumulant generating function.
[4]

(ii)

Using a normal distribution to approximate the distribution of annual aggregate


claims, calculate the premium loading factor necessary such that the probability
that annual aggregate claims exceed premium income is 0.05.
[3]

(iii)

Market conditions dictate that the insurer can only charge a premium which
includes a loading of 25%. Calculate the amount of capital that the insurer must
allocate to this line of business in order to ensure that the probability that annual
aggregate claims exceed premium income and capital is 0.05 (again using a
normal approximation).
[2]

(iv)

Comment on the assumption of independence and the use of a normal


approximation, in relation to your answers to (ii) and (iii).
[4]
[Total 13]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 19

Ruin theory
1

ActEd
S (t ) is a compound Poisson process with Poisson parameter 40, and claim size
distribution which is log N (5, 4) .

(i)

Find E[S(10)] and var[S (10)] .

(ii)

The initial surplus is 400,000, and the rate of premium income is 41,000 per unit
time. Assuming that U (t ) can be approximated by a normal distribution, find
[3]
the probability that U (10) < 0 .
[Total 6]

[3]

Subject CT6, September 2007, Question 5

Aggregate annual claims on a portfolio of insurance policies have a compound Poisson


distribution with parameter l . Individual claim amounts have an exponential
distribution with mean 1.
The insurer calculates premiums using a loading of a (so that the annual premium is
1 + a times the annual expected claims) and has initial surplus U .
(i)

Show that if the first claim occurs at time t, the probability that this claim causes
ruin is e -U e - (1+a ) l t .

[3]
e -U
.
2 +a

(ii)

Show that the probability of ruin on the first claim is

(iii)

Show that if the insurer wishes to set a such that the probability of ruin at the
first claim is less than 1% then it must choose a > 100e -U - 2 .

The Actuarial Education Company

[4]

[2]
[Total 9]

IFE: 2014 Examinations

Page 20

CT6 Online Classroom Questions Handout

ActEd

The aggregate daily claims (000s) on a certain portfolio of policies occur according to
a Poisson process with parameter 30. Individual claim sizes (000s) have a gamma
distribution with mean 40 and variance 800. The insurer adds a premium loading factor
of 50%.

(i)

Calculate the value of the adjustment coefficient.

[4]

(ii)

Hence calculate the minimum amount of capital needed to ensure that the
probability of ultimate ruin is less than 0.1%.
[1]

(iii)

Calculate the expected daily profit on this portfolio of policies.

[1]
[Total 6]

Subject 106, September 2004, Question 8 (part (ii))

Claims arrive as a Poisson process rate l , and the premium loading factor is 25%.
(a)

Determine to one significant figure the adjustment coefficient R* if each claim


is exactly 100.

(b)

If claims are exponentially distributed with mean 100, the adjustment


coefficient Rexp is 0.002. Compare R* with Rexp and comment.

IFE: 2014 Examinations

[3]

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 21

ActEd

Claims arrive as a Poisson process with rate . Individual claim sizes are exponentially
distributed with mean 100. The insurer uses a premium loading factor of 0.2.
A proportional reinsurance arrangement has been proposed, with a retained proportion
of . The reinsurer uses a security loading of 0.4.
(i)

State the range of possible values of a such that the probability of ruin is less
than 1.
[2]

(ii)

(a)

Show that the adjustment coefficient, R , is given by:


R=

(iii)

2a - 1
100a (7a - 1)

(b)

Hence, find the value of a that maximises R .

(c)

Determine the expected profit per unit time and the upper bound for the
probability of ultimate ruin for the value of a calculated in part (ii)(b).
[10]

Compare the profit and the probability of ultimate ruin in part (ii)(c) with those
where no reinsurance is effected.
[2]
[Total 14]

The Actuarial Education Company

IFE: 2014 Examinations

Page 22

CT6 Online Classroom Questions Handout

Generalised linear models


1

ActEd

(i)

(ii)

Show that each of the following distributions are members of the exponential
family:
(a)

Yi ~ Poi( mi )

(b)

Yi ~ Exp(li )

(c)

Yi ~ N ( mi ,s 2 )

(d)

Yi = Zi n where Zi ~ Bin(n, mi )

[8]

For each distribution in part (i), use the properties of exponential families to
determine their mean, variance and variance function.
[8]
[Total 16]

Subject CT6, April 2007, Question 10 (part)

(i)

The gamma distribution with mean m and variance m 2 a has density function:

f ( y) =

aa

m G (a )

ya -1 e - ya / m

( y > 0)

(a)

Show that this may be written in the form of an exponential family.

(b)

Use the properties of exponential families to confirm that the mean and
variance of the distribution are m and m 2 a .

IFE: 2014 Examinations

[9]

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 23

The next six questions refer to the following generalised linear model:

the number of claims Yi on policy i (i = 1, ,15) has a Poisson distribution with


unknown mean mi .

The number of claims observed in the last year on 15 policies were as follows:
i

10 11 12 13 14 15

yi

ActEd

(i)

Show that the log-likelihood function for this model, based on observations
{ yi : i = 1,...,15} is given by:
15

ln L( mi ) = { yi ln mi - mi + c}

where c is a constant .

