Comprehensive Spreadsheet Modeling

The reduced cost for a decision variable that appears in a Sensitivity Report indicates the change in the optimal objective function value that results from changing the right-hand side of the nonnegativity constraint from a. 0 to 1. b. 0 to -1. c. 1 to 0. d. -1 to 0.

0 to 1.

Fast food restaurants pride themselves in being able to fill orders quickly. A study was done at a local fast food restaurant to determine how long it took customers to receive their order at the drive-thru. It was discovered that the time it takes for orders to be filled is exponentially distributed with a mean of 1.5 minutes. What is the probability that it takes less than one minute to fill an order? a. 0.4866 b. 0.6321 c. 0.7769 d. 0.1813

0.4866

Using the data below, what would be the joint probabilities, P(U ∩ Sj)? States of Nature (sj) Prior Probabilities P(sj) Conditional Probabilities P(U | sj) s1 0.65 0.75 s2 0.20 0.35 s3 0.15 0.20 Total 1.00 ​ a. 0.49, 0.07, and 0.03 b. 1.00, 0.59, and 1.00 c. 0.83, 0.12, and 0.05 d. 0.47, 0.49, and 0.04

0.49, 0.07, and 0.03

Using the data below, which of the following would be the posterior probabilities, P(Sj | U)? States of Nature (sj) Prior Probabilities P(sj) Conditional Probabilities P(U | sj) s1 0.65 0.75 s2 0.20 0.35 s3 0.15 0.20 Total 1.00 ​ a. 0.83, 0.12, and 0.05 b. 0.47, 0.49, and 0.04 c. 1.00, 0.59, and 1.00 d. 0.49, 0.07, and 0.03

0.83, 0.12, and 0.05

What is the total area under the normal distribution curve? a. It must be calculated b. 1 c. It depends upon the mean and standard deviation d. 100

1

A survey of 100 random high school students finds that 85 students watched the Super Bowl, 25 students watched the Stanley Cup Finals, and 20 students watched both games. How many students did not watch either game? a. 10 b. 30 c. 15 d. 20

10

Which of the following is the value of e, the mathematical constant used in the exponential utility function, U(x) = 1 - e-x/R? a. 3.14159 b. 2.71828 c. 1 d. The value of e depends on the risk tolerance value.

2.71828

The profit realized by the sales of a particular item follows a normal distribution with a mean of $0.5 million per quarter and a standard deviation of $0.1 million per quarter. What percent of the quarters can be expected to see a profit of at least $0.5 million? a. 60% b. 40% c. 10% d. 50%

50%

decision variable

A controllable input for a linear programming model is known as a

time series

A set of observations on a variable measured at successive points in time or over successive periods of time constitute a

number of time series values under consideration

In the moving averages method, the order k determines the

__________ is the situation in which no solution to the linear programming problem satisfies all the constraints. a. Unboundedness b. Infeasibility c. Optimality d. Divisibility

Infeasibility

Which of the following is true of verification? a. It requires an agreement among analysts and managers. b. It is performed prior to the development of the computer procedure for simulation. c. It deals with the accurate modeling of real system operations. d. It is largely a debugging task.

It is largely a debugging task.

RANDBETWEEN

The Excel function __________ generates integer values between lower and upper bounds.

exponential

The type of distribution shown in the graph below is a(n) __________ distribution.

The outcome of a simulation experiment is a(n) a. probability distribution for one or more output measures. b. objective function. c. single number. d. what-if scenario.

probability distribution for one or more output measures.

the better the classifier is at identifying responders...

the larger the vertical gap between points on the red and blue curves.

The center of a normal curve is a. the mean of the distribution. b. equal to the standard deviation. c. always a positive number. d. always equal to zero.

the mean of the distribution.

Class 1 error rate

"false negative error rate" or error of omission determining something is not when it actually is FN / ( TP + FN)

What would be the value added by a market analysis undertaken if the expected value with sample information is $8.56 million and the expected value without sample information is $6.39 million? a. $6.39 million b. $2.17 million c. $14.95 million d. $8.56 million

$2.17 million

Logistic Function Equation

1/1+e^-x

The random variable X is known to be uniformly distributed between 2 and 12. Compute the standard deviation of X. a. 8.333 b. 12 c. 2.887 d. 3.464

2.887

The number of minutes that Samantha waits to catch the bus is uniformly distributed between 0 and 15 minutes. What is the probability that Samantha has to wait less than 4.5 minutes to catch the bus? a. 20% b. 30% c. 10% d. 3%

30%

The random variable X is known to be uniformly distributed between 2 and 12. Compute E(X), the expected value of the distribution. a. 6 b. 7 c. 4 d. 5

7

trial

A set of values for the random variables is called a(n)

uniformly distributed

All the values of computer-generated random numbers are

__________ refers to the probability of one event, given the known outcome of a (possibly) related event. a. Conditional probability b. Decisive probability c. Priori probability d. Joint probability

Conditional probability

A special case of sample information where the information tells the decision maker exactly which state of nature is going to occur is known as __________ information. a. conditional b. prior c. mutual d. perfect

Perfect

__________, or modeling, is the process of translating a verbal statement of a problem into a mathematical statement. a. Problem-solving approach b. Data preparation c. Data structuring d. Problem formulation

Problem formulation

probability distribution for one or more output measures

The outcome of a simulation experiment is a(n)

76.5

The weekly demand for an item in a retail store follows a uniform distribution over the range 70 to 83. What would be the weekly demand if its corresponding computer-generated value is 0.5?

