ISYE 6644 Summer Final Exam Actual Q&A 2026/2027 – Comprehensive
Simulation & Stochastic Modeling Assessment with Detailed Rationales | 100%
Verified | Pass Guaranteed – A+ Graded
Section A: Probability & Statistics Review
Q1: A simulation analyst is modeling two independent random variables X and Y with
joint PDF f(x,y) = cxy for 0 < x < 2 and 0 < y < 3. Which statement correctly characterizes
the independence of X and Y?
A. X and Y are dependent because the joint PDF is not uniform
B. X and Y are independent because f(x,y) factors into a function of x times a function of
y [CORRECT]
C. X and Y are independent only if c = 1
D. X and Y are dependent because their supports overlap
Correct Answer: B
Rationale: Two random variables are independent if and only if their joint PDF factors
into the product of their marginal PDFs: f(x,y) = a(x)b(y); here f(x,y) = cxy = (cx)(y) =
a(x)b(y), confirming independence. The constant c is determined by normalization
(∫∫f(x,y)dxdy = 1) and does not affect independence; overlapping support does not imply
dependence.
,Q2: A simulation model uses two independent and identically distributed (i.i.d.) random
variables X and Y, each with variance Var(X) = Var(Y) = 4. What is the variance of the
difference X - Y?
A. 0
B. 4
C. 8 [CORRECT]
D. 16
Correct Answer: C
Rationale: For independent random variables, Var(X - Y) = Var(X) + Var(Y) - 2Cov(X,Y) =
Var(X) + Var(Y) = 4 + 4 = 8, since Cov(X,Y) = 0 for independent variables. Note that Var(X
- Y) = Var(X + Y) for independent variables because variance is unaffected by sign
changes; this is a common point of confusion.
Q3: A simulation analyst is working with a Brownian bridge process B(t) on [0,1] with
B(0) = 0 and B(1) = 0. What is the expected value of the area under the Brownian bridge
curve from 0 to 1?
A. 0 [CORRECT]
B. 1/2
C. 1
D. The area is undefined for a Brownian bridge
,Correct Answer: A
Rationale: The Brownian bridge has E[B(t)] = 0 for all t ∈ [0,1] since it is a Brownian
motion conditioned on B(1) = 0, and Brownian motion has zero mean; therefore, E[∫₀¹
B(t)dt] = ∫₀¹ E[B(t)]dt = ∫₀¹ 0 dt = 0. The area under the curve is a random variable with
mean zero, positive variance, and known distribution properties.
Q4: A random variable X follows a geometric distribution with success probability p =
0.2. What is the expected number of trials until the first success?
A. 0.2
B. 4
C. 5 [CORRECT]
D. 20
Correct Answer: C
Rationale: For a geometric distribution (number of trials until first success), E[X] = 1/p =
1/0.2 = 5. This is distinct from the alternative parameterization (number of failures
before first success) where E[X] = (1-p)/p = 4; the question specifies "trials until first
success," so E[X] = 1/p = 5.
Q5: A simulation model requires generating random variables from a Poisson
distribution with rate λ = 3. What is the variance of this Poisson distribution?
, A. 1
B. 3 [CORRECT]
C. 9
D. √3
Correct Answer: B
Rationale: For a Poisson distribution, the mean and variance are equal: E[X] = Var(X) = λ
= 3. This is a defining property of the Poisson distribution; the standard deviation is √3,
but the variance is 3. This property makes the Poisson distribution useful for modeling
count data where the mean equals the variance.
Q6: A simulation analyst is modeling component lifetimes using a Weibull distribution
with shape parameter k = 2 and scale parameter λ = 100. Which statement about this
Weibull distribution is correct?
