QQ登录
微博登录
微信登录
Exam C, Fall 2005
FINAL ANSWER KEY
Question # AnswerQuestion # Answer
1D 19 B
2A 20 A
3 E 21 B
4 B 22A
5 E 23E
6 E 24 B and C
7 A 25C
8 D 26 C
9 B 27A
10 D and E28 B
11D29 C
12 C30 D
13 C 31 B
14 C 32B
15A 33 E
16 D 34A
17 D 35 E
18A
Exam C: Fall 2005 -1- GO ON TO NEXT PAGE
**BEGINNING OF EXAMINATION**
1. A portfolio of policies has produced the following claims:
100 100 100 200 300 300 300 400 500 600
Determine the empirical estimate of H(300).
(A) Less than 0.50
(B) At least 0.50, but less than 0.75
(C) At least 0.75, but less than 1.00
(D) At least 1.00, but less than 1.25
(E) At least 1.25
Exam C: Fall 2005 -2- GO ON TO NEXT PAGE
2. You are given:
(i) The conditional distribution of the number of claims per policyholder is Poisson with
mean λ .
(ii) The variable λ has a gamma distribution with parameters α and θ .
(iii) For policyholders with 1 claim in Year 1, the credibility estimate for the number of
claims in Year 2 is 0.15.
(iv) For policyholders with an average of 2 claims per year in Year 1 and Year 2, the
credibility estimate for the number of claims in Year 3 is 0.20.
Determine θ .
(A) Less than 0.02
(B) At least 0.02, but less than 0.03
(C) At least 0.03, but less than 0.04
(D) At least 0.04, but less than 0.05
(E) At least 0.05
Exam C: Fall 2005 -3- GO ON TO NEXT PAGE
3. A random sample of claims has been drawn from a Burr distribution with known parameter
α = 1 and unknown parameters θ and γ . You are given:
(i) 75% of the claim amounts in the sample exceed 100.
(ii) 25% of the claim amounts in the sample exceed 500.
Estimate θ by percentile matching.
(A) Less than 190
(B) At least 190, but less than 200
(C) At least 200, but less than 210
(D) At least 210, but less than 220
(E) At least 220
Exam C: Fall 2005 -4- GO ON TO NEXT PAGE
4. You are given:
(i) f ( x) is a cubic spline with knots (0, 0) and (2, 2).
(ii) f ′(0) = 1 and f ′′(2) = ?24
Determine f (1).
(A) 1
(B) 4
(C) 6
(D) 8
(E) 10
Exam C: Fall 2005 -5- GO ON TO NEXT PAGE
5. For a portfolio of policies, you are given:
(i) There is no deductible and the policy limit varies by policy.
(ii) A sample of ten claims is:
350 350 500 500 500+ 1000 1000+ 1000+ 1200 1500
where the symbol + indicates that the loss exceeds the policy limit.
(iii) ^
S1(1250) is the product-limit estimate of S(1250).
(iv) ^
S2 (1250) is the maximum likelihood estimate of S(1250) under the assumption that
the losses follow an exponential distribution.
Determine the absolute difference between ^
S1(1250) and ^
S2 (1250) .
(A) 0.00
(B) 0.03
(C) 0.05
(D) 0.07
(E) 0.09
Exam C: Fall 2005 -6- GO ON TO NEXT PAGE
6. The random variable X has survival function:
( )
( )
4
2 2 2
SX x
x
θ
θ
=
+
Two values of X are observed to be 2 and 4. One other value exceeds 4.
Calculate the maximum likelihood estimate of θ.
(A) Less than 4.0
(B) At least 4.0, but less than 4.5
(C) At least 4.5, but less than 5.0
(D) At least 5.0, but less than 5.5
(E) At least 5.5
Exam C: Fall 2005 -7- GO ON TO NEXT PAGE
7. For a portfolio of policies, you are given:
(i) The annual claim amount on a policy has probability density function:
2
f(x|θ ) 2x, 0 x θ
θ
= < <
(ii) The prior distribution of θ has density function:
π (θ)=4θ 3, 0<θ <1
(iii) A randomly selected policy had claim amount 0.1 in Year 1.