Range of the distribution

Which of the following parameters is required to convert a computer-generated random variable into a uniform random variable?

For a particular maximization problem, the payoff for the best decision alternative is $15.7 million while the payoff for one of the other alternatives is $12.9 million. The regret associated with the alternate decision would be a. $15.7 million. b. $0.129 million. c. $28.6 million. d. $2.8 million.

$2.8 million.

Brett wants to sell throw blankets for the holiday season at a local flea market. Brett purchases the throws for $15 and sells them to his customers for $35. The rental space is fixed fee of $1,500 for the season. Assume there is no leftover value for unsold units. If he orders 200 and demand is 150, what is the payoff? a. $800 b. $2,800 c. $750 d. $50

$750

Confusion Matrix

- A matrix showing the counts of actual versus predicted class values. - Classification error is commonly displayed in this - Displays a model's correct and incorrect classifications exp: class 1 = loan default and class 0 = no default

In the probability table below, which value is a marginal probability? Completed Obstacle Course Level No Yes Total Challenging 0.4 0.3 0.7 Easy 0.1 0.2 0.3 Total 0.5 0.5 1.0

0.5

Data Mining Process

1. Data sampling 2. Data preparation 3. Data partitioning 4. Model construction 5. Model assessment

A health conscious student faithfully wears a device that tracks his steps. Suppose that the distribution of the number of steps he takes is normally distributed with a mean of 10,000 and a standard deviation of 1,500 steps. How many steps would he have to take to make the cut for the top 5% for his distribution? a. 7,533 b. 10,000 c. 12,467 d. 8,078

12,467

Fast food restaurants pride themselves in being able to fill orders quickly. A study was done at a local fast food restaurant to determine how long it took customers to receive their order at the drive thru. It was discovered that the time it takes for orders to be filled is exponentially distributed with a mean of 1.5 minutes. What is the probability density function for the time it takes to fill an order?

2/3e

What is the mean of x, given the exponential probability function a. 0.05 b. 100 c. 20 d. 2,000

20

The newest model of smart car is supposed to get excellent gas mileage. A thorough study showed that gas mileage (measured in miles per gallon) is normally distributed with a mean of 75 miles per gallon and a standard deviation of 10 miles per gallon. What value represents the 50th percentile of this distribution? a. 85 b. 75 c. 105 d. 95

75

The weekly demand for an item in a retail store follows a uniform distribution over the range 70 to 83. What would be the weekly demand if its corresponding computer-generated value is 0.5? a. 90.1 b. 76.5 c. 50.85 d. 83

76.5

A health conscious student faithfully wears a device that tracks his steps. Suppose that the distribution of the number of steps he takes in a day is normally distributed with a mean of 10,000 and a standard deviation of 1,500 steps. One day he took 13,000 steps. What was his percentile on that day? a. 95% b. 100% c. 97.7% d. 99.7%

97.7%

A health conscious student faithfully wears a device that tracks his steps. Suppose that the distribution of the number of steps he takes in a day is normally distributed with a mean of 10,000 and a standard deviation of 1,500 steps. What percent of the days does he exceed 13,000 steps? a. 5% b. 2.28% c. 97.72% d. 95%

97.72%

Which of the following functions computes a value such that 2.5% of the area under the standard normal distribution lies in the upper tail defined by this value? a. =NORM.S.INV(0.975) b. =NORM.S.INV(0.025) c. =NORM.S.INV(0.05) d. =NORM.S.INV(0.95)

=NORM.S.INV(0.975)

Which of the following Excel functions would generate random integers from 0 to 100? a. =RAND( ) b. =SUMIF(A1:A100, 100) c. =RANDBETWEEN(0, 100) d. =100*RAND( )

=RANDBETWEEN(0, 100)

what-if

A __________ analysis involves considering alternative values for the random variables and computing the resulting value for the output.

Monte Carlo simulation

A ___________ uses repeated random sampling to represent uncertainty in a model representing a real system and that computes the values of model outputs.

Cumulative lift chart

A chart used to present how well a model performs in identifying observations most likely to be in Class 1 as compared with random classification.

probability distribution

A description of the range and relative likelihood of possible values of an uncertain variable is known as a

there is no indication of the likelihood of various output values

A disadvantage of the simple what-if analyses is that

normal

A distribution of a random variable for which values extremely larger or smaller than the mean are increasingly unlikely can possibly be modeled as a(n) _____________ probability distribution.

prediction of future values of a time series

A forecast is defined as a(n)

linear function

A mathematical function in which each variable appears in a separate term and is raised to the first power is known as a

replacing the use of single values for parameters with a range of possible values

A simulation model extends spreadsheet modeling by

random variable

A(n) __________ is an input to a simulation model whose value is uncertain and described by a probability distribution.

feasible

A(n) ___________ solution satisfies all the constraint expressions simultaneously.