[1]

i =1

(ii)

Identify the canonical link function associated with the Poisson model from the
Tables.
[1]

ActEd

The insurance company proposes a simple model (Model A) with linear predictor:

hi = a

for i = 1,...,15

(i)

Describe in words what this model represents.

(ii)

Use the canonical link function to show that the log-likelihood in terms of a is
given by:
15

[1]

ln L(a ) = a yi - ea + c
i =1

(iii)

(iv)

Hence,

show

a = ln

15
y
i =1 i

that

the

maximum

15 = -0.3102 .

State the fitted values, m i , for this model.

[1]

likelihood

estimate

for

is
[1]
[1]

[Total 4]

The Actuarial Education Company

IFE: 2014 Examinations

Page 24

CT6 Online Classroom Questions Handout

ActEd

The insurance company proposes a second model (Model B) with linear predictor:
a for i = 1,...,10
hi =
b for i = 11,...,15

(i)

Describe in words what this model represents.

[1]

(ii)

Write down the log-likelihood function for Model B and derive maximum
likelihood estimates for a and b .
[2]

(iii)

State the fitted values, m i , for this model.

[1]
[Total 4]

ActEd

The insurance company proposes a third model (Model C) with linear predictor:

hi = a i for i = 1,...,15
(i)

Describe in words what this model represents.

[1]

(ii)

Derive the maximum likelihood estimates for a i for i = 1, ,15 .

[2]

(iii)

State the fitted values, m i , for this model.

[1]
[Total 4]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 25

ActEd

(i)

Describe what is meant by the saturated model.

(ii)

Write down the log-likelihood function of the saturated model for the data in the
previous question in terms of yi only.
[1]

(iii)

(a)

Define the scaled deviance and describe what it measures.

(b)

Show that the scaled deviances for Models A, B and C are:


20.01

12.89

[1]

(Assume that yi log yi = 0 for yi = 0 ).


(iv)

[7]

By performing a chi-squared test, determine whether:


(a)

Model B is a significant improvement over Model A

(b)

Model C is a significant improvement over Model B.

[2]
[Total 11]

ActEd

(i)

(ii)

(iii)

Show that the deviance residual for y11 :


(a)

under Model A is 0.2949

(b)

under Model B is -0.5099 .

[2]

Show that the Pearson residual for y11 :


(a)

under Model A is 0.3114

(b)

under Model B is -0.4743 .

[2]

In Model B, the maximum likelihood estimate of b * = b - a is b * = 1.674 and


the estimated standard error of the corresponding estimator is 0.677. Interpret
this result.
[1]
[Total 5]

The Actuarial Education Company

IFE: 2014 Examinations

Page 26

CT6 Online Classroom Questions Handout

ActEd

A statistician is using generalised linear modelling to try to estimate the probability of


lives in Country C developing a particular medical condition. He believes that the
relevant covariates are the region in which a person lives, socio-economic group and
age.
For the purposes of the investigation, the country has been divided into 4 regions.
There are 5 socio-economic groups.
The statistician is considering a linear predictor of the form:

h = ai + b j + g x
where i denotes region ( i = 1,..., 4 ), j denotes socio-economic group ( j = 1,...,5 ) and
x denotes age. He has fitted a binomial model to a set of relevant data and has obtained
the following estimates of the parameters.

a1 = -2.3975

a 2 = -2.3118

a 3 = -2.7375

a 4 = -2.6562

b1 = 0

b 2 = 0.1242

b 3 = 0.3894

b 4 = 0.4665

b 5 = 0.6616

g = 0.0012
(i)

Explain why the statistician has chosen a binomial model and write down the
canonical link function.
[2]

(ii)

Use the canonical link function to predict the probability of each of the
following lives developing the condition.

(iii)

(a)

Life X, who is aged 40, lives in Region 1 and belongs to socio-economic


group 2

(b)

Life Y, who is aged 42, lives in Region 3 and belongs to socio-economic


group 1.
[4]

Comment on the relative levels of risk for Life X and Life Y.

IFE: 2014 Examinations

[2]
[Total 8]

The Actuarial Education Company

CT6 Online Classroom Questions Handout

10

Page 27

Subject 106, April 2004, Question 9 (part (ii))

Let Yij be the number of accidents on a particular motorway in the j th quarter of


year i , i = 1, 2,3 , j = 1, , 4 . Suppose that Yij has a Poisson distribution with mean mij
.
Three models are shown below.

Model 1

log mij = m

266.35

Degrees of
Freedom
11

Model 2

log mij = a i

202.19

Model 3

log mij = a i + b j

10.68

Deviance

11

(a)

Interpret each of these models.

(b)

Determine which model you would recommend, giving your reasons.

[7]

ActEd

A generalised linear model is being used to estimate the expected future lifetime of
individuals aged exactly 25. The following covariates are used:

(i)

A
Si

average number of cigarettes smoked per day


average number of units of alcohol consumed per week
sex ( i = male, female)

Oj

occupation ( j = 1, 2, 3, 4 representing stress and risk levels)

Write the parameterised form of the linear predictor for the following models:
(a)

(ii)

cigarettes

(b)

(cigarettes)2

(c)

occupation

[3]

Write the parameterised form of the linear predictor for the following models:
(a)
(c)
(e)

cigarettes + (cigarettes)2
cigarettes + sex
sex + occupation

The Actuarial Education Company

(b)
(d)
(f)

cigarettes + alcohol
alcohol + occupation
[6]
cigarettes + sex + occupation
[Total 9]

IFE: 2014 Examinations

Page 28

12

CT6 Online Classroom Questions Handout

ActEd

(i)

What is an interactive effect between two covariates?

