ISYE 6644 OAN|001 EXAM 1, EXAM 2
AND FINAL EXAM SIMULATION —
ORIGINAL PRACTICE QUESTION BANK
QUESTIONS 1–100 WITH ANSWERS AND DETAILED
RATIONALES
INTRODUCTION
ISYE 6644 is centered on simulation modeling and analysis, with emphasis on
understanding stochastic systems, constructing valid simulation models, selecting
appropriate probability distributions, generating random variates, designing
experiments, and interpreting simulation output. This comprehensive practice bank is
intended for students preparing across the major assessment areas represented by
Exam 1, Exam 2, and the Final Exam. The questions emphasize application rather
than memorization: students must diagnose modeling choices, interpret statistical
output, distinguish discrete-event from continuous simulation approaches, reason
about queues and inventories, and select appropriate validation and experimental-
design procedures. The problems also address random-number generation, Monte
Carlo methods, input modeling, variance reduction, confidence intervals, warm-up
periods, replication, and performance measures. Each question provides four
alternatives with one best answer followed by a detailed rationale explaining both the
correct reasoning and why the alternatives are inappropriate. The material is designed
to function as a rigorous study resource for identifying conceptual weaknesses,
practicing quantitative reasoning, and developing the judgment needed to analyze
stochastic systems effectively.
CORE DOMAINS TESTED
1.
Simulation Fundamentals — Modeling stochastic systems, system
boundaries, entities, attributes, resources, events, and state variables.
2.
3.
Discrete-Event Simulation — Event scheduling, time advancement, queues,
resources, and state transitions.
4.
5.
1
,Monte Carlo Simulation — Random sampling and estimation of uncertain
quantities.
6.
7.
Probability and Random Variables — Distribution properties,
transformations, dependence, and conditional probability.
8.
9.
Random-Number Generation — Pseudorandom sequences, uniformity,
independence, seeds, and reproducibility.
10.
11.
Input Modeling — Selecting, fitting, and validating probability distributions.
12.
13.
Queueing and Waiting-Line Models — Arrival processes, service
mechanisms, utilization, congestion, and performance measures.
14.
15.
Simulation Output Analysis — Replications, confidence intervals, precision,
and statistical estimation.
16.
17.
Initialization and Termination — Warm-up periods, transient behavior,
steady state, and run length.
18.
19.
Variance Reduction — Common random numbers, antithetic variates, and
related techniques.
20.
21.
Verification and Validation — Establishing that a model is implemented
correctly and represents the intended system adequately.
2
, 22.
23.
Simulation Experimentation — Comparing alternatives, sensitivity analysis,
and interpreting simulation results.
24.
QUESTIONS 1-100
Q1:
A hospital emergency department is being modeled to evaluate the effect of adding a
second physician. Patients arrive randomly, wait for available physicians, receive
treatment, and then leave the system. Which representation is most appropriate for the
patient's status while waiting for a physician?
A) A permanent model parameter
B) A state-related condition indicating that the patient is in the waiting queue
C) A random-number seed
D) A model verification statistic
Rationale: The patient's position in the waiting queue represents the current state of
the system and changes as events occur. Option A is incorrect because a parameter
generally remains fixed during a particular experiment. Option C is incorrect because
a seed controls a pseudorandom sequence rather than patient status. Option D is
incorrect because verification statistics concern whether the model was implemented
correctly.
Q2:
A simulation clock currently reads 14.2 minutes. The event list contains events
scheduled at 14.7, 15.1, and 16.4 minutes. Under standard next-event time advance,
what happens next?
A) The clock advances to 14.3 minutes
B) The clock advances to 14.7 minutes and the corresponding event is executed
C) All three events are executed simultaneously
D) The clock remains at 14.2 until a new random number is generated
Rationale: In a next-event simulation, the clock jumps directly to the time of the
earliest scheduled event. Therefore 14.7 is the next event time. The other events
remain on the event list.
Q3:
3
, A modeler observes that the simulation produces implausibly long queues. Inspection
reveals that every customer requires service from the same server even though the real
facility has three parallel servers. This is primarily a problem of:
A) Random-number generation
B) Model representation
C) Confidence-interval construction
D) Replication independence
Rationale: The model incorrectly represents the system's resource structure. The issue
is not inherently random-number generation or statistical estimation; the model itself
fails to represent three parallel servers.
Q4:
A simulation model contains entities, resources, queues, and events. Which item most
directly causes a discrete-event simulation to change system state?
A) A static parameter
B) An event
C) A confidence interval
D) A histogram bin
Rationale: Events trigger state transitions, such as an arrival, service completion,
machine failure, or departure. Parameters and statistical summaries describe the
model but do not themselves constitute state-changing events.
Q5:
A manufacturing system is modeled in which machines can fail at random times and
repairs restore them to operation. Which event should be scheduled when a machine
fails?
A) Only the next customer arrival
B) A repair-completion event based on the repair-time model
C) A confidence-interval calculation
D) A new simulation replication
Rationale: Once a failure occurs, the model needs to represent the future repair
completion. A repair-time distribution can be sampled to schedule that event.
