pg. 1
ISYE 6501 - MIDTERM 2 EXAM WITH STUDY GUIDE EXAM
LATEST 2025| COMPLETE 350 ACCURATE QUESTIONS AND
VERIFIED ANSWERS (100% CORRECT ANSWERS) ALREADY
GRADED A+
What is forward selection? - ANSWER - Start with a model with no factors, at each step, find each best new factor to add to model, and put it in if good enough (parameter of your choice like p value<=0.15) improvement; when there is no factor that is good enough or if we add enough factors, we stop; can remove any factors at the end
What is backward selection? - ANSWER - Start with all factors, and at each step, we find worst factor, and remove from model and we keep going until no factor bad enough to remove or we reach the number of factors we want
What is stepwise regression? - ANSWER - it is a combination of forward selection and backward elimination. We can either start with all factors or no factors and at each step we remove or add a factor. As we go through the procedure after adding each new factor and at the end we eliminate right away factors that no longer appear; Allows model to adjust if factor we earlier thought we needed no longer seems necessary thanks to new factors added
What is a greedy algorithm? - ANSWER - At each step, it does the one thing that looks best without future options are considered
What is the multi-armed bandit? - ANSWER - Testing multiple alternatives, but updating probability of each alternative after each test to reach the right choice - exploration and exploitation 1 / 4
pg. 2 What are some parameters of multi-armed bandit iteration? - ANSWER - * number of tests between recalculating probabilities
- how to update probabilities (Bayesian updates, observed distribution)
- how to pick an alternative to test based on probabilities and/or expected
values
What is a Bernoulli distribution? - ANSWER - it's like a flipping coin. It can be used to model a single event and is most useful when we put many of them together
What is the Binomial distribution? - ANSWER - Probability of getting x success out of n independent identically distributed Bernoulli(p) trials.
For binomial distribution, as n gets very large... - ANSWER - the distribution converges to normal distribution
What is the geometric distribution? - ANSWER - * Probability of having x Bernoulli(p) failures until first success or, having x Bernoulli (1-p) success until first failure; assumes each Bernoulli trial is independent and identically distributed; if it is geometric, then its II
What is the Poisson Distribution? - ANSWER - Distribution of random events in a period, good at modeling random arrivals
What is the lambda in the Poisson Distribution? - ANSWER - average number of arrivals or events / time period
What is the exponential distribution? - ANSWER - If arrivals are Poisson distribution (lambda), the time between successive arrivals is exponential (lambda), while arrival time is 1/lambda 2 / 4
pg. 3 What is the Weibull distribution? - ANSWER - Useful modeling the amount of time something to fail, specifically time between failures - similar to Geometric, but Geometric tracks the number of trials while Weibull measures time
What is the QQ plot? - ANSWER - The idea of Q-Q plot is that whatever variations in the data there might be, and even if the number of data points in two sets is different, two similar distributions should have about the same value at each quantile
Why is it sometimes better to visualize the distribution of two data sets rather than just doing a statistical test? - ANSWER - A visual representation can may give more information such as where the distribution of data sets are different, while a statistical test may just show if it is differing or not
Memoryless Property - ANSWER - Means it doesn't matter what happens in the past, all that matters is where we are now in probability
Which distribution is memoryless? - ANSWER - Exponential distribution and Poisson distribution; the next state of a 'memoryless' process doesn't depend on previous states, but it does depend on the current state
If it is not memoryless, it is not... - ANSWER - Exponential
What is a deterministic simulations? - ANSWER - · Same inputs give the same outputs (no randomness)
What is stochastic simulations? - ANSWER - · Use when system has randomness, may get a different output even with the same input 3 / 4
pg. 4 What is the Markov chain model? - ANSWER - based on states of system; apply a change matrix p to the current state n number of times
What is steady state? - ANSWER - the state has gotten so mixed, initial condition doesn't matter, in steady state, the probability of being in state i is everyday
What is a key assumption of Markov chain? - ANSWER - It is memoryless, the state transitions only depend on the most recent state, though most systems do not exhibit this property
What is modularity? - ANSWER - measures of how well the graph is separated into communities or modules that are connected a lot internally but not connected much in between each other
What are the three levels of neurons - ANSWER - 1. Input level - external inputs, each neuron accepts a single piece of information
- Hidden level
- Output level
The flow of neural network - ANSWER - each neuron gets an input from previous layer, calculates function of weighted inputs, gives its output in next layer
When we create models, we assume the system does not react; give examples of when it does - ANSWER - Pricing decisions - company may model based on competitor pricing, but the competitor pricing may change based on the company's pricing Government tax policy - government set corporate tax policies and companies react by how to store and spend money
- / 4