Determine the Bühlmann credibility estimate of the claim amount for the selected policy in
Year 2.
(A) 0.43
(B) 0.45
(C) 0.50
(D) 0.53
(E) 0.56
Exam C: Fall 2005 -8- GO ON TO NEXT PAGE
8. Total losses for a group of insured motorcyclists are simulated using the aggregate loss
model and the inversion method.
The number of claims has a Poisson distribution with λ = 4 . The amount of each claim has
an exponential distribution with mean 1000.
The number of claims is simulated using u = 0.13. The claim amounts are simulated using
u1 = 0.05 , u2 = 0.95 and u3 = 0.10 in that order, as needed.
Determine the total losses.
(A) 0
(B) 51
(C) 2996
(D) 3047
(E) 3152
Exam C: Fall 2005 -9- GO ON TO NEXT PAGE
9. You are given:
(i) The sample:
1 2 3 3 3 3 3 3 3 3
(ii) ? ( )
1 F x is the kernel density estimator of the distribution function using a uniform
kernel with bandwidth 1.
(iii) ? ( )
2 F x is the kernel density estimator of the distribution function using a triangular
kernel with bandwidth 1.
Determine which of the following intervals has ? ( )
1 F x = ? ( )
2 F x for all x in the interval.
(A) 0 < x < 1
(B) 1 < x < 2
(C) 2 < x < 3
(D) 3 < x < 4
(E) None of (A), (B), (C) or (D)
Exam C: Fall 2005 -10- GO ON TO NEXT PAGE
10. 1000 workers insured under a workers compensation policy were observed for one year. The
number of work days missed is given below:
Number of Days of Work
Missed
Number of Workers
0 818
1 153
2 25
3 or more 4
Total 1000
Total Number of Days Missed 230
The chi-square goodness-of-fit test is used to test the hypothesis that the number of work
days missed follows a Poisson distribution where:
(i) The Poisson parameter is estimated by the average number of work days missed.
(ii) Any interval in which the expected number is less than one is combined with the
previous interval.
Determine the results of the test.
(A) The hypothesis is not rejected at the 0.10 significance level.
(B) The hypothesis is rejected at the 0.10 significance level, but is not rejected at the 0.05
significance level.
(C) The hypothesis is rejected at the 0.05 significance level, but is not rejected at the
0.025 significance level.
(D) The hypothesis is rejected at the 0.025 significance level, but is not rejected at the
0.01 significance level.
(E) The hypothesis is rejected at the 0.01 significance level.
Exam C: Fall 2005 -11- GO ON TO NEXT PAGE
11. You are given the following data:
Year 1 Year 2
Total Losses 12,000 14,000
Number of Policyholders 25 30
The estimate of the variance of the hypothetical means is 254.
Determine the credibility factor for Year 3 using the nonparametric empirical Bayes method.
(A) Less than 0.73
(B) At least 0.73, but less than 0.78
(C) At least 0.78, but less than 0.83
(D) At least 0.83, but less than 0.88
(E) At least 0.88
Exam C: Fall 2005 -12- GO ON TO NEXT PAGE
12. A smoothing spline is to be fit to the points (0, 3), (1, 2), and (3, 6).
The candidate function is:
( )
( ) ( )
( )( ) ( ) ( )( )
3
2 3
2.6 4/15 4/15 , 0 1
2.6 8/15 1 0.8 1 2/15 1 1 3
x x x
f x
x x x x
? = ?? ? + ≤ ≤
+ ? + ? ? ? ≤ ≤ ??
Determine the value of S, the squared norm smoothness criterion.
(A) Less than 2.35
(B) At least 2.35, but less than 2.50
(C) At least 2.50, but less than 2.65
(D) At least 2.65, but less than 2.80
(E) At least 2.80
Exam C: Fall 2005 -13- GO ON TO NEXT PAGE
13. You are given the following about a Cox proportional hazards model for mortality:
(i) There are two covariates: : z1 = 1 for smoker and 0 for non-smoker, and z2 =1 for
male and 0 for female.