Which of the following numbers cannot result from the Excel function =NORM.INV(RAND( ), 100, 10)? a. 115 b. 121 c. 99 d. All of these numbers can result from this Excel function.

All of these numbers can result from this Excel function.

the percentage of change between periods in the value of the variable is relatively constant

An exponential trend pattern occurs when

controllable input

An input to a simulation model that is selected by the decision maker is known as a

Which of the following tools is used to create decision trees in Excel? a. GoalSeek b. Analytic Solver Platform c. Data Analysis d. WhatIf

Analytic Solver Platform

Choosing a decision alternative that maximizes the minimum profit is a feature of the __________ approach. a. expected value b. conservative c. maximin regret d. optimistic

Conservative

Rob is a financial manager with Sharez, an investment advisory company. He must select specific investments—for example, stocks and bonds—from a variety of investment alternatives. Restrictions on the type of permissible investments would be a __________ in this case. a. surplus variable b. feasible solution c. slack variable d. constraint

Constraint

restrictions that limit the settings of the decision variables

Constraints are

Supervised Learning

Data mining methods for predicting an outcome based on a set of input variables, or features. Usually makes use of human-labeled data.

___________ are graphical representations of the decision problems that show the sequential nature of the decision-making process. a. Influence diagrams b. Decision trees c. Payoff tables d. Utility functions

Decision trees

Which of the following cannot be described by a discrete probability distribution? a. The cost of parts for manufacturing an item, where the parts can take on any value between $80 and $100. b. Sales of two medical devices in which Device A generates $35 per unit sold and will likely constitute 30% of the sales and Device B generates $50 per unit sold and will likely constitute 70% of the sales. c. The number of units produced in a given day, where 20% of the time 99 units are produced and 80% of the time 100 units are produced. d. The labor cost for manufacturing goods, where one-third of the units cost $10 in labor, one-third cost $15 in labor, and one-third cost $50 in labor.

Each simulation run provides only a sample of how the real system will operate

Which of the following is a disadvantage of using simulation? a. Experimenting directly with a simulation model is often not feasible. b. Simulation models warn against poor decision strategies by projecting disastrous outcomes such as system failures, large financial losses, and so on. c. The simulation models are used to describe systems without requiring the assumptions that are required by mathematical models. d. Each simulation run provides only a sample of how the real system will operate.

Each simulation run provides only a sample of how the real system will operate

Supervised learning used for

Estimation of a continuous outcome. Classification of a categorical outcome.

In Excel, the expression LN(RAND())*(-m) would generate a(n) __________ random variable with mean m. a. lognormal b. logarithmic c. exponential d. normal

Exponential

Class 0 Error Rate

FP / (FP + TP) --- "false positive error rate" determines something that is actually not innocent person is guilty/ healthy person diagnosed with cancer

overall error rate equation

False Neg + False Positive / True Positive + False Positive + False Negative + True Neg (FN + FP) / (TP+ FP + FN + TN)

A(n) ___________ solution satisfies all the constraint expressions simultaneously. a. objective b. feasible c. infeasible d. extreme

Feasible

NORM.INV

For a given mean and standard deviation, the __________ function in Excel is used to generate a value for the random variable characterized by a normal distribution.

is associated with measuring forecast accuracy

Forecast error

logistic regression model

Given a set of explanatory variables, a logistic regression algorithm determines values of that best estimate the log odds

Examples of Unsupervised Learning

Hierarchical clustering k-means clustering Association rules

Which statement is true about mutually exclusive events? a. If either event A or event B must occur, they are called mutually exclusive. b. P(A) + P(B) = 1 for any events A and B that are mutually exclusive. c. If events A and B cannot occur at the same time, they are called mutually exclusive. d. None of these choices are correct.

If events A and B cannot occur at the same time, they are called mutually exclusive.

2.5

If the forecasted value of the time series variable for period 2 is 22.5 and the actual value observed for period 2 is 25, what is the forecast error in period 2?

exponential

In Excel, the expression LN(RAND())*(-m) would generate a(n) ____________________ random variable with mean m.

continuous probability

In a __________ distribution, a random variable can take any value in a specified range.

the most likely values for the random variables of a model.

In a base-case scenario, the output is determined by assuming

objective is expressed in terms of the decision variables.

In problem formulation, the

The average monthly salary is $3,000

In reviewing the graph below, which of the following inferences can be drawn about the monthly salary?

probability distributions

In simulation analysis, the ___________ of random variables can be adjusted to determine the impact of the assumptions about the shape of the uncertainty on the results.