A. The hazard rate is constant over time
B. The hazard rate increases with time, indicating wear-out failure [CORRECT]
C. The hazard rate decreases with time, indicating infant mortality
D. The Weibull distribution reduces to an exponential distribution for all parameter
values
Correct Answer: B
Rationale: For a Weibull distribution, when the shape parameter k > 1, the hazard rate
increases with time (wear-out phase); when k < 1, the hazard rate decreases (infant
Simulation & Stochastic Modeling Assessment with Detailed Rationales | 100%
Verified | Pass Guaranteed – A+ Graded
Section A: Probability & Statistics Review
Q1: A simulation analyst is modeling two independent random variables X and Y with
joint PDF f(x,y) = cxy for 0 < x < 2 and 0 < y < 3. Which statement correctly characterizes
the independence of X and Y?
A. X and Y are dependent because the joint PDF is not uniform
B. X and Y are independent because f(x,y) factors into a function of x times a function of
y [CORRECT]
C. X and Y are independent only if c = 1
D. X and Y are dependent because their supports overlap
Correct Answer: B
Rationale: Two random variables are independent if and only if their joint PDF factors
into the product of their marginal PDFs: f(x,y) = a(x)b(y); here f(x,y) = cxy = (cx)(y) =
a(x)b(y), confirming independence. The constant c is determined by normalization
(∫∫f(x,y)dxdy = 1) and does not affect independence; overlapping support does not imply
dependence.
,Q2: A simulation model uses two independent and identically distributed (i.i.d.) random
variables X and Y, each with variance Var(X) = Var(Y) = 4. What is the variance of the
difference X - Y?
A. 0
B. 4
C. 8 [CORRECT]
D. 16
Correct Answer: C
Rationale: For independent random variables, Var(X - Y) = Var(X) + Var(Y) - 2Cov(X,Y) =
Var(X) + Var(Y) = 4 + 4 = 8, since Cov(X,Y) = 0 for independent variables. Note that Var(X
- Y) = Var(X + Y) for independent variables because variance is unaffected by sign
changes; this is a common point of confusion.
Q3: A simulation analyst is working with a Brownian bridge process B(t) on [0,1] with
B(0) = 0 and B(1) = 0. What is the expected value of the area under the Brownian bridge
curve from 0 to 1?
A. 0 [CORRECT]
B. 1/2
C. 1
D. The area is undefined for a Brownian bridge
,Correct Answer: A
Rationale: The Brownian bridge has E[B(t)] = 0 for all t ∈ [0,1] since it is a Brownian
motion conditioned on B(1) = 0, and Brownian motion has zero mean; therefore, E[∫₀¹
B(t)dt] = ∫₀¹ E[B(t)]dt = ∫₀¹ 0 dt = 0. The area under the curve is a random variable with
mean zero, positive variance, and known distribution properties.
Q4: A random variable X follows a geometric distribution with success probability p =
0.2. What is the expected number of trials until the first success?
A. 0.2
B. 4
C. 5 [CORRECT]
D. 20
Correct Answer: C
Rationale: For a geometric distribution (number of trials until first success), E[X] = 1/p =
1/0.2 = 5. This is distinct from the alternative parameterization (number of failures
before first success) where E[X] = (1-p)/p = 4; the question specifies "trials until first
success," so E[X] = 1/p = 5.
Q5: A simulation model requires generating random variables from a Poisson
distribution with rate λ = 3. What is the variance of this Poisson distribution?
, A. 1
B. 3 [CORRECT]
C. 9
D. √3
Correct Answer: B
Rationale: For a Poisson distribution, the mean and variance are equal: E[X] = Var(X) = λ
= 3. This is a defining property of the Poisson distribution; the standard deviation is √3,
but the variance is 3. This property makes the Poisson distribution useful for modeling
count data where the mean equals the variance.
Q6: A simulation analyst is modeling component lifetimes using a Weibull distribution
with shape parameter k = 2 and scale parameter λ = 100. Which statement about this
Weibull distribution is correct?
A. The hazard rate is constant over time
B. The hazard rate increases with time, indicating wear-out failure [CORRECT]
C. The hazard rate decreases with time, indicating infant mortality
D. The Weibull distribution reduces to an exponential distribution for all parameter
values
Correct Answer: B
Rationale: For a Weibull distribution, when the shape parameter k > 1, the hazard rate
increases with time (wear-out phase); when k < 1, the hazard rate decreases (infant