(ii) The parameter estimates are 1
β? = 0.05 and 2
β? = 0.15 .
(iii) The covariance matrix of the parameter estimates, 1
?β
and 2
?β
, is:
? ??
?
? ??
?
0.0001 0.0003
0.0002 0.0001
Determine the upper limit of the 95% confidence interval for the relative risk of a female
non-smoker compared to a male smoker.
(A) Less than 0.6
(B) At least 0.6, but less than 0.8
(C) At least 0.8, but less than 1.0
(D) At least 1.0, but less than 1.2
(E) At least 1.2
Exam C: Fall 2005 -14- GO ON TO NEXT PAGE
14. You are given:
(i) Fifty claims have been observed from a lognormal distribution with unknown
parameters μ and σ .
(ii) The maximum likelihood estimates are ?? μ = 6.84 and σ?? = 1.49 .
(iii) The covariance matrix ofμ? and σ? is:
0 0444 0
0 0 0222
.
.
LN M
OQ P
(iv) The partial derivatives of the lognormal cumulative distribution function are:
F φ (z)
μ σ
? ?
=
?
and
?
?
=
F ?z× z
σ
φ
σ
b g
(v) An approximate 95% confidence interval for the probability that the next claim
will be less than or equal to 5000 is:
[PL, PH]
Determine PL.
(A) 0.73
(B) 0.76
(C) 0.79
(D) 0.82
(E) 0.85
Exam C: Fall 2005 -15- GO ON TO NEXT PAGE
15. For a particular policy, the conditional probability of the annual number of claims given
Θ = θ , and the probability distribution of Θ are as follows:
Number of Claims 0 1 2
Probability 2θ θ 1?3θ
θ 0.10 0.30
Probability 0.80 0.20
One claim was observed in Year 1.
Calculate the Bayesian estimate of the expected number of claims for Year 2.
(A) Less than 1.1
(B) At least 1.1, but less than 1.2
(C) At least 1.2, but less than 1.3
(D) At least 1.3, but less than 1.4
(E) At least 1.4
Exam C: Fall 2005 -16- GO ON TO NEXT PAGE
16. You simulate observations from a specific distribution F(x), such that the number of
simulations N is sufficiently large to be at least 95 percent confident of estimating
F(1500) correctly within 1 percent.
Let P represent the number of simulated values less than 1500.
Determine which of the following could be values of N and P.
(A) N = 2000 P = 1890
(B) N = 3000 P = 2500
(C) N = 3500 P = 3100
(D) N = 4000 P = 3630
(E) N = 4500 P = 4020
Exam C: Fall 2005 -17- GO ON TO NEXT PAGE
17. For a survival study, you are given:
(i) Deaths occurred at times s 1 2 9 y < y < … < y .
(ii) The Nelson-Aalen estimates of the cumulative hazard function at 3 y and 4 y are:
^ ^
H(y3)=0.4128 and H(y4)=0.5691
(iii) The estimated variances of the estimates in (ii) are:
^
Var[H(y3)] = 0.009565
∧
and ^
Var[H(y4 )] = 0.014448
∧
Determine the number of deaths at y4 .
(A) 2
(B) 3
(C) 4
(D) 5
(E) 6
Exam C: Fall 2005 -18- GO ON TO NEXT PAGE
18. A random sample of size n is drawn from a distribution with probability density function:
2 ( ) , 0 , 0
( )
f x x
x
θ
θ
θ
= < < ∞ >
+
Determine the asymptotic variance of the maximum likelihood estimator of θ .
(A) n
3θ 2
(B) 3 2
1
nθ
(C) 2
3
nθ
(D) 3 2
n
θ
(E) 3 2
1
θ
Exam C: Fall 2005 -19- GO ON TO NEXT PAGE
19. For a portfolio of independent risks, the number of claims for each risk in a year follows
a Poisson distribution with means given in the following table:
Class
Mean Number of
Claims per Risk Number of Risks
1 1 900
2 10 90
3 20 10
You observe x claims in Year 1 for a randomly selected risk.