Rob is a financial manager with Sharez, an investment advisory company. He must select specific investments—for example, stocks and bonds—from a variety of investment alternatives. Which of the following statements is most likely to be the objective function in this scenario? a. Maximization of investment risk b. Minimization of the number of stocks held c. Minimization of tax dues d. Maximization of expected return

Maximization of expected return

For a minimization problem, the optimistic approach often is referred to as the __________ approach. a. maximax b. minimax c. maximin d. minimin

Minimin

A canned food manufacturer has its manufacturing plants in three locations across a state. Their product has to be transported to 3 central distribution centers, which in turn disperse the goods to 72 stores across the state. Which of the following is most likely to be the objective function in this scenario? a. Increasing the number of goods manufactured at the plant b. Decreasing the cost of their raw material sourcing c. Minimizing the quantity of goods distributed across the stores d. Minimizing the cost of shipping goods from the plant to the store

Minimizing the cost of shipping goods from the plant to the store

A ___________ uses repeated random sampling to represent uncertainty in a model representing a real system and that computes the values of model outputs. a. Monte Carlo simulation b. deterministic model c. discrete event simulation d. what-if analysis

Monte Carlo simulation

For a given mean and standard deviation, the __________ function in Excel is used to generate a value for the random variable characterized by a normal distribution. a. VLOOKUP b. FREQUENCY c. RAND d. NORM.INV

NORM.INV

The __________ function in Excel is used to compute the statistics required to create a histogram. a. NORM.INV b. RAND c. FREQUENCY d. STDEV.S

NORM.INV

In a normal distribution, which is greater, the mean or the median? a. Mean b. Median c. Neither the mean or the median (they are equal) d. Cannot be determined with the information provided.

Neither the mean or the median (they are equal)

A canned food manufacturer has its manufacturing plants in three locations across a state. Their product has to be transported to 3 central distribution centers, which in turn disperse the goods to 72 stores across the state. Which of the following visualization tools could help understand this problem better? a. Scatter chart b. Contour plot c. Time-series plot d. Network graph

Network graph

Which of the following cannot be modeled by a continuous distribution? a. Height of the finished manufactured product b. Number of products produced in an hour c. Length of time it takes to manufacture a product d. Weight of a finished manufactured product

Number of products produced in an hour

Which of the following error messages is displayed in Excel Solver when attempting to solve an unbounded problem? a. Solver could not find a feasible solution. b. Solver could not find a bounded solution. c. Objective Cell values do not converge. d. Solver cannot improve the current solution. All constraints are satisfied.

Objective Cell values do not converge.

The __________ approach evaluates each decision alternative in terms of the best payoff that can occur. a. optimistic b. conservative c. maximin regret d. expected value

Optimistic

A(n) _________ refers to the result obtained when a decision alternative is chosen and a chance event occurs. a. payoff table b. node c. state of nature d. outcome

Outcome

The __________ probability distribution can be used to estimate the number of vehicles that go through an intersection during the lunch hour. a. binomial b. triangular c. Poisson d. normal

Poisson

__________ refer to the probabilities of the states of nature after revising the prior probabilities based on sample information. a. Posterior probabilities b. Perfect probabilities c. Preliminary probabilities d. Joint probabilities

Posterior probabilities

The __________ assumption necessary for a linear programming model to be appropriate means that the contribution to the objective function and the amount of resources used in each constraint are in accordance to the value of each decision variable. a. negativity b. additivity c. divisibility d. proportionality

Proportionality

The __________ function is used to generate a pseudorandom number in Excel. a. FREQUENCY() b. ROUND() c. RAND() d. NORM.INV()

RAND()

The Excel function __________ generates integer values between lower and upper bounds. a. RANDBETWEEN b. UPPER c. LOWER d. RAND

RANDBETWEEN

Which of the following parameters is required to convert a computer-generated random variable into a uniform random variable? a. Mean of the distribution b. Range of the distribution c. Moments of the distribution d. Variance of the distribution

Range of the distribution

__________ is the study of the possible payoffs and probabilities associated with a decision alternative or a decision strategy in the face of uncertainty. a. Certainty analysis b. Optimization c. Cost analysis d. Risk analysis

Risk analysis

Maximization of expected return

Rob is a financial manager with Sharez, an investment advisory company. He must select specific investments—for example, stocks and bonds—from a variety of investment alternatives. Which of the following statements is most likely to be the objective function in this scenario?

Suppose that profit for a particular product is calculated using the linear equation: Profit = 20S + 3D. Which of the following combinations of S and D would yield a maximum profit? a. S = 0, D = 299 b. S = 182, D = 145 c. S = 405, D = 0 d. S = 0, D = 0

S = 405, D = 0

Which algorithm, developed by George Dantzig and utilized by Excel Solver, is effective at investigating extreme points in an intelligent way to find the optimal solution to even very large linear programs? a. Ellipsoidal algorithm b. Trial-and-error algorithm c. Simplex algorithm d. Complex algorithm

Simplex algorithm

_____________ are possible outcomes for chance events that affect the consequences associated with a decision alternative. a. Payoffs b. Decision trees c. States of nature d. Forecasts

States of nature

FREQUENCY

The __________ function in Excel is used to compute the statistics required to create a histogram.

specificity

The ability to correctly predict Class 0 (negative) observations is 1 - class 0 error rate

sensitivity or recall

The ability to correctly predict Class 1 (positive) observations 1 - class 1 error rate

Negative Avg error

The average error estimates the bias in a model's predictions. If the average error is ____________ , then the model tends to overestimate the value of the outcome variable.

Positive Avg Error

The average error estimates the bias in a model's predictions. If the average error is ____________. If the average error is positive, the model tends to underestimate

In reviewing the graph below, which of the following inferences can be drawn about the monthly salary? a. The monthly salary is always less than $3,000. b. The range of the monthly salary distribution is $3,000 to $5,000. c. The average monthly salary is $3,000. d. The monthly salary is always greater than $3,000.

