FandI CT6 200804 Exam FINAL
FandI CT6 200804 Exam FINAL
EXAMINATION
1. Enter all the candidate and examination details as requested on the front of your answer
booklet.
2. You must not start writing your answers in the booklet until instructed to do so by the
supervisor.
4. Attempt all 10 questions, beginning your answer to each question on a separate sheet.
Hand in BOTH your answer booklet, with any additional sheets firmly attached, and this
question paper.
In addition to this paper you should have available the 2002 edition of the Formulae
and Tables and your own electronic calculator from the approved list.
© Faculty of Actuaries
CT6 A2008 © Institute of Actuaries
1 Give two examples of the main types of liability insurance, stating for each example a
typical insured peril. [4]
2 A claim amount distribution is normal with unknown mean μ and known standard
deviation £50. Based on past experience a suitable prior distribution for μ is normal
with mean £300 and standard deviation £20.
(i) Calculate the prior probability that μ, the mean of the claim amount
distribution, is less than £270. [1]
(b) Calculate the posterior probability that μ is less than £270 and
comment on your answer.
[5]
[Total 6]
3 (i) X and Y are independent Poisson random variables with mean λ. Derive the
moment generating function of X, and hence show that X + Y also has a
Poisson distribution. [4]
(ii) An insurer has a portfolio of 100 policies. Annual premiums of 0.2 units per
policy are payable annually in advance. Claims, which are paid at the end of
the year, are for a fixed sum of 1 unit per claim. Annual claims numbers on
each policy are Poisson distributed with mean 0.18.
Calculate how much initial capital is needed in order to ensure that the
probability of ruin at the end of the year is less than 1%. [4]
[Total 8]
4 Y1, Y2, …, Yn are independent observations from a normal distribution with E[Yi] = μi
and Var[Yi] = σ2.
(ii) Identify the natural parameter and derive the variance function. [3]
(iii) Show that the Pearson residual is the same as the deviance residual. [4]
[Total 9]
CT6 A2008—2
5 The following table shows the claim payments for an insurance company in units of
£5,000:
Development year
Accident
year 0 1 2 3
The inflation for a 12 month period to the middle of each year is given as follows:
Calculate the amount of outstanding claims arising from accidents in year 2007, using
the inflation adjusted chain ladder method.
[9]
For the first type of policy, a total of 65 claims are expected each year and the
expected size of each claim is £1,200.
For the second type of policy, a total of 20 claims are expected each year and the
expected size of each claim is £4,500.
(i) Calculate the mean and variance of the total cost of annual claims, S, arising
from this portfolio. [3]
The risk premium loading is denoted by θ, so that the annual premium on each policy
is (1+θ)×expected annual claims on each policy. The initial reserve is denoted by u.
A normal approximation is used for the distribution of S, and the initial reserve is set
by ensuring that
(b) Determine the annual premium required in order that no initial reserve
is necessary. [7]
[Total 10]
where et is a white noise process with mean zero and variance σ2.
(i) Express in terms of β1 and β4 the roots of the characteristic polynomial of the
MA part, and give conditions for invertibility of the model. [2]
Lag ACF
1 0.73
2 0.14
3 0.37
4 0.59
5 0.24
6 0.12
7 0.07
(iii) Explain whether these results confirm the initial belief that the model could be
appropriate for these data. [3]
[Total 10]
Level 0 0%
Level 1 25%
Level 2 50%
The premium at the Level 0 is £800. The probability that a policyholder has an
accident in a year is 0.2, and it is assumed that a policyholder does not have more than
one accident each year.
In the event of a claim free year the policyholder moves to the next higher level of
discount in the coming year or remains at Level 2.
In the event of a claim the policyholder moves to the next lower level of discount in
the coming year or remains at Level 0.
Following an accident the policyholder decides whether or not to make a claim based
on the claim size and the amount of premiums over the period of the next 2 policy
years, assuming no more claims are made.
CT6 A2008—4
(i) For each discount level, find the minimum claim amount for which the
policyholder will make a claim. [2]
(ii) Assuming that the cost of repair for each accident has an exponential
distribution with mean £600, calculate the probability that a policyholder
makes a claim at each level of discount. [5]
(iii) Write down the transition matrix and calculate the average premium payment
for a year when the system has reached the equilibrium. [6]
[Total 13]
9 (i) Describe the difference between strictly stationary processes and weakly
stationary processes. [2]
(ii) Explain why weakly stationary multivariate normal processes are also strictly
stationary. [1]
(iii) Show that the following bivariate time series process, (Xn, Yn)t , is weakly
stationary:
where enx and enx are two independent white noise processes. [5]
is stationary. [6]
[Total 14]
250
⎡ pe 200t + 18 pe100t + 81 p ⎤
M S (t ) = ⎢ +1− p⎥ . [4]
⎣⎢ 100 ⎦⎥
(ii) Show that E ( S ) = 5, 000 p and Var ( S ) = 550, 000 p − 100, 000 p 2 [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.
END OF PAPER
CT6 A2008—6