The Bühlmann credibility estimate of the number of claims for the same risk in Year 2 is
11.983.
Determine x.
(A) 13
(B) 14
(C) 15
(D) 16
(E) 17
Exam C: Fall 2005 -20- GO ON TO NEXT PAGE
20. A survival study gave (0.283, 1.267) as the symmetric linear 95% confidence interval
for H(5).
Using the delta method, determine the symmetric linear 95% confidence interval for S(5).
(A) (0.23, 0.69)
(B) (0.26, 0.72)
(C) (0.28, 0.75)
(D) (0.31, 0.73)
(E) (0.32, 0.80)
Exam C: Fall 2005 -21- GO ON TO NEXT PAGE
21. You are given:
(i) Losses on a certain warranty product in Year i follow a lognormal distribution
with parameters i
μ and i
σ .
(ii) i
σ =σ , for i = 1, 2, 3,…
(iii) The parameters i
μ vary in such a way that there is an annual inflation rate of 10%
for losses.
(iv) The following is a sample of seven losses:
Year 1: 20 40 50
Year 2: 30 40 90 120
Using trended losses, determine the method of moments estimate of μ3 .
(A) 3.87
(B) 4.00
(C) 30.00
(D) 55.71
(E) 63.01
Exam C: Fall 2005 -22- GO ON TO NEXT PAGE
22. You are given:
(i) A region is comprised of three territories. Claims experience for Year 1 is as
follows:
Territory Number of Insureds Number of Claims
A 10 4
B 20 5
C 30 3
(ii) The number of claims for each insured each year has a Poisson distribution.
(iii) Each insured in a territory has the same expected claim frequency.
(iv) The number of insureds is constant over time for each territory.
Determine the Bühlmann-Straub empirical Bayes estimate of the credibility factor Z for
Territory A.
(A) Less than 0.4
(B) At least 0.4, but less than 0.5
(C) At least 0.5, but less than 0.6
(D) At least 0.6, but less than 0.7
(E) At least 0.7
Exam C: Fall 2005 -23- GO ON TO NEXT PAGE
23. Determine which of the following is a natural cubic spline passing through the three
points (0, y1 ), (1, y2 ), and (3, 6).
(A) ( )
( )
( )( ) ( )( ) ( )( )
3
2 3
3 7/6 , 0 1
2 1/6 1 11/6 1 11/24 1 , 1 3
x x x
f x
x x x x
= ??? ? ? ≤ <
+ ? + ? ? ? ≤ ≤ ??
(B) ( )
( ) ( )( )
2 3
2 3
3 , 0 1
2 2 1 1/2 1 , 1 3
x x x x
f x
x x x
= ??? ? ? + ≤ <
+ ? ? ? ≤ ≤ ??
(C) ( )
( ) ( )
( )( ) ( ) ( )( )
2 3
2 3
3 1/2 1/2 , 0 1
2 1/2 1 1 1/8 1 , 1 3
x x x x
f x
x x x x
= ??? ? ? + ≤ <
? ? + ? ? ? ≤ ≤ ??
(D) ( )
( ) ( ) ( )
( )( ) ( )( )
2 3
2 3
3 5/ 4 1/2 3/ 4 , 0 1
2 7/4 1 3/8 1 , 1 3
x x x x
f x
x x x
= ??? ? ? + ≤ <
+ ? ? ? ≤ ≤ ??
(E) ( )
( ) ( )
( )( ) ( )( )
3
2 3
3 3/2 1/2 , 0 1
2 3/ 2 1 1/ 4 1 , 1 3
x x x
f x
x x x
= ??? ? + ≤ <
+ ? ? ? ≤ ≤ ??
Exam C: Fall 2005 -24- GO ON TO NEXT PAGE
24. You are given:
(i) A Cox proportional hazards model was used to study the survival times of
patients with a certain disease from the time of onset to death.