The average monthly salary is $3,000.

Which of the following statements is correct? a. The binomial and normal distributions are both continuous probability distributions. b. The binomial distribution is a continuous probability distribution, and the normal distribution is a discrete probability distribution. c. The binomial distribution is a discrete probability distribution and the normal distribution is a continuous probability distribution. d. The binomial and normal distributions are both discrete probability distributions.

The binomial distribution is a discrete probability distribution and the normal distribution is a continuous probability distribution.

historical data

The choice of the probability distribution for a random variable can be guided by

determining how well a particular forecasting method is able to reproduce the time series data that are already available

The mean absolute error, mean squared error, and mean absolute percentage error are all methods to measure the accuracy of a forecast. These methods measure forecast accuracy by

uses the average of the most recent data values in the time series as the forecast for the next period

The moving averages method refers to a forecasting method that

Which of the following is a discrete random variable? a. The amount of gasoline purchased by a customer b. The height of water-oak trees c. The amount of mercury found in fish caught in the Gulf of Mexico d. The number of times a student guesses the answers to questions on a certain test

The number of times a student guesses the answers to questions on a certain test

overall error rate

The percentage of misclassified observations is expressed as the

extreme points

The points where constraints intersect on the boundary of the feasible region are termed as the

verification

The process of determining that a computer program implements a simulation model as it is intended is known as

Risk Analysis

The process of evaluating a decision in the face of uncertainty by quantifying the likelihood and magnitude of an undesirable outcome is known as

discrete-event

The random variables corresponding to the interarrival times of customers and the service times of the servers are commonly part of a(n) __________ simulation.

0 to 1

The reduced cost for a decision variable that appears in a Sensitivity Report indicates the change in the optimal objective function value that results from changing the right-hand side of the nonnegativity constraint from

unbounded

The situation in which the value of the solution may be made infinitely large in a maximization linear programming problem or infinitely small in a minimization problem without violating any of the constraints is known as

cutoff value

The smallest value that the predicted probability of an observation can be for the observation to be classified as Class 1.

Which of the following is not a characteristic of the normal probability distribution? a. The mean of the distribution can be negative, zero, or positive. b. The standard deviation must be 1. c. The mean, median, and the mode are equal. d. The distribution is symmetrical.

The standard deviation must be 1.

minimized in a linear programming model

The term __________ refers to the expression that defines the quantity to be maximized or

Uniform Distribution

The time it takes to manufacture a product is modeled by a continuous distribution. The time to manufacture one unit can take anywhere from 5 to 6 minutes with equal probability. What distribution can be used to model the random variable, production time?

generated randomly from probability distributions

The values for random variables in a Monte Carlo simulation are

Which of the following inferences about a variable of interest can be drawn from the graph given below? a. The variable is more likely to take the value 20 than 40. b. The variable is equally likely to take any value between 20 and 40. c. The variable can only take the value 30. d. The variable is more likely to take any value outside the range of 20 and 40.

The variable is more likely to take any value outside the range of 20 and 40.

Which of the following is true of decision trees when used to solve a complex problem? a. They provide a useful way to decompose the problem. b. They can be converted into truth tables. c. They can be used only when the decision maker is risk neutral. d. They are used to compute a decision maker's risk tolerance.

They provide a useful way to decompose the problem.

K Nearest-Neighbors (k-NN)

This method can be used either to classify a categorical outcome or predict a continuous outcome.

The situation in which the value of the solution may be made infinitely large in a maximization linear programming problem or infinitely small in a minimization problem without violating any of the constraints is known as a. semi-optimality. b. unbounded. c. infiniteness. d. infeasibility.

Unbounded

The time it takes to manufacture a product is modeled by a continuous distribution. The time to manufacture one unit can take anywhere from 5 to 6 minutes with equal probability. What distribution can be used to model the random variable, production time? a. Discrete probability distribution b. Binomial distribution c. Normal distribution d. Uniform distribution

Uniform distribution

smoothing out random fluctuations

Using a large value for order k in the moving averages method is effective in

__________ is a measure of the total worth of a consequence reflecting a decision maker's attitude toward considerations such as profit, loss, and risk. a. Decision value b. Utility c. Cost-to-company d. Regret

Utility

__________ is the process of determining that a simulation model provides an accurate representation of a real system. a. Validation b. Verification c. Consideration d. Regression

Validation

The cost of parts for manufacturing an item, where the parts can take on any value between $80 and $100

Which of the following cannot be described by a discrete probability distribution?

Number of products produced in an hour

Which of the following cannot be modeled by a continuous distribution?

The variable is more likely to take any value outside the range of 20 and 40.

Which of the following inferences about a variable of interest can be drawn from the graph given below?

Each simulation run provides only a sample of how the real system will operate

Which of the following is a disadvantage of using simulation?

Operational variations

Which of the following is not present in a time series?

The time series plot is a straight line

Which of the following is not true of a stationary time series?

It is chosen as the value that minimizes a selected measure of forecast accuracy such as the mean squared error.

