Free CAS MAS-I (Modern Actuarial Statistics I) Probability Models Practice Questions

Probability models on CAS Exam MAS-I cover parametric loss distributions, severity and frequency models, mixture distributions, and maximum likelihood estimation applied to property and casualty insurance data (CAS).

134 questions 61 easy 32 medium 41 hard 2026 syllabus

Sample Questions

Question 1 Easy
The number of claims filed per month at a small insurance agency follows a Poisson distribution with mean 6.

Calculate P(4≤N≤7)P(4 \leq N \leq 7).
Solution
B is correct.

With λ=6\lambda = 6 and e−6≈0.002479e^{-6} \approx 0.002479:
P(N=k)=e−6⋅6kk!P(N = k) = \frac{e^{-6} \cdot 6^k}{k!}
- P(N=4)=0.002479×1296/24=0.002479×54=0.13385P(N=4) = 0.002479 \times 1296/24 = 0.002479 \times 54 = 0.13385
- P(N=5)=0.002479×7776/120=0.002479×64.8=0.16062P(N=5) = 0.002479 \times 7776/120 = 0.002479 \times 64.8 = 0.16062
- P(N=6)=0.002479×46656/720=0.002479×64.8=0.16062P(N=6) = 0.002479 \times 46656/720 = 0.002479 \times 64.8 = 0.16062
- P(N=7)=0.002479×279936/5040=0.002479×55.543=0.13768P(N=7) = 0.002479 \times 279936/5040 = 0.002479 \times 55.543 = 0.13768

P(4≤N≤7)=0.13385+0.16062+0.16062+0.13768=0.59277P(4 \leq N \leq 7) = 0.13385 + 0.16062 + 0.16062 + 0.13768 = 0.59277

Since 0.592770.59277 falls in the band at least 0.58 but less than 0.60, that is the correct interval.
Question 2 Medium
You are given:
- Constant force of mortality μ=0.04\mu = 0.04
- Force of interest δ=0.06\delta = 0.06

Calculate Aˉx\bar{A}_x, the actuarial present value of a continuous whole life insurance of 1 on life (x).
Solution
E is correct.

With constant force of mortality, the continuous whole life insurance APV is:
Aˉx=∫0∞e−δtμe−μt dt=μμ+δ=0.040.04+0.06=0.040.10=0.40\bar{A}_x = \int_0^{\infty} e^{-\delta t} \mu e^{-\mu t}\,dt = \frac{\mu}{\mu + \delta} = \frac{0.04}{0.04 + 0.06} = \frac{0.04}{0.10} = 0.40
Question 3 Hard
A reliability engineer evaluates a 2-out-of-3 redundant system: it remains operational as long as at least two of its three independent components are functioning. The three components have exponentially distributed lifetimes with mean lifetimes of 100, 150, and 200 hours, respectively. Calculate the expected lifetime of the system, in hours.
Solution
D is correct.

Step 1. Let component ii have failure rate λi\lambda_i: λ1=1/100=0.01\lambda_1 = 1/100 = 0.01, λ2=1/150≈0.006667\lambda_2 = 1/150 \approx 0.006667, λ3=1/200=0.005\lambda_3 = 1/200 = 0.005. Let T(k)T_{(k)} denote the kkth order statistic of the three lifetimes. A 2-of-3 system fails at T(2)T_{(2)} (the SECOND failure), so we want E[T(2)]E[T_{(2)}], NOT E[T(1)]E[T_{(1)}].

Step 2. Time to first failure is exponential with rate λ1+λ2+λ3=0.021667\lambda_1 + \lambda_2 + \lambda_3 = 0.021667:
E[T(1)]=10.021667=46.154.E[T_{(1)}] = \frac{1}{0.021667} = 46.154.

Step 3. The conditional probability that component ii is the first to fail is λi/∑λ\lambda_i / \sum \lambda:
P1=0.4615,P2=0.3077,P3=0.2308.P_1 = 0.4615, \quad P_2 = 0.3077, \quad P_3 = 0.2308.

Step 4. By the memoryless property of the exponential distribution, the two survivors retain their original failure rates after the first failure. The expected time from first failure to second failure, conditional on which component failed first, is the reciprocal of the sum of the surviving rates:
1λ2+λ3=85.714,1λ1+λ3=66.667,1λ1+λ2=60.000.\frac{1}{\lambda_2 + \lambda_3} = 85.714, \quad \frac{1}{\lambda_1 + \lambda_3} = 66.667, \quad \frac{1}{\lambda_1 + \lambda_2} = 60.000.

Step 5. Apply the law of total expectation, weighting each conditional time by the probability that the corresponding component failed first:
E[T(2)−T(1)]=0.4615(85.714)+0.3077(66.667)+0.2308(60.000)=39.560+20.512+13.846=73.918.E[T_{(2)} - T_{(1)}] = 0.4615(85.714) + 0.3077(66.667) + 0.2308(60.000) = 39.560 + 20.512 + 13.846 = 73.918.
Therefore
E[T(2)]=46.154+73.918≈120.07.E[T_{(2)}] = 46.154 + 73.918 \approx 120.07.
The most plausible wrong path is to treat the three components as IID with mean 150 and apply the symmetric 2-of-3 formula 150⋅(1/3+1/2)=125150 \cdot (1/3 + 1/2) = 125; this ignores how the heterogeneous rates skew which component is likeliest to fail first.

Guides & Articles

About FreeFellow

Jeffrey Ting, founder of FreeFellow
Jeffrey Ting
FSA, CFA · Founder

FreeFellow was built by Jeffrey Ting, a credentialed actuary and CFA charterholder who has passed thirteen of the hardest exams in finance, all on his first attempt. He paid four-figure prep fees along the way.

So he started writing his own questions, then lessons, then mock exams, until it grew into a full prep platform covering 41 exams with more than 48,000 original practice questions.

01
Cost shouldn't decide who gets in.

A CFA charter, a CPA license, an actuarial credential. Each opens a real career, but prep fees add to the cost of getting there. FreeFellow keeps its original question bank and written lessons free so you can study even if a paid course is out of reach.

02
Free should mean free.

The original question bank, the worked solutions, the topic lessons, mixed practice, and your readiness score stay free, forever. Full access needs a free account, and practice usage limits apply. Fellow adds AI grading on supported exams, spaced-repetition flashcards, full-length mock exams, analytics, and a study plan that adapts to your progress.