(ii) A single covariate z was used with z = 0 for a male patient and z = 1 for a female
patient.
(iii) A sample of five patients gave the following survival times (in months):
Males: 10 18 25
Females: 15 21
(iv) The parameter estimate is ?β= 0.27.
Using the Nelson-Aalen estimate of the baseline cumulative hazard function, estimate the
probability that a future female patient will survive more than 20 months from the time of
the onset of the disease.
(A) 0.33
(B) 0.36
(C) 0.40
(D) 0.43
(E) 0.50
Exam C: Fall 2005 -25- GO ON TO NEXT PAGE
25. You are given:
(i) A random sample of losses from a Weibull distribution is:
595 700 789 799 1109
(ii) At the maximum likelihood estimates of θ and τ , Σln(f (xi )) = ?33.05.
(iii) When τ = 2 , the maximum likelihood estimate of θ is 816.7.
(iv) You use the likelihood ratio test to test the hypothesis
H0:τ =2
H1:τ ≠2
Determine the result of the test.
(A) Do not reject 0 H at the 0.10 level of significance.
(B) Reject 0 H at the 0.10 level of significance, but not at the 0.05 level of
significance.
(C) Reject 0 H at the 0.05 level of significance, but not at the 0.025 level of
significance.
(D) Reject 0 H at the 0.025 level of significance, but not at the 0.01 level of
significance.
(E) Reject 0 H at the 0.01 level of significance.
Exam C: Fall 2005 -26- GO ON TO NEXT PAGE
26. For each policyholder, losses X1,…, Xn , conditional on Θ, are independently and
identically distributed with mean,
( μ θ )=E(X jΘ=θ ), j=1,2,...,n
and variance,
v(θ)=Var(Xj Θ=θ), j = 1,2,...,n .
You are given:
(i) The Bühlmann credibility assigned for estimating X5 based on X1,…, X4 is
Z = 0.4.
(ii) The expected value of the process variance is known to be 8.
Calculate Cov(Xi, Xj), i≠ j.
(A) Less than ?0.5
(B) At least ?0.5 , but less than 0.5
(C) At least 0.5, but less than 1.5
(D) At least 1.5, but less than 2.5
(E) At least 2.5
Exam C: Fall 2005 -27- GO ON TO NEXT PAGE
27. Losses for a warranty product follow the lognormal distribution with underlying normal
mean and standard deviation of 5.6 and 0.75 respectively.
You use simulation to estimate claim payments for a number of contracts with different
deductibles.
The following are four uniform (0,1) random numbers:
0.6217 0.9941 0.8686 0.0485
Using these numbers and the inversion method, calculate the average payment per loss
for a contract with a deductible of 100.
(A) Less than 630
(B) At least 630, but less than 680
(C) At least 680, but less than 730
(D) At least 730, but less than 780
(E) At least 780
Exam C: Fall 2005 -28- GO ON TO NEXT PAGE
28. The random variable X has the exponential distribution with mean θ .
Calculate the e mean-squared error of X 2 as an estimator of θ 2 .
(A) 20θ 4
(B) 21θ 4
(C) 22θ 4
(D) 23θ 4
(E) 24θ 4
Exam C: Fall 2005 -29- GO ON TO NEXT PAGE
29. You are given the following data for the number of claims during a one-year period:
Number of Claims Number of Policies
0 157
1 66
2 19
3 4
4 2
5+ 0
Total 248
A geometric distribution is fitted to the data using maximum likelihood estimation.
Let P = probability of zero claims using the fitted geometric model.
A Poisson distribution is fitted to the data using the method of moments.
Let Q = probability of zero claims using the fitted Poisson model.
Calculate P Q ? .
(A) 0.00
(B) 0.03
(C) 0.06
(D) 0.09
(E) 0.12
Exam C: Fall 2005 -30- GO ON TO NEXT PAGE
30. For a group of auto policyholders, you are given:
(i) The number of claims for each policyholder has a conditional Poisson
distribution.