Which of the following is true of the exponential smoothing coefficient?

It is largely a debugging task

Which of the following is true of verification?

Mean forecast error

Which of the following measures of forecast accuracy is susceptible to the problem of positive and negative forecast errors offsetting one another?

To smooth out random fluctuations in the time series

Which of the following statements is the objective of the moving averages and exponential smoothing methods?

The range of computer-generated random numbers is a. [-8, 0). b. [1, 8]. c. [-8, 8]. d. [0, 1).

[0, 1).

Forecast error

__________ is the amount by which the predicted value differs from the observed value of the time series variable.

Validation

__________ is the process of determining that a simulation model provides an accurate representation of a real system.

Infeasibility

__________ is the situation in which no solution to the linear programming problem satisfies all the constraints.

Problem formulation

__________, or modeling, is the process of translating a verbal statement of a problem into a mathematical statement.

when k-NN is used to estimate a continuous outcome

a new observation's outcome value is predicted to be the average of the outcome values of it k-nearest neighbors in the training set

The assumption that is necessary for a linear programming model to be appropriate and that ensures that the value of the objective function and the total resources used can be found by summing the objective function contribution and the resources used for all decision variables is known as a. proportionality. b. divisibility. c. additivity. d. negativity.

additivity.

Overall error rate is an

aggregate measure of misclassification that assumes all errors are equal

A scenario in which the optimal objective function contour line coincides with one of the binding constraint lines on the boundary of the feasible region leads to __________ solutions. a. binding b. infeasible c. unique optimal d. alternative optimal

alternative optimal

Receiving Operating Characteristic (ROC) curve

an alternative graphical approach for displaying the tradeoff between a classifier's ability to correctly identify Class 1 observations and its Class 0 error rate

Logistic Regression

attempts to classify a binary categorical outcome (y = 0 or 1) as a linear function of explanatory variables

The newest model of smart car is supposed to get excellent gas mileage. A thorough study showed that gas mileage (measured in miles per gallon) is normally distributed with a mean of 75 miles per gallon and a standard deviation of 10 miles per gallon. What is the probability that, if driven normally, the car will get 100 miles per gallon or better? a. 25% b. 0.6% c. 2.5% d. 6%

b. 0.6%

Two events are independent if a. the probability of one or both events is greater than 1. b. P(A | B) = P(A) or P(B | A) = P(B). c. the two events occur at the same time. d. None of these choices are correct.

b. P(A | B) = P(A) or P(B | A) = P(B).

A __________ refers to a constraint that can be expressed as an equality at the optimal solution. a. nonnegativity constraint b. first class constraint c. binding constraint d. slack variable

binding constraint

Lines showing the alternatives from decision nodes and the outcomes from chance nodes are called a. payoffs. b. weights. c. diagonals. d. branches.

branches.

the quality of the classifier

by computing the area under the ROC curve (AUC), we can evaluate

An uncertain future event affecting the consequence associated with a decision is known as a a. chance event. b. decision node. c. payoff. d. decision alternative.

chance event.

The states of nature are defined so that they are ___________. This means that at least one state of nature must occur at a given time for a chance event. a. collectively exhaustive b. mutually exclusive c. optimistic outcomes d. certain events

collectively exhaustive

F1 Score

combines precision and sensitivity into a single measure and is defined as

In a __________ distribution, a random variable can take any value in a specified range. a. relative frequency b. cumulative c. discrete probability d. continuous probability

continuous probability

An experiment consists of determining the speed of automobiles on a highway by the use of radar equipment. The random variable in this experiment is a a. discrete random variable. b. categorical random variable. c. continuous random variable. d. complex random variable.

continuous random variable

An input to a simulation model that is selected by the decision maker is known as a a. controllable input. b. probable input. c. random variable. d. nonnegativity constraint.

controllable input

Using the Table below, which is the recommended decision alternative using the conservative approach? Payoff Table Decision Alternative State of Nature 1 State of Nature 2 d1 5 7 d2 -4 1 d3 1 -3 d4 10 2 d5 6 4 a. d2 b. d3 c. d1 d. d5

d3

Using the Table below, which is the recommended decision alternative using the optimistic approach? Payoff Table Decision Alternative State of Nature 1 State of Nature 2 d1 5 7 d2 -4 1 d3 1 -3 d4 10 2 d5 6 4 a. d4 b. d1 c. d5 d. d2

d4

The parameter R in an exponential utility function represents the a. posterior probability. b. decision maker's risk tolerance. c. utility function's error tolerance. d. likely profit/loss from the investment.

decision maker's risk tolerance.

A controllable input for a linear programming model is known as a a. dummy variable. b. constraint. c. parameter. d. decision variable.

decision variable.

A variable that can only take on specific numeric values is called a a. discrete random variable. b. categorical variable. c. continuous random variable. d. complex random variable.

discrete random variable.