(ii)

The average effect on life expectancy of smoking 20 cigarettes a day and/or


drinking 21 units a week are shown in the table below:
Covariates
Smoker only
Drinker only
Smoker and drinker

[1]

Reduction in life expectancy


5 years
2 years
10 years

Explain in words what the following represent and relate that to a reduction in
life expectancy:
(a)
(iii)

(b)

smoker * drinker

[2]

Using the covariates from 11, write the parameterised form of the linear
predictor for the following models:
(a)
(b)
(c)

(iv)

smoker drinker

cigarettes + alcohol + cigarettesalcohol


cigarettes + sex + cigarettessex
sex + occupation + sex occupation

[3]

Using the covariates from 11, write the parameterised form of the linear
predictor for the following models:
(a)
(b)
(c)

cigarettes * alcohol + sex


cigarettes * sex + alcohol
sex * occupation * cigarettes

IFE: 2014 Examinations

[3]
[Total 9]

The Actuarial Education Company

CT6 Online Classroom Questions Handout

13

Page 29

Subject CT6, April 2007, Question 10 (part)

(ii)

Explain the difference between a continuous covariate and a factor.

[3]

(iii)

A company is analysing its claims data on a portfolio of motor policies, and uses
a gamma distribution to model the claim severities. The company uses three
rating factors:
policyholder age (as a continuous variable)
policyholder gender
vehicle rating group (as a factor).

(a)

Write down the form of the linear predictor when all rating factors are
included as main effects.

(b)

State how the linear predictor changes if an interaction between


policyholder age and gender is included.
[4]
[Total 7]

The Actuarial Education Company

IFE: 2014 Examinations

Page 30

CT6 Online Classroom Questions Handout

Run off triangles


1

ActEd

The figures below give the claim payments made during the calendar years 2007-2009
for a certain portfolio of general insurance policies:

Claim payments made


during year (000)

Accident
year

Development year
0

2007

320

460

110

2008

350

410

2009

400

Estimates of past and future inflation are given below:


Annual claim inflation
rate (past)

Annual claim inflation


rate (future)

2007/08

5%

2009/10

3%

2008/09

4%

2010/11

4%

Use the inflation adjusted chain ladder method to estimate the total amount outstanding
for future claims arising from accident years 2008 and 2009.
[6]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 31

Subject CT6, September 2006, Question 6

The table below shows cumulative paid claims and premium income on a portfolio of
general insurance policies.

Underwriting
year

Development Year
0

2002

38,419

77,112

91,013

2003

31,490

78,504

2004

43,947

Premium
income
120,417
117,101
135,490

(i)

Assuming an ultimate loss ratio of 93% for underwriting years 2003 and 2004,
calculate the Bornhuetter-Ferguson estimate of outstanding claims for this
triangle.
[8]

(ii)

State the assumptions underlying this estimate.

The Actuarial Education Company

[2]
[Total 10]

IFE: 2014 Examinations

Page 32

CT6 Online Classroom Questions Handout

Subject CT6, April 2007, Question 5

The delay triangles given below relate to a portfolio of motor insurance policies.
The cost of claims settled during each year is given in the table below:
(Figures in 000s)

Accident
Year

Development Year
0

2004

4,144

694

183

2005

4,767

832

2006

5,903

The corresponding number of settled claims is as follows:

Accident
Year

Development Year
0

2004

581

75

28

2005

626

71

2006

674

Calculate the outstanding claims reserve for this portfolio using the average cost per
claim method with grossing-up factors, and state the assumptions underlying your
result.
[7]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 33

Time series (part 1)


Time series processes

A time series is a stochastic process, { X t : t J } , with a continuous state space, X t S ,


and discrete time set J . A time series can be univariate or multivariate.
Covariances refresher

Give formulas for, or simplify the following:


1.

cov( X , Y )

2.

cov ( X , c )

3.

cov ( 2 X ,3Y )

4.
5.
6.
7.
8.

cov(2 X + 1, 5 - 3Y )
cov( X , X )
cov( aX + b, cY + d )
cov( X , Y + Z )
corr( X , Y )

If { X t } denotes a time series defined at integer times and {Zt } is white noise with
variance s 2 (and mean 0), calculate each of the following:
1.

cov( Z 2 , Z3 )

2.

cov( Z3 , Z3 )

3.

cov( X 2 , Z3 )
ie what is the connection between future white noise ( Z3 ) and the current
observed time series ( X 2 ) ?