Q6:
A simulation of a call center treats the number of calls in the system as a variable that
changes after arrivals and departures. This quantity is best classified as:
A) A fixed input parameter
B) A state variable
4
AND FINAL EXAM SIMULATION —
ORIGINAL PRACTICE QUESTION BANK
QUESTIONS 1–100 WITH ANSWERS AND DETAILED
RATIONALES
INTRODUCTION
ISYE 6644 is centered on simulation modeling and analysis, with emphasis on
understanding stochastic systems, constructing valid simulation models, selecting
appropriate probability distributions, generating random variates, designing
experiments, and interpreting simulation output. This comprehensive practice bank is
intended for students preparing across the major assessment areas represented by
Exam 1, Exam 2, and the Final Exam. The questions emphasize application rather
than memorization: students must diagnose modeling choices, interpret statistical
output, distinguish discrete-event from continuous simulation approaches, reason
about queues and inventories, and select appropriate validation and experimental-
design procedures. The problems also address random-number generation, Monte
Carlo methods, input modeling, variance reduction, confidence intervals, warm-up
periods, replication, and performance measures. Each question provides four
alternatives with one best answer followed by a detailed rationale explaining both the
correct reasoning and why the alternatives are inappropriate. The material is designed
to function as a rigorous study resource for identifying conceptual weaknesses,
practicing quantitative reasoning, and developing the judgment needed to analyze
stochastic systems effectively.
CORE DOMAINS TESTED
1.
Simulation Fundamentals — Modeling stochastic systems, system
boundaries, entities, attributes, resources, events, and state variables.
2.
3.
Discrete-Event Simulation — Event scheduling, time advancement, queues,
resources, and state transitions.
4.
5.
1
,Monte Carlo Simulation — Random sampling and estimation of uncertain
quantities.
6.
7.
Probability and Random Variables — Distribution properties,
transformations, dependence, and conditional probability.
8.
9.
Random-Number Generation — Pseudorandom sequences, uniformity,
independence, seeds, and reproducibility.
10.
11.
Input Modeling — Selecting, fitting, and validating probability distributions.
12.
13.
Queueing and Waiting-Line Models — Arrival processes, service
mechanisms, utilization, congestion, and performance measures.
14.
15.
Simulation Output Analysis — Replications, confidence intervals, precision,
and statistical estimation.
16.
17.
Initialization and Termination — Warm-up periods, transient behavior,
steady state, and run length.
18.
19.
Variance Reduction — Common random numbers, antithetic variates, and
related techniques.
20.
21.
Verification and Validation — Establishing that a model is implemented
correctly and represents the intended system adequately.
2
, 22.
23.
Simulation Experimentation — Comparing alternatives, sensitivity analysis,
and interpreting simulation results.
24.
QUESTIONS 1-100
Q1:
A hospital emergency department is being modeled to evaluate the effect of adding a
second physician. Patients arrive randomly, wait for available physicians, receive
treatment, and then leave the system. Which representation is most appropriate for the
patient's status while waiting for a physician?
A) A permanent model parameter
B) A state-related condition indicating that the patient is in the waiting queue
C) A random-number seed
D) A model verification statistic
Rationale: The patient's position in the waiting queue represents the current state of
the system and changes as events occur. Option A is incorrect because a parameter
generally remains fixed during a particular experiment. Option C is incorrect because
a seed controls a pseudorandom sequence rather than patient status. Option D is
incorrect because verification statistics concern whether the model was implemented
correctly.
Q2:
A simulation clock currently reads 14.2 minutes. The event list contains events
scheduled at 14.7, 15.1, and 16.4 minutes. Under standard next-event time advance,
what happens next?
A) The clock advances to 14.3 minutes
B) The clock advances to 14.7 minutes and the corresponding event is executed
C) All three events are executed simultaneously
D) The clock remains at 14.2 until a new random number is generated
Rationale: In a next-event simulation, the clock jumps directly to the time of the
earliest scheduled event. Therefore 14.7 is the next event time. The other events
remain on the event list.
Q3:
3
, A modeler observes that the simulation produces implausibly long queues. Inspection
reveals that every customer requires service from the same server even though the real
facility has three parallel servers. This is primarily a problem of:
A) Random-number generation
B) Model representation
C) Confidence-interval construction
D) Replication independence
Rationale: The model incorrectly represents the system's resource structure. The issue
is not inherently random-number generation or statistical estimation; the model itself
fails to represent three parallel servers.
Q4:
A simulation model contains entities, resources, queues, and events. Which item most
directly causes a discrete-event simulation to change system state?
A) A static parameter
B) An event
C) A confidence interval
D) A histogram bin
Rationale: Events trigger state transitions, such as an arrival, service completion,
machine failure, or departure. Parameters and statistical summaries describe the
model but do not themselves constitute state-changing events.
Q5:
A manufacturing system is modeled in which machines can fail at random times and
repairs restore them to operation. Which event should be scheduled when a machine
fails?
A) Only the next customer arrival
B) A repair-completion event based on the repair-time model
C) A confidence-interval calculation
D) A new simulation replication
Rationale: Once a failure occurs, the model needs to represent the future repair
completion. A repair-time distribution can be sampled to schedule that event.
Q6:
A simulation of a call center treats the number of calls in the system as a variable that
changes after arrivals and departures. This quantity is best classified as:
A) A fixed input parameter
B) A state variable
4
