F71AH/PT Coursework Assignment-1
Hello, dear friend, you can consul t us at any time if you have any questions, add WeChat: daixieit
F71AH/PT Coursework Assignment-1
Project description
The insurance business in a single period can be modeled by a so-called surplus process (S) defined as
N
S = µ * n – Xi . (1)
i1+
In (1), µ is the constant premium rate and n is the total number of policies in this business; N is a random positive integer for the number of claims and Xi is another random variables independent from N, describing the size (amount) of i-th claim. For a S with n = 100, it is believed that N ~ Poisson(30) distribution and Xi are i.i.d. Pareto(100, β = 3) distributed with density
fX (x) = β × 100β (2)
where x > 100 denotes the claim size in =. Otherwise the density is 0. Your task is to estimate risk measures and other quantities associated with this portfolio over a period of a single year. (Hint: use simulation in question (1) for the estimations of other questions)
(1) Describe mathematically an algorithm which could be used transform independent sam- ples from a U(0, 1) distribution to generate samples from the above Pareto distribution.
[2 marks]
(2) The insurer determines a premium rate µ = =60 in S. Use the R programming lan- guage to estimate the Value at Risk (VaR) and the Conditional Tail Expectation (CTE) at probability level α = 0.9. From the insurer’s point of view, use simulation to estimate a µf such that the ruin probability is smaller than 1%, i.e.,
Pr(S < 0) < 0.01.
(Hint: for the calculation of VaR & CTE, consider –S as the loss of the insurer, i.e. to estimate VaRα [ –S]).
[8 marks]
(3) From a policyholder’s point of view (who is a rational investor), consider a client facing a truncated Pareto(100, β = 3) loss Y with upper bound 1000, i.e. Pr(Y < 1000) = 1. Estimate the maximum premium µff that he or she is willing to pay to purchase this insurance policy if the client adopts a utility function with form
y
500
where y denotes the client’s wealth in =. The initial wealth of the policy holder is =1000.
Comparing with µf in question (b), which premium rate would you suggest? Explain your answer. In particular, if it holds that µff < µf or µff > µf , could you explain the motivation for this?
(Hint: 1. The upper bounded Y has density fY (y) = fX (y)/0.999, for Y e [100, 1000] and fY (x) = 0 for Y > 100; 2. Consider insurer’s the pooling effect and the policy- holder’s level of risk averse).
[5 marks]
[Total 15 marks]
Your findings should be presented in the form of a report, which should:
· have a clear and logical structure;
· include detail of your mathematical calculations so that your results could be reproduced by another statistician;
· include clearly labelled and correctly referenced tables and diagrams, as appropriate;
· include the R code you used in an appendix (you do not need to explain individual
R commands but some comments should be included to indicate the purpose of each section of code);
· include citation and referencing for any material (books, papers, websites etc.) used.
2022-03-05