4.

cov( Z1 + Z 2 , Z1 + Z3 )

5.

cov(0.5Z1 + Z 2 , 0.5Z 2 + Z3 )

6.

var( Z1 + Z 2 )

The Actuarial Education Company

IFE: 2014 Examinations

Page 34

CT6 Online Classroom Questions Handout

Backward shift operator B

Shifts a process, X t , backwards:


BX t = X t -1
Note: B has no effect on constants, eg B m = m
Example:
X t - 3 X t -1 + 2 X t - 2 = et
Strict and weak stationarity

A time series is strictly stationary if all the statistical properties are unchanged over
time.
For a weakly stationary time series, we require that E ( X t ) and var( X t ) are constant,
and that the covariances are the same for the same lags:

cov( X ti , X t j ) = cov( X ti + k , X t j + k )
Why do we want a time series to be stationary?
Indeterminism

A time series is purely indeterministic if knowledge of X1, , X n is less useful in


predicting X N as N . This excludes purely deterministic processes like 0,1,0,1,
What happens to corr( X t , X t + k ) as k ? How does this help us?
Note: If an exam question states stationary time series it means weakly stationary and
purely indeterministic.

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 35

Invertibility

A time series is invertible if we can calculate the white noise terms (residuals) from
observed data values by inverting the formula for the process.
Examples:
X t = 0.8 X t -1 + et
X t = et + 0.6et -1
Why do we want a time series to be invertible?
Markov property

A time series has the Markov property if we can predict the future development of a
time series from its present state alone. In the course this is formerly expressed as the
process probabilities depend only on the most recent value:

P( X t A | X t1 = x1, , X tm = xm ) = P( X t A | X tm = xm )
Examples:
X t = 0.8 X t -1 + et
X t = 0.8 X t -1 - 0.3 X t - 2 + et
X t = et + 0.6et -1
Characteristic polynomials

1.

Write the formula for the time series in terms of the backwards shift operators:
f ( B) X t = q ( B)et

2.

Replace B s by l s to obtain the 2 characteristic polynomials


f ( l ) and q ( l )

Test for stationarity

3a.

If all roots of f ( l ) = 0 satisfy l > 1 then stationary

Testing for invertibility

3b.

If all roots of q ( l ) = 0 satisfy l > 1 then invertible

The Actuarial Education Company

IFE: 2014 Examinations

Page 36

CT6 Online Classroom Questions Handout

Examples:
Check stationarity and invertibility of:
12 X t = 10 X t -1 - 2 X t - 2 + 12et - 11et -1 + 2et - 2
X t = 0.8 X t -1 + et
X t = et + 0.6et -1
Autocovariance Function

Covariance between X t s of a stationary random process:

g 0 = var( X t )
g k = cov( X t , X t + k )
Note: if process is not stationary, then covariances g k (t ) would depend on t and k .
Autocorrelation Function (ACF)

Correlation between X t s of a stationary random process:

rk = corr( X t , X t + k )

- 1 rk 1

Note: rk 0 as k for purely indeterministic processes.


What is rk expressed in terms of g k ?
Partial Autocorrelation Function (PACF)

Conditional correlation of X t + k with X t given X t +1, , X t + k -1 , ie how much the


variance of X t + k is due to just X t .

f1 = r1,

r2 - r12
f2 =
,
1 - r12

IFE: 2014 Examinations

fk given on page 40 of Tables

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 37

MA(q)

A moving average process of order q is a weighted average of the past q white noise
terms (plus a new white noise term):

X t = et + b1et -1 + + b q et - q

(zero mean)

X t = m + et + b1et -1 + + b q et - q

(mean m )

Always stationary
rk cuts off for k > q

fk decays as k

Not Markov
Do the test for invertibility

AR(p)

An autoregressive process of order p depends on the previous p values (plus just one
white noise term):

X t = a1 X t -1 + + a p X t - p + et
X t = m + a1( X t -1 - m ) + + a p ( X t - p - m ) + et

Always invertible
rk decays as k

fk cuts off for k > p

Not Markov unless p = 1

Do the test for stationarity

The Actuarial Education Company

(zero mean)
(mean m )

IFE: 2014 Examinations

Page 38

CT6 Online Classroom Questions Handout

Subject C2, April 1999, Question 6 (adapted)

Yt is a moving average process given by:


Yt = 0.5Zt + 0.1Zt -1 - 0.4 Zt - 3
where {Zt } are independent random variables, each with mean 0 and variance s 2 .
(i)

Calculate the first three autocorrelations, r1, r2 and r3 .

[5]

(ii)

State, without calculation, the values of rk , k > 3 .

[1]
[Total 6]

Subject 103, April 2000, Question 7

(i)

(a)

Calculate the autocovariance function {g k : k 0} and autocorrelation


function {rk : k 0} of a first-order Moving Average process:
X t = m + et + b1et -1
where {et : t 0} is a sequence of uncorrelated, zero-mean random
variables with common variance s e2 .

(b)

(ii)

State the conditions on the values of the parameters such that the process
is invertible.
[5]

A sequence of observations x1, x2 , , xn has sample variance g0 = 14.5 , sample


lag-1 autocovariance g1 = 5.0 . Show that there is more than one first-order
moving average process which can be fitted to these data, but verify that only
one of the fitted processes is invertible.
[4]
[Total 9]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 39

Subject 103, September 2001, Question 3

A stationary stochastic process {Yt : t = 0,1,} satisfies the relationship:

Yt = m + 0.8 (Yt -1 - m ) - 0.4 (Yt - 2 - m ) + et


where

{et : t = 0,1,}

is a sequence of independent, zero-mean Normal random

variables with common variance s 2 .