(ii) During Year 1, the following data are observed for 8000 policyholders:
Number of Claims Number of Policyholders
0 5000
1 2100
2 750
3 100
4 50
5+ 0
A randomly selected policyholder had one claim in Year 1.
Determine the semiparametric empirical Bayes estimate of the number of claims in
Year 2 for the same policyholder.
(A) Less than 0.15
(B) At least 0.15, but less than 0.30
(C) At least 0.30, but less than 0.45
(D) At least 0.45, but less than 0.60
(E) At least 0.60
Exam C: Fall 2005 -31- GO ON TO NEXT PAGE
31. You are given:
(i) The following are observed claim amounts:
400 1000 1600 3000 5000 5400 6200
(ii) An exponential distribution with θ = 3300 is hypothesized for the data.
(iii) The goodness of fit is to be assessed by a p-p plot and a D(x) plot.
Let (s, t) be the coordinates of the p-p plot for a claim amount of 3000.
Determine (s?t)?D(3000).
(A) ? 0.12
(B) ? 0.07
(C) 0.00
(D) 0.07
(E) 0.12
Exam C: Fall 2005 -32- GO ON TO NEXT PAGE
32. You are given:
(i) In a portfolio of risks, each policyholder can have at most two claims per year.
(ii) For each year, the distribution of the number of claims is:
Number of Claims Probability
0 0.10
1 0.90? q
2 q
(iii) The prior density is:
2
( ) , 0.2 0.5
0.039
πq= q <q<
A randomly selected policyholder had two claims in Year 1 and two claims in Year 2.
For this insured, determine the Bayesian estimate of the expected number of claims in
Year 3.
(A) Less than 1.30
(B) At least 1.30, but less than 1.40
(C) At least 1.40, but less than 1.50
(D) At least 1.50, but less than 1.60
(E) At least 1.60
Exam C: Fall 2005 -33- GO ON TO NEXT PAGE
33. For 500 claims, you are given the following distribution:
Claim Size Number of Claims
[0, 500) 200
[500, 1,000) 110
[1,000, 2,000) x
[2,000, 5,000) y
[5,000, 10,000) ?
[10,000, 25,000) ?
[25,000, ∞) ?
You are also given the following values taken from the ogive:
F
500(1500) = 0.689
F
500(3500) = 0.839
Determine y.
(A) Less than 65
(B) At least 65, but less than 70
(C) At least 70, but less than 75
(D) At least 75, but less than 80
(E) At least 80
Exam C: Fall 2005 -34- GO ON TO NEXT PAGE
34. Which of statements (A), (B), (C), and (D) is false?
(A) The chi-square goodness-of-fit test works best when the expected number of
observations varies widely from interval to interval.
(B) For the Kolmogorov-Smirnov test, when the parameters of the distribution in the
null hypothesis are estimated from the data, the probability of rejecting the null
hypothesis decreases.
(C) For the Kolmogorov-Smirnov test, the critical value for right censored data should
be smaller than the critical value for uncensored data.
(D) The Anderson-Darling test does not work for grouped data.
(E) None of (A), (B), (C) or (D) is false.
Exam C: Fall 2005 -35- STOP
35. You are given:
(i) The number of claims follows a Poisson distribution.
(ii) Claim sizes follow a gamma distribution with parameters α (unknown) and
θ = 10,000 .
(iii) The number of claims and claim sizes are independent.
(iv) The full credibility standard has been selected so that actual aggregate losses will
be within 10% of expected aggregate losses 95% of the time.
Using limited fluctuation (classical) credibility, determine the expected number of claims
required for full credibility.
(A) Less than 400
(B) At least 400, but less than 450
(C) At least 450, but less than 500
(D) At least 500
(E) The expected number of claims required for full credibility cannot be determined
from the information given.
高顿网校小编提醒您，我们一定会努力做到*4，期待大家时刻关注高顿网校，把考试*9时间的信息与您一起分享！
高顿网校小编提醒您，我们一定会努力做到*4，期待大家时刻关注高顿网校，把考试*9时间的信息与您一起分享！
