Hi,
I'm working on ADAPT practice exams and this problem came up. I would be very grateful if someone could please help me understand this problem. My question simply regards at the bolded sentences:
The full credibility standard has been selected so that actual aggregate losses will be within k% of expected aggregate losses p% of the time.
Consider the limited fluctuation full credibility standard for each of the followings:
I. The number of claims has a Poisson distribution and the claim size has a gamma distribution with \alpha>1.
II. The number of claims has a Poisson distribution and the claim size has an exponential distribution.
III. The number of claims has a Poisson distribution and the claim size has a Pareto distribution with \alpha>2.
Rank the limited fluctuation full credibility standard in ascending order.
the solution compares each one's full credibility standard, in terms of NUMBER OF LOSSES. But I don't get that: shouldn't the credibility standards be expressed in terms of AGGREGATE LOSSES, i.e. expected number of claims * expectation of severity? If I'm wrong, could someone tell me what wording in this problem indicates expected numbers? Please help!
I'm working on ADAPT practice exams and this problem came up. I would be very grateful if someone could please help me understand this problem. My question simply regards at the bolded sentences:
The full credibility standard has been selected so that actual aggregate losses will be within k% of expected aggregate losses p% of the time.
Consider the limited fluctuation full credibility standard for each of the followings:
I. The number of claims has a Poisson distribution and the claim size has a gamma distribution with \alpha>1.
II. The number of claims has a Poisson distribution and the claim size has an exponential distribution.
III. The number of claims has a Poisson distribution and the claim size has a Pareto distribution with \alpha>2.
Rank the limited fluctuation full credibility standard in ascending order.
the solution compares each one's full credibility standard, in terms of NUMBER OF LOSSES. But I don't get that: shouldn't the credibility standards be expressed in terms of AGGREGATE LOSSES, i.e. expected number of claims * expectation of severity? If I'm wrong, could someone tell me what wording in this problem indicates expected numbers? Please help!
Regarding Limited Fluctuation Credibility: Poisson Frequency
0 commentaires:
Enregistrer un commentaire