Let X represent the number of customers arriving during the morning hours and let Y represent the number

of customers arriving during the afternoon hours at a diner. This is given: a) X and Y are Poisson distributed. b)The rst moment of X is less than the rst moment of Y by 8. c) The second moment of X is 60% of the second moment of Y. Calculate the variance of Y. i) For a Poisson random variable N, E(N) = Var(N) = and E(N2 ) = +2 . ii) We are given x = y -8 and x +2 x = 0.6(x +2 y ). iii) Combining equations, we get a quadratic in y :y - 8 +(y - 8)2 = 0.6(y +2 y ). iv) symplifying, we get: 0.42 y - 15.6y + 56 = 0. v) Two roots: y = 35 and 4. The second root is rejected since this would make x negative. vi) .: the variance = 35. Automobiles policies are separated into two groups: low-risk and high-risk. Actuary Ismael examines low-risk policies, continuing until a policy with a claim is found and then stopping. Actuary Ruben follows the same procedure with high-risk policies. Each low-risk policy has a 10% probability of having a claim. Each high-risk policy has a 20% probability of having a claim. The claim statuses of polices are mutually independent. Calculate the probability that Actuary Ismael examines fewer policies than Actuary Ruben. The probability that Ismael examines exactly n policies is 0.10.9n1 . The probability that Ruben examines more than n policies is 0.8n . The required 0.72 1 n probability is thus n=1 0.10.9n1 0.8n = 9 n=1 0.72 = 910.72 = 0.2857. Another solution: Ismael and Ruben examine policies simultaneously until at least one of them nds a claim. At each examination there are four possible outcomes: a) Both nd a claim. The probability is 0.02 b) Ismael nds a claim and Ruben does not. the pro is 0.08. c) Ruben nds a claim and Ismael does not. The prob is 0.18. d) Neither nds a claim. The prob. is 0.72. Conditioning on the examination at which the process ends, the probability that it ends with Ismael being the rst to nd a claim (and thus needing to examine 0.08 8 fewer policies) is 0.02+0 .08+0.18 = 28 = 0.2857. From 27 pieces of luggage, an airline luggage handler damages a random sample of four. The probability that exactly one of the damage pieces of luggage is insured is 1

twice the probability that none of the damage pieces are insured. Calculate the prob that exactly two of the four damaged pieces are insured. The ratio of the probability that one of the damaged pieces is insured to the r 27 r 27 r 27 r 27 4r probability (( )/ )(( )/ ) = 27 r , r is the 1 3 4 0 4 4 total number of pieces insured. Setting this ratio 2= 4r/27-r r= 8. r 27 r 27 8 19 27 19! 27! 8! 2!17! ) 4!23! Therefore, (( )/ ) = (( )/ ) = ( 2!6! 2 2 4 2 2 4 =0.27. An automobile insurance company issues a one-year policy with a deductible of 500. The prob is 0.8 that the insured automobile has no accident, and 0.0 that the automobile has more than one accident. If there is an accident, the loss before application of the deductible is exponentially distributed with mean 3000. Calculate the 95th percentile of the insurance company payout on this policy. The 95th percentile is in the range when an accident occurs. It is the 75th percentile of the payout, given that an accident occurs, because ( 0.95-0.80)(10.80) = 0.75. Letting x be the 75th percentile of the given exponential distrix bution, F(x) = 1 - e 3000 = 0.75, so x = 4159. Subtracting the deductible of 500 gives 3659 as the (unconditional) 95th percentile of the insurance company payout A motorist makes three driving errors, each independently resulting in an accident with prob 0.25. Each accident results in a loss that is exponentially distributed with mean 0.80. Losses are mutually independent and independent of the number of accidents. The motorists insurer reimburses 70% of each loss due to an accident. Calculate the variance of the total unreimburesed loss the motorist experiences due to accidents resulting from these driving errors. Let N denote the number of accidents, which is binomial with parameters 1 4 3 1 3 9 and 3 and thus has mean 3( 1 4 ) = 4 and variance 3( 4 )( 4 ) = 16 . Let Xi denote the unreimbursed loss due to the ith accident, which is 0.3 times an exponentially distributed random variable with mean 0.8 and therefore variance (0.8)2 = 0.64. i.e; Xi has mean 0.8(0.3) = 0.24 and variance 0.64(0.3)2 = 0.0576. Let X denote the total unreimbursed loss due to the N accidents. Using conditional variance formula. Var(X) = Var E(X|N) +E Var (X|N) =Var[E(X1 +. . . +XN )] +E[Var(X1 +. . . +XN )] = Var[NE(X1 )]+E[N Var(X1 = Var(0.24N) + E(0.0576N) = (0.24)2 Var(N) + 0.0576E(N) 9 =0.0576( 16 ) + 0.0576( 3 4 ) = 0.0756.