ISYE 6402 FINAL TEST 2026 QUESTIONS
WITH CORRECT ANSWERS GRADED A+
◍ what is forward selection.
Answer: we select the best new factor and see if it's good enough (R^2, AIC,
or p-value) add it to our model and fit the model with the current set of
factors. Then at the end we remove factors that are lower than a certain
threshold
◍ Variance Reduction Techniques.
Answer: Methods used to improve the efficiency of a simulation by reducing
the variability of the output statistics.
◍ Linear Congruential Generator (LCG).
Answer: A common algorithm for generating pseudo-random numbers using
a linear recurrence relation modulo m.
◍ Initialization Bias (Start-up Bias).
Answer: The effect of the initial conditions of a simulation on the output
data, particularly in steady-state simulations.
◍ Input Analysis.
Answer: The process of identifying, collecting, and statistically modeling
the data that drives a simulation.
◍ Numerical Methods.
Answer: Computational techniques used to approximate solutions to
mathematical models, often when analytical solutions are not feasible.
◍ Dynamic Model.
Answer: A model that evolves or changes over time.
◍ Random Variate Generation.
Answer: The process of generating random numbers that follow a specific
, probability distribution, based on Unif(0,1) pseudo-random numbers.
◍ why do we have to scale the data for LASSO.
Answer: if we don't the measure of the data will artificially affect how big
the coefficients need to be
◍ Queueing Models.
Answer: Simulation models used to analyze systems involving waiting lines,
such as call centers or manufacturing processes.
◍ Seed.
Answer: The initial value used to start a pseudo-random number generator.
◍ Pseudo-Random Numbers (PRN's).
Answer: Numbers generated by a deterministic algorithm that appear to be
random and uniformly distributed between 0 and 1.
◍ Batch Means.
Answer: A method for analyzing steady-state simulations by dividing a
single long simulation run into contiguous batches and treating the mean of
each batch as an independent observation.
◍ Validation.
Answer: The process of determining whether the simulation model is an
accurate representation of the real-world system being studied.
◍ what are replications.
Answer: number of runs of a simulaiton
◍ What is the objective function in k-means.
Answer: minimize total distance from data points to their cluster centers
◍ Independent Replications.
Answer: A method for analyzing terminating simulations by running the
simulation multiple times with different random number streams to obtain
independent observations of system performance.
◍ what are the constraints in network models.
Answer: flow into node = flow out of node; flow on arc between min and
, max allowable
◍ If the interarrival time is exponential what type of distribution is the arrival.
Answer: poisson
◍ what are some common network models?.
Answer: shortest path model - find quickest/shortest route from one place to
another; assignment model - which worker gets which job to maximize
workforce efficiency; maximum flow model - how much oil can flow
through complex network of pipes
◍ what is the objective function for a time series model.
Answer: minimize prediction error
◍ Discrete Model.
Answer: A model where the state of the system changes only at a countable
number of points in time.
◍ order linear regression, ridge regession, elastic net and lasso regression in
order of variable selected ascending.
Answer: lasso, elastic net, ridge and linear (tied)
◍ Simulation Model.
Answer: A high-level representation used to imitate the operation of a
real-world process or system over time.
◍ what is a key difference between stepwise regresson and lasso regression.
Answer: If the data is not scaled, the coefficients can have artificially
different orders of magnitude, which means they'll have unbalanced effects
on the lasso constraint.
◍ How do you know when to switch from exploration to exploitation.
Answer: when a significant difference has been achieved (non-overlapping
CIs)
◍ Terminating Simulation.
Answer: A simulation where the system's behavior is of interest only for a
finite duration or until a specific event occurs.
WITH CORRECT ANSWERS GRADED A+
◍ what is forward selection.
Answer: we select the best new factor and see if it's good enough (R^2, AIC,
or p-value) add it to our model and fit the model with the current set of
factors. Then at the end we remove factors that are lower than a certain
threshold
◍ Variance Reduction Techniques.
Answer: Methods used to improve the efficiency of a simulation by reducing
the variability of the output statistics.
◍ Linear Congruential Generator (LCG).
Answer: A common algorithm for generating pseudo-random numbers using
a linear recurrence relation modulo m.
◍ Initialization Bias (Start-up Bias).
Answer: The effect of the initial conditions of a simulation on the output
data, particularly in steady-state simulations.
◍ Input Analysis.
Answer: The process of identifying, collecting, and statistically modeling
the data that drives a simulation.
◍ Numerical Methods.
Answer: Computational techniques used to approximate solutions to
mathematical models, often when analytical solutions are not feasible.
◍ Dynamic Model.
Answer: A model that evolves or changes over time.
◍ Random Variate Generation.
Answer: The process of generating random numbers that follow a specific
, probability distribution, based on Unif(0,1) pseudo-random numbers.
◍ why do we have to scale the data for LASSO.
Answer: if we don't the measure of the data will artificially affect how big
the coefficients need to be
◍ Queueing Models.
Answer: Simulation models used to analyze systems involving waiting lines,
such as call centers or manufacturing processes.
◍ Seed.
Answer: The initial value used to start a pseudo-random number generator.
◍ Pseudo-Random Numbers (PRN's).
Answer: Numbers generated by a deterministic algorithm that appear to be
random and uniformly distributed between 0 and 1.
◍ Batch Means.
Answer: A method for analyzing steady-state simulations by dividing a
single long simulation run into contiguous batches and treating the mean of
each batch as an independent observation.
◍ Validation.
Answer: The process of determining whether the simulation model is an
accurate representation of the real-world system being studied.
◍ what are replications.
Answer: number of runs of a simulaiton
◍ What is the objective function in k-means.
Answer: minimize total distance from data points to their cluster centers
◍ Independent Replications.
Answer: A method for analyzing terminating simulations by running the
simulation multiple times with different random number streams to obtain
independent observations of system performance.
◍ what are the constraints in network models.
Answer: flow into node = flow out of node; flow on arc between min and
, max allowable
◍ If the interarrival time is exponential what type of distribution is the arrival.
Answer: poisson
◍ what are some common network models?.
Answer: shortest path model - find quickest/shortest route from one place to
another; assignment model - which worker gets which job to maximize
workforce efficiency; maximum flow model - how much oil can flow
through complex network of pipes
◍ what is the objective function for a time series model.
Answer: minimize prediction error
◍ Discrete Model.
Answer: A model where the state of the system changes only at a countable
number of points in time.
◍ order linear regression, ridge regession, elastic net and lasso regression in
order of variable selected ascending.
Answer: lasso, elastic net, ridge and linear (tied)
◍ Simulation Model.
Answer: A high-level representation used to imitate the operation of a
real-world process or system over time.
◍ what is a key difference between stepwise regresson and lasso regression.
Answer: If the data is not scaled, the coefficients can have artificially
different orders of magnitude, which means they'll have unbalanced effects
on the lasso constraint.
◍ How do you know when to switch from exploration to exploitation.
Answer: when a significant difference has been achieved (non-overlapping
CIs)
◍ Terminating Simulation.
Answer: A simulation where the system's behavior is of interest only for a
finite duration or until a specific event occurs.