(i)

Calculate the autocorrelation function, rk , and the partial autocorrelation


function, fk , of Y for k = 1 and 2.

(ii)

[5]

State, without performing additional calculations, what you would expect to find
if you were to calculate rk and fk for larger values of k .
[2]
[Total 7]

Subject C2, September 1996, Question 2 (adapted)

An autoregressive process of order 2 is defined by:


Yt - 0.8Yt - 2 = Zt
where {Zt } is a white noise process.

Obtain the values of the autocorrelation

coefficients r1 and r2 .

[3]

Subject 103, September 2004, Question 7 (part, adapted)

Consider the second order autoregressive process:


X t = 0.6 X t -1 + 0.3 X t - 2 + et
where {et : t 1} is white noise process with variance s 2 .
(a)

Determine whether the process can be stationary.

(b)

State, with a reason, whether the process possesses the Markov property.

(c)

700 2
600 2
s and g 1 = 169
s , and find the value of g 2 .
Show that g 0 = 169

The Actuarial Education Company

[8]

IFE: 2014 Examinations

Page 40

CT6 Online Classroom Questions Handout

AR(p) stationarity explored

We can express an AR (1) as a summation of white noise terms:


X t = a X t -1 + et = a (a X t - 2 + et -1 ) + et = a 2 X t - 2 + a et -1 + et
= ...
t -1

= a X 0 + a j et - j
t

j =0

From this we can see that:

E( X t ) = a t E( X 0 )

var( X t ) = a 2t var( X 0 ) +

1 - a 2t 2
s
1-a 2

If we assume the time series has infinite history then we obtain:

Xt =

a j et - j
j =0

with E ( X t ) = 0 and, if | a | < 1 then var( X t ) =

s2
.
1-a 2

ARMA(p, q)

A process that is a combination of an AR ( p ) and an MA ( q ) :


X t = a1 X t -1 + + a p X t - p + et
+ b1et -1 + + b q et - q

(zero mean)

X t = m + a1 ( X t -1 - m ) + + a p ( X t - p - m ) + et
+ b1et -1 + + b q et - q

rk decays as k

fk decays as k

Not Markov unless p = 1 and q = 0

Do the test for stationarity


Do the test for invertibility

IFE: 2014 Examinations

(mean m )

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 41

Subject CT6, April 2005, Question 4

Yt , t = 1, 2,3, is a time series defined by:


Yt - 0.8Yt -1 = Zt + 0.2 Zt -1
where Z t , t = 0,1, is a sequence of independent zero-mean variables with common
variance s 2 . Derive the autocorrelation rk , k = 0,1, 2, .

[6]

Difference operator

Finds the 1st difference of a process, X t :


X t = (1 - B) X t = X t - X t -1
Note: = 1 - B
Examples:
X t = 3 X t -1 - 3 X t - 2 + X t - 3 + Zt
6 X t = 17 X t -1 - 17 X t - 2 + 7 X t - 3 - X t - 4 + Zt
Integrated I ( d )

A process, X t , is integrated of order d , if:


X t not stationary and Yt = d X t is stationary
ARIMA(p, d, q)

A series, such that the d th difference:

Yt = d X t is a stationary ARMA( p, q )

The Actuarial Education Company

IFE: 2014 Examinations

Page 42

CT6 Online Classroom Questions Handout

Example:
Classify the following processes:
X t - 0.6 X t -1 - 0.3 X t - 2 - 0.1X t - 3 = et - 0.25et -1
2 X t = 7 X t -1 - 9 X t - 2 + 5 X t - 3 - X t - 4 + et + et - 2
6 X t = 17 X t -1 - 17 X t - 2 + 7 X t - 3 - X t - 4 + Zt

Multivariate Time Series

A time series that depends on more than one variable. This is as opposed to a univariate
time series which is a time series with only one variable in it (white noise doesnt count
as a variable). For example AR ( p ), MA( p ), ARMA( p, q ) and ARIMA( p, d , q ) are all
univariate. Multivariate time series can be written in vector (VARMA) form:
Example:
X t = 0.7 X t -1 - 0.1Yt -1 + et
Yt = 0.2 X t -1 - 0.3Yt -1 + et
Is this example time series:
a)
b)
c)

stationary (eigenvalues < 1 in magnitude)?


invertible?
Markov?

Cointegrated

This means that the individual processes are not stationary but when combined in some
way, they do produce a stationary series.
Two time series processes, X t and Yt are cointegrated if:

X t , Yt are both I (1)

a X t + b Yt is stationary, where (a b ) 0 , where (a b ) is called the


cointegrating vector.

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 43

Bilinear models

X t + a ( X t -1 - m ) = m + et + b et -1 + b ( X t -1 - m ) et -1
Threshold AR models

a1 ( X t -1 - m ) + et
Xt = m +
a 2 ( X t -1 - m ) + et

if X t -1 d
if X t -1 > d

Random coefficient AR models

X t = m + a t ( X t -1 - m ) + et , a t random
ARCH models
p

X t = m + et a 0 + a k ( X t - k - m )

k =1

Note: ARCH has now been tested twice (Sept 2007 and Sept 2008).