The random variables corresponding to the interarrival times of customers and the service times of the servers are commonly part of a(n) __________ simulation. a. what-if b. risk analysis c. discrete-event d. Monte Carlo

discrete-event

In a linear programming model, the __________ assumption plus the nonnegativity constraints mean that decision variables can take on any value greater than or equal to zero. a. divisibility b. additivity c. negativity d. proportionality

divisibility

Bayes' theorem is a method used to compute __________ probabilities. a. empirical b. posterior c. conditional d. prior

empirical

Bayes' theorem a. cannot be used to calculate posterior probabilities. b. enables the use of sample information to revise prior probabilities. c. can be used only for cases where conditional probabilities are unknown. d. is useful for determining optimal decisions without requiring knowledge of probabilities of the states of nature.

enables the use of sample information to revise prior probabilities.

The weighted average of the payoffs for a chance node is known as the a. expected value. b. median value. c. risk measure. d. variance of the node.

expected value.

The points where constraints intersect on the boundary of the feasible region are termed as the a. feasible points. b. feasible edges. c. extreme points. d. objective function contour.

extreme points.

The values for random variables in a Monte Carlo simulation are a. selected manually. b. taken from forecasting analysis. c. derived secondarily using formulas. d. generated randomly from probability distributions.

generated randomly from probability distributions.

The choice of the probability distribution for a random variable can be guided by a. an objective function. b. historical data. c. forecasting. d. likelihood factors.

historical data.

The parameter R in the exponential utility function U(x) = 1 - e-x/R represents the decision maker's risk tolerance. Larger values of R indicate that the decision maker a. is less risk averse (closer to neutral). b. is more risk averse (has less risk tolerance). c. will accept the gamble. d. is not concerned with risk.

is less risk averse (closer to neutral).

k-NN uses the

k most similar observations from the training set, where similarity is typically measured with Euclidean distance

A mathematical function in which each variable appears in a separate term and is raised to the first power is known as a a. linear function. b. power function. c. what-if function. d. nonlinear function.

linear function.

Unsupervised Learning

looks for previously undetected patterns in a data set with no pre-existing labels and with a minimum of human supervision. It allows for modeling of probability densities over inputs. It is typically describing not predicting.

For a maximization problem, the optimistic approach often is referred to as the __________ approach. a. minimin b. minimax c. maximin d. maximax

maximax

If a z-score is zero, then the corresponding x-value must be equal to the a. mode. b. mean. c. standard deviation. d. median.

mean.

mallow's statistic

measure commonly computed by statistical software that can be used to identify models with promising sets of variables

Precision

measure that corresponds to the proportion of observations predicted to be Class 1 by a classifier that are actually in Class 1

Class 1 Error Rate and Class 0 Error Rate

misclassification often results in asymmetric costs

The utility function for money is a curve that depicts the relationship between a. branch probabilities and utility. b. regret and utility. c. monetary value and utility. d. decision alternative and utility.

monetary value and utility.

As we decrease the cutoff value...

more observations will be classified as Class 1, thereby increasing the likelihood that a Class 1 observation will be correctly classified as Class 1 (decreasing the Class 1 error rate)

No more than one state of nature can occur at a given time for a chance event. This indicates that the states of nature are defined such that they are a. collectively exhaustive. b. mutually exclusive. c. conservative events. d. independent outcomes.

mutually exclusive.

accuracy

ne minus the overall error rate is often referred to as the _______ of the model

The minimax regret approach is a. purely optimistic. b. purely conservative. c. both purely optimistic and purely conservative. d. neither purely optimistic nor purely conservative.

neither purely optimistic nor purely conservative

An intersection or junction point of a decision tree is called a(n) a. node. b. intercept. c. branch. d. stem.

node.

Chance nodes are a. nodes provided at the end of the states-of-nature branches. b. nodes indicating points where an uncertain event will occur. c. nodes provided at the end of the decision alternative branches where a payoff is shown. d. nodes indicating points where a decision is made.

nodes indicating points where an uncertain event will occur.

A distribution of a random variable for which values extremely larger or smaller than the mean are increasingly unlikely can possibly be modeled as a(n) _____________ probability distribution. a. binomial b. normal c. gamma d. exponential

normal

The type of distribution shown in the graph below is a(n) __________ distribution. a. exponential b. beta c. normal d. uniform

normal

Probability is the a. number of successes divided by the standard deviation of the distribution. b. number of successes divided by the number of failures. c. numerical measure of the likelihood that an event will occur. d. chance that an event will not happen.

numerical measure of the likelihood that an event will occur.

The term __________ refers to the expression that defines the quantity to be maximized or minimized in a linear programming model. a. problem formulation b. objective function c. decision variable d. association rule

objective function

A(n) __________ refers to a set of points that yield a fixed value of the objective function. a. objective function contour b. infeasible solution c. objective function coefficient d. feasible region

objective function contour

In problem formulation, the a. objective is expressed in terms of the decision variables. b. constraints are expressed in terms of the obtained objective function coefficients. c. optimal solution is decided upon. d. nonnegativity constraints are always ignored.

objective is expressed in terms of the decision variables.

The amount of loss (lower profit or higher cost) from not making the best decision for each state of nature is known as a. risk profile. b. best payoff. c. utility. d. opportunity loss.

opportunity loss.

Geometrically, binding constraints intersect to form the a. zero slack. b. subspace. c. optimal point. d. decision cell.

optimal point.

