THE CATHOLIC UNIVERSITY OF EASTERN

AFRICA
A. M. E. C. E. A P.O. Box 62157
00200 Nairobi - KENYA
Telephone: 891601-6
Ext 1022/23/25
MAIN EXAMINATION Fax: 254-20-891084
email:[email protected]
[email protected]
JANUARY – APRIL 2022

FACULTY OF SCIENCE

DEPARTMENT OF MATHEMATICS AND ACTUARIAL SCIENCE

REGULAR PROGRAMME

ACS 402: RISK MATHEMATICS

Date: APRIL 2022 Duration: 2 Hours

INSTRUCTIONS: Answer Question ONE and any TWO Questions

Q 1 (a.) State the key characteristics of the individual risk model. (4 marks)
(b.)If X has a Pareto distribution with parameters µ = 400 and θ = 3, and N has a
Poisson (50) distribution, find the expected value and standard deviation of
aggregate claims. (6 marks)
(c.)Suggest an example of an insurance contract where the individual risk model
may be suitable, and an example where it is unlikely to be. (4
marks)
(d.)Describe the differences between the individual risk model and the collective risk
model. (6 marks)
(e.)List the benefits of risk modelling in actuarial work. (4 marks)
(f.) Explain any two types of utility functions commonly used in risk mathematics for
actuarial science (6 marks)
Q 2 Claims on a portfolio of insurance policies arise as a Poisson process with
parameter λ. Individual claim amounts are taken from a distribution X and we define mi =
E(Xi) for i = 1,2,.... The insurance company calculates premiums using a premium
loading of θ.

(i.) Define the adjustment coefficient R. (2 marks)

CUEA/ACAD/EXAMINATIONS/DIRECTORATE OF EXAMINATIONS & TIMETABLING Page 1

ISO 9001:2015 Certified by the Kenya Bureau of Standards

 2θ m1
(ii.) Show that R can be approximated as , by truncating the series expansion
m2
of MX(t). (4 marks)
Now suppose that X follows an exponential distribution with parameter γ.

(iii.) Show that R = . (4 marks)

The insurance company uses a premium loading of 12%, and the mean claim
amount is 200.

(iv.) Calculate R, commenting on the difference with the approximation to R shown in

part (ii). (4 marks)
The initial surplus is 5,000.

(v.) Calculate an upper bound for the ultimate probability of ruin. (2 marks)
(vi.) Suggest two methods by which the insurance company can reduce the
probability of ruin. (4 marks)

Q3. Total annual claim amounts S on a portfolio of insurance policies come from
two independent types of policies:

Type I, which have claim amounts uniformly distributed between 3,000 and 4,000.

Type II, which have claim amounts following an Exponential distribution with mean
3,600.

Claims occur according to a Poisson process, with mean 15 per annum for Type 1
claims and mean 25 per annum for Type 2 claims.

The insurance company uses a premium loading factor of 7% and checks for ruin
at the end of each year.
(i.) Calculate the mean and standard deviation of S. (4 marks)
(ii.)Calculate the minimum initial surplus Um required such that the probability of ruin
at the end of the first year is less than 0.015, using a Normal approximation for the
distribution of S. (6 marks)
Regulatory reforms mean the insurance company is trying to reduce this
probability of ruin to less than 0.005. The insurance company is therefore
purchasing proportional reinsurance from a reinsurer, who uses a premium loading
factor of 17% in its premiums.

CUEA/ACAD/EXAMINATIONS/DIRECTORATE OF EXAMINATIONS & TIMETABLING Page 2

ISO 9001:2015 Certified by the Kenya Bureau of Standards

 The insurance company retains a proportionα of each claim, and denotes by SI the
aggregate annual claims it retains net of reinsurance. The insurance company
continues to hold initial surplus Um.
(iii.) Calculate the maximum proportion αmax that the insurance company can
retain in order to keep the probability of ruin less than 0.005, using a Normal
approximation for the distribution of SI. (6 marks)
The insurance company is concerned that αmax is too low, reducing its profits, and
intends to retain a higher proportion.

(iv.) Suggest other ways in which the insurance company can reduce the
probability of ruin. (4 marks)

Q4. Claim events on a portfolio of insurance policies follow a Poisson process with
parameter λ. Individual claim amounts, X, follow a Normal distribution with
parameters µ = 500 and σ2 = 200. The insurance company calculates premiums
using a premium loading factor of 20%.
(i.) Show that the adjustment coefficient, r = 0.000708 to three significant
figures. (7 marks)
The insurance company’s initial surplus is 5,000.
(ii.) Calculate an upper bound on the probability of ruin, using Lundberg’s
inequality. (2 marks)
The insurance company actuary believes that claim amounts are better modelled
using an exponential distribution. You may assume that the mean m is unchanged,
and is now equal to the standard deviation.
(iii.) Calculate the new upper bound of the probability of ruin. (8 marks)
(iv.) Give a reason why claim amounts on insurance policies are not usually
modelled using a Normal distribution, and suggest an alternative distribution, other than
the exponential. (3 marks)

Q5.
(a) An actuary is considering a portfolio of insurance policies. This portfolio only
contains five policies. Each policy has been taken out by a different couple
who are getting married on the same day in the same city. Each policy would
pay out in the event of rain on that day in that city.

CUEA/ACAD/EXAMINATIONS/DIRECTORATE OF EXAMINATIONS & TIMETABLING Page 3

ISO 9001:2015 Certified by the Kenya Bureau of Standards

 i. Explain why these policies may not meet the ideal criteria for an
insurable risk.
(4 marks)
ii. Suggest two ways in which either the portfolio or the policy terms could
be changed in order to better meet the criteria for insurable risks. (4
marks)
(b) A company sells fire insurance policies that are categorized as high risks and
lo risks groups. In high-risk groups, the number of claims in a year follows a
Poisson distribution with mean 300. In low-risk groups, the number of claims
in a year follows a Poisson distribution with mean 200. The amount of each
claim is exponential distributed with mean 2000. Assuming that frequency
and severity are independent. Calculate the expected and the variance of the
aggregate loss. (12 marks)

*END*

CUEA/ACAD/EXAMINATIONS/DIRECTORATE OF EXAMINATIONS & TIMETABLING Page 4

ISO 9001:2015 Certified by the Kenya Bureau of Standards