The Actuarial Education Company

IFE: 2014 Examinations

Page 44

CT6 Online Classroom Questions Handout

Time series (part 2)


Box Jenkins

Tentative identification of a model from the ARIMA class


Estimation of parameters in the identified model
Diagnostic checks
differencing
least squares trend
removal (apply the
model xt = a + bt + yt )

linear trend

remove trends and cycles

exponential trend

seasonal/periodic

take logs
method of moving
averages
seasonal differencing
method of seasonal
means

difference to minimise s d2
Identify
p, d and q

identify d

MA( q )
AR ( p )

ARMA( p, q )

(the sample

variance of the process z ( d ) )


if rk tends towards 0 slowly, go to the next
difference
rk cuts off (ie within 95% CI) when k > q ,

fk decays
fk cuts off (ie within 95% CI) when k > p ,
rk decays
if not MA( q ) or AR ( p ) then ARMA( p, q )
start with ARMA(1,1) and work up to more
complicated models if fit poor
AIC only add new parameters if relative
reduction in sum of squares of residuals
-2

Estimate the
parameters

method of moments

e n
solve rk = rk

method of least squares

minimise

method of maximum
likelihood

need to assume a distribution so may not be


easy

IFE: 2014 Examinations

et2

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 45

First, calculate the residuals


graph of residuals

shouldnt be a pattern
with t

95% CI for ACF of


residuals

1.96 n
should be no more than
5% outside this CI

portmanteau test
(Ljung-Box test):
ACF of the residuals is 0

Tables pg 42
one-tailed test

turning point test:


residuals (or ACF of
residuals) are patternless

Tables pg 42
assume normal
distribution
two-tailed test (with
continuity correction)

Check the fit


of the model.
The principle
is that if
ARMA( p, q )
is a good
model then
the residuals
are white
noise

Subject 103, April 2002, Question 5 (part)

The ratio of claims to premium income is calculated annually by a division of a large


insurance company over a period of 30 years. The observed values are plotted against
time in Figure 1a, with the sample autocorrelation function (ACF) plotted in Figure 1b;
the dotted lines indicate the cutoff points for significance at the 5% level.
Figure 1a
Ratio of claims to premium income
1.200
1.100

Ratio

check white noise


(needs to be
independent and
stationary ie the
constant mean
and variance)

1.000
0.900
0.800
0.700
1

11 13 15 17 19 21 23 25 27 29
Year, t

Figure 1b

The Actuarial Education Company

IFE: 2014 Examinations

Page 46

CT6 Online Classroom Questions Handout

Autocorrelation Function for Ratio

Autocorrelation, rk

0.6
0.4
0.2
0
-0.2 0

-0.4
-0.6
Lag, k

(i)

Explain which feature of the Figures indicates that differencing is not required in
order to obtain a stationary series.
[1]

(ii)

On the basis of the sample ACF, rk , the companys analyst decides to fit a firstorder autoregressive model to the data. State, with reasons, whether you
consider this to be a reasonable decision and indicate what additional plot you
would require in order to make a firmer recommendation.
[3]

(iii)

The model is fitted and the residuals calculated. The sample ACF of the
residuals is shown in Figure 1c. State what conclusions you would draw from
the plot.
[1]
Figure 1c

Autocorrelation, rk

Autocorrelation Function for Residuals


0.5
0.4
0.3
0.2
0.1
0
-0.1 0
-0.2
-0.3
-0.4
-0.5

Lag, k

[Total 5]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 47

Subject CT6, September 2008, Question 10 (part)

From a sample of 50 consecutive observations from a stationary process, the table


below gives values for the sample autocorrelation function (ACF) and the sample partial
autocorrelation function (PACF):
Lag
1
2
3

ACF
0.854
0.820
0.762

PACF
0.854
0.371
0.085

The sample variance of the observations is 1.253.


(i)

Suggest an appropriate model, based on this information, giving your reasoning.


[2]

(ii)

Consider the AR (1) model:


Yt = a1Yt -1 + et
where et is a white noise error term with mean zero and variance s 2 .
Calculate method of moments (Yule-Walker) estimates for the parameters of a1
and s 2 on the basis of the observed sample.

The Actuarial Education Company

[4]
[Total 6]

IFE: 2014 Examinations

Page 48

ActEd

The monthly sales (in kilolitres) of red wine by Australian winemakers from January
1980 through to October 1991 are shown in the graph below:
3000
2500
2000
Sales

1500
1000
500
0
0

10

20

30

40

50

60

70

80

90

100

110

120

130

140

150

Month

(i)

(a)

Give two features which indicate that the time series is non-stationary.

(b)

Describe how each of these features can be removed.

[3]

The data is logged and seasonally adjusted and the statistician tries to fit an
ARIMA( p, d , q ) model to the adjusted data:

(ii)

Xt

X t

2 X t

3 X t

sample
variance
r1

0.0791

0.0159

0.0471

0.1565

0.8805

-0.4774

-0.6672

-0.7453

r2

0.8541

0.0433

0.1918

0.2998

r3

0.8245

-0.0374

0.0010

-0.0115

r4

0.8025

-0.0920

-0.1148

-0.1316

r5

0.8110

0.1810

0.1967

0.1985

r6

0.7815

-0.1284

-0.1409

-0.1456

SACF

CT6 Online Classroom Questions Handout

Use the data in the table to choose the most appropriate value for d . State your
reasons clearly.
[2]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 49

After being differenced an appropriate number of times, the statistician examines the
SACF and SPACF:

0.5
0.4
0.3
0.2
0.1
0
-0.1
-0.2
-0.3
-0.4
-0.5

SACF

Lag
1

10

0.5
0.4

SPACF

0.3
0.2
0.1

Lag

0
-0.1

-0.2
-0.3
-0.4
-0.5

(iii)

Using the principle of parsimony, suggest appropriate values of p and q .

(iv)

The statistician fits an ARIMA(0,1,1) model and examines the residuals:

[2]

Ljung-Box statistic p -value = 0.76836


Turning points test p -value = 0.59190
Interpret these results.

The Actuarial Education Company

[2]
[Total 9]

IFE: 2014 Examinations

Page 50

CT6 Online Classroom Questions Handout

Forecasting (Box Jenkins)

replace all unknown parameters by their estimated values


replace the random variables X1,..., X n by their observed values x1,..., xn

replace the random variables

X n +1,..., X n + k -1 by their forecast values

xn (1),..., xn (k - 1)

replace the innovations e1,..., en by the residuals e1,..., en

replace the random variables en +1,..., en + k -1 by 0 (their expectations)

xn (k ) is the estimate of the expected value of X n + k (given the observations up to X n ) .


Example:
X n = a1 X n -1 + a 2 X n - 2 + en + b1en -1
Forecasting (Exponential smoothing)
xn (1) = a xn + (1 - a ) xn -1 + (1 - a ) 2 xn - 2 +

This is a weighted average of the past values but there is less emphasis on older values.
Rearrangements: xn (1) = a xn + (1 - a ) xn -1 (1) or xn (1) = xn -1(1) + a [ xn - xn -1(1)]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 51

Subject CT6, April 2007, Question 8 (corrected, extended)

A modeller has attempted to fit an ARMA ( p, q ) model to a set of data using the BoxJenkins methodology. The plot of residuals based on this proposed fit is shown below.
Residuals based on fitted model
120
100
80
60
40
20
0
-20
-40
-60
-80
1

6 11 16 21 26 31 36 41 46 51 56 61 66 71 76 81 86 91 96
Time

(i)

(ii)

Under the assumptions of the model, the residuals should form a white noise
process.
(a)

By inspection of the chart, suggest two reasons to suspect that the


residuals do not form a white noise process.

(b)

Define what is meant by a turning point.

(c)

Perform a significance test on the number of turning points in the data


above. (There are 100 points in the data and 59 turning points.)
[6]

On your suggestion, the original fitted model is discarded, and re-parameterised


to:
X n + 2 = 5 + 0.9( X n +1 - 5) + en + 2 + 0.5en
The sample autocorrelations of the 100 residuals at lags 1, 2, 3, 4 and 5 were
calculated to be:
0.10 +0.20 +0.05 +0.04 0.05
Carry out a portmanteau (Ljung and Box) test and state your conclusion.

The Actuarial Education Company

[3]

IFE: 2014 Examinations

Page 52

(iii)

CT6 Online Classroom Questions Handout

Given the following observations:


x99 = 2 x100 = 7 e99 = -0.7 e100 = 1.4
(a)

Use the Box-Jenkins methodology to calculate the forward estimates


x100 (1) , x100 (2) and x100 (3) .

(b)

The simplest form of exponential smoothing used at time 99 gave a


forecast for x100 of 5.2. Assuming the smoothing parameter is equal to
0.2, find the forecast for x101 .

[6]
[Total 15]

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 53

Monte Carlo simulation


Inverse transform method (continuous random variable)

1.
2.

Generate a random number u from U (0,1)


Return:

x = F -1 (u )
Inverse transform method (discrete random variable)

1.

Generate a random number u from U (0,1)

2.

Return xi such that:


F ( xi -1 ) < u F ( xi )

where the discrete random variable, X , can take only the values x1, x2 , , xN , (
x1 < x2 < < xN )
Box-Muller algorithm (page 39 Tables)

1.

Generate 2 random numbers u1 and u2 from U (0,1)

2.

Return:

z1 = -2ln u1 cos(2p u2 ) and z2 = -2ln u1 sin(2p u2 )


Polar algorithm (page 39 Tables)

1.

Generate 2 random numbers u1 and u2 from U (0,1)

2.

Set v1 = 2u1 - 1 , v2 = 2u2 - 1 and s = v12 + v22


(ie v1 and v2 are random variates from U ( -1,1) )

3.

If s > 1 go back to step 1, otherwise return:


z1 = v1

-2ln S
-2ln S
and z2 = v2
S
S

The Actuarial Education Company

IFE: 2014 Examinations

Page 54

CT6 Online Classroom Questions Handout

Acceptance/rejection method

Scales up h( x) , so that the area under Ch ( x ) includes all of the area under f ( x ) :
C = max
all x

f ( x)
h( x )

1.

Generate a random number u1 from U (0,1)

2.

Use u1 to generate a random variate x from h( x)

3.

Generate a random number u2 from U (0,1)

4.

If u2 < g ( x ) =

f ( x)
then return x otherwise repeat.
Ch ( x )

IFE: 2014 Examinations

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 55

ActEd

A random variable, X , has the density function:


7
f ( x) = - 18 x 2 + 23 x - 24
,

1< x < 3

(i)

Explain why the inverse transform method is not appropriate for generating
random variates from X .
[1]

(ii)

It is planned to generate random variates using the acceptance-rejection method on


a uniform distribution over (1, 3) .
(a)

Show that the scaling factor, C = max

f ( x)
h( x)

, is

43
36

where h( x) is the

density function of U (1, 3) .


(b)

Write down the function, g ( x) =

f ( x)
Ch ( x )

, which gives the probability of

accepting a particular value from the U (1, 3) distribution.


(c)

Use the random numbers 0.461, 0.966, 0.024 and 0.222 to generate
random variates from the U (1, 3) distribution.

(d)

Use the random numbers 0.458, 0.373, 0.711 and 0.606 together with the
probability function in part (ii)(b) to decide which of the values in part
(ii)(c) should be kept.
[5]

(iii)

Explain the proportion of the pseudo-random numbers used that will be rejected
in the long run.
[2]

(iv)

State the circumstances where it is possible to apply the acceptance-rejection


[2]
method using a uniform h ( x ) . Explain why you might not wish to do so.
[Total 10]

The Actuarial Education Company

IFE: 2014 Examinations

Page 56

CT6 Online Classroom Questions Handout

Errors
1
Using q = xi to estimate q = E ( X ) :
n

absolute error = q - q

relative error =

q - q
q

Number of simulations required

Using

q - q
~ N (0,1) , the number of simulations required, n , to ensure:
t n

P q - q < e = 1 - a
q - q

P
< e =1-a
q

n > za2

t 2
2 2
e

n > za2

t 2
2 2 2
e q

1 n
where q = x , q = E[ X ] and t 2 =
( x - q)2 .
n - 1 k =1 k

ActEd

Monte Carlo simulation is being used to model the life expectancy of a particular group
of annuitants. The standard deviation of the life expectancy has been estimated as 6.52
years and a previous estimate of the mean life-expectancy was 74.13 years. Calculate
how many simulations should be performed to ensure that, with 95% probability, the:
(i)

absolute error when estimating the mean life expectancy is less than 0.05

(ii)

relative error when estimating the mean life expectancy is less than 0.01%. [2]
[Total 4]

IFE: 2014 Examinations

[2]

The Actuarial Education Company

CT6 Online Classroom Questions Handout

Page 57

Preparing for the exam


As the exam gets closer, we recommend that you focus on question practice in order to prepare for the
exam. If you have purchased the CMP, dont forget that you have the Series X Assignments and
Question and Answer Bank, which contain many exam-style questions as well as other questions to
develop your understanding of the material.
In addition, you may find some of the following study material very helpful in the run-up to the exam:
ASET

ActEds solutions to exams set from 2010 to 2013, with useful exam technique
comments. In the summer, Mini-ASET will also be available covering the April 2014
paper only.

Mock Exam

There is a 100-mark mock exam paper (Mock Exam A) available. You can purchase
the mock exam with or without mock exam marking.

AMP

The Additional Mock Pack (AMP) consists of two further 100-mark mock exam
papers. This pack is ideal for students who are retaking and have already sat Mock
Exam A, or for those who just want some extra question practice. You can have either
or both mock exams marked by submitting the relevant mock exam with a Marking
Voucher (purchased separately).

Revision Notes

These are a set of conveniently-sized A5 spiral-bound booklets perfect for revising


on the train or tube to work. Each booklet contains relevant Core Reading with a set
of integrated short questions to develop your bookwork knowledge, relevant past
exam questions with concise solutions, detailed analyses of key past exam questions
(selected for their difficulty) and other useful revision aids.

Flashcards

These A6-sized cards cover the key points of the course that most students like to
commit to memory and are an excellent supplement to our other study materials.
Each flashcard has questions on one side and the answers on the reverse.

For more information about these products, please see the Student Brochure or visit our website at
www.ActEd.co.uk. Please order online at www.ActEd.co.uk/estore or complete an order form and send it
to us by post or fax.
If you have queries in this subject then please use the Questions forum that is within the Online
Classroom.

The Actuarial Education Company

IFE: 2014 Examinations

Page 58

CT6 Online Classroom Questions Handout

All study material produced by ActEd is copyright and is


sold for the exclusive use of the purchaser. The copyright
is owned by Institute and Faculty Education Limited, a
subsidiary of the Institute and Faculty of Actuaries.
Unless prior authority is granted by ActEd, you may not
hire out, lend, give out, sell, store or transmit
electronically or photocopy any part of the study material.
You must take care of your study material to ensure that it
is not used or copied by anybody else.
Legal action will be taken if these terms are infringed. In
addition, we may seek to take disciplinary action through
the profession or through your employer.
These conditions remain in force after you have finished
using the course.

IFE: 2014 Examinations

The Actuarial Education Company

Das könnte Ihnen auch gefallen