A measure of the outcome of a decision such as profit, cost, or time is known as a a. payoff. b. branch. c. forecasting index. d. regret.

payoff

An initial estimate of the probabilities of events is a __________ probability. a. empirical b. posterior c. conditional d. prior

prior

A __________ describes the range and relative likelihood of all possible values for a random variable. a. probability mass function of an event b. probability distribution for a random variable c. probability d. density function

probability distribution for a random variable

A description of the range and relative likelihood of possible values of an uncertain variable is known as a a. simulation optimization. b. base-case scenario. c. risk analysis. d. probability distribution.

probability distribution.

In simulation analysis, the ___________ of random variables can be adjusted to determine the impact of the assumptions about the shape of the uncertainty on the results. a. probability distributions b. relative frequencies c. ranges d. manual generations

probability distributions

A joint probability is the a. sum of the probabilities of two events. b. sum of the probabilities of two independent events. c. probability of the intersection of two events. d. probability of the union of two events.

probability of the intersection of two events.

In linear programming models of real problems, the occurrence of an unbounded solution means that the a. problem formulation is improper. b. mathematical models sufficiently represent the real-world problems. c. constraints have been excessively used in modeling. d. resultant values of the decision variables have no bounds.

problem formulation is improper.

A(n) __________ is an input to a simulation model whose value is uncertain and described by a probability distribution. a. random variable b. constraint c. decision variable d. identifier

random variable

A simulation model extends spreadsheet modeling by a. using historical data to make predictions about future values and expected trends. b. extending the range of parameters for which solutions are computed. c. using real-time values for parameters from the application to formulate solutions. d. replacing the use of single values for parameters with a range of possible values.

replacing the use of single values for parameters with a range of possible values.

Constraints are a. quantities to be minimized in a linear programming model. b. restrictions that limit the settings of the decision variables. c. quantities to be maximized in a linear programming model. d. input variables that can be controlled during optimization.

restrictions that limit the settings of the decision variables.

The process of evaluating a decision in the face of uncertainty by quantifying the likelihood and magnitude of an undesirable outcome is known as a. decision tree analysis. b. regression analysis. c. risk analysis. d. data mining.

risk analysis.

A __________ is a decision maker who would choose a guaranteed payoff over a lottery with a better expected payoff. a. risk taker b. risk-creator c. risk avoider d. risk-neutral

risk avoider

Exponential utility functions assume that the decision maker is a. a risk taker. b. a risk monitor. c. risk neutral. d. risk averse.

risk neutral.

New information obtained through research or experimentation that enables an updating or revision of the state-of-nature probabilities is known as a. sample information. b. conditional probability. c. expected utility. d. joint probability.

sample information

The study of how changes in the input parameters of a linear programming problem affect the optimal solution is known as a. regression analysis. b. optimality analysis. c. model analysis. d. sensitivity analysis.

sensitivity analysis.

The study of how changes in the probability assessments for the states of nature or changes in the payoffs affect the recommended decision alternative is known as a. sensitivity analysis. b. probability analysis. c. uncertainty analysis. d. cost analysis.

sensitivity analysis.

The reduced cost for a decision variable that appears in a Sensitivity Report refers to the __________ of the nonnegativity constraint for that variable. a. range of feasibility b. range of optimality c. shadow price d. slack value

shadow price

The change in the optimal objective function value per unit increase in the right-hand side of a constraint is given by the a. allowable increase. b. objective function coefficient. c. restrictive cost. d. shadow price.

shadow price.

The triangular distribution is a good model for __________ distributions. a. poisson b. uniform c. normal d. skewed

skewed

The __________ value for each less-than-or-equal-to constraint indicates the difference between the left-hand and right-hand values for a constraint. a. slack b. unbounded c. surplus d. objective function coefficient

slack

A variable subtracted from the left-hand side of a greater-than-or-equal to constraint to convert the constraint into an equality is known as a(n) a. unbounded variable. b. binding constraint. c. surplus variable. d. slack variable.

surplus variable.

Visually, the taller the bar in a decile-wise lift chart...

the better the classifier is at identifying responders in the respective decile group

Sample space is a. the collection of events b. a process that results in some outcome. c. a subgroup of a population/the likelihood of an outcome. d. the collection of all possible outcomes.

the collection of all possible outcomes.

All the events in the sample space that are not part of the specified event are called a. independent events. b. joint events. c. simple events. d. the complement of the event.

the complement of the event.

In a base-case scenario, the output is determined by assuming a. worst values that can be expected for the random variables of a model. b. best values that can be expected for the random variables of a model. c. the most likely values for the random variables of a model. d. the mean trial values for the random variables of a model.

the most likely values for the random variables of a model.

Nonnegativity constraints ensure that a. the problem modeling includes only nonnegative values in the constraints. b. the objective function of the problem always returns maximum quantities. c. there are no inequalities in the constraints. d. the solution to the problem will contain only nonnegative values for the decision variables.

the solution to the problem will contain only nonnegative values for the decision variables.

When formulating a constraint, care must be taken to ensure that a. there are no inequalities in the mathematical expression. b. the decision variables are set at either maximum or minimum values. c. all the objective function coefficients are included. d. the units of measurement on both sides of the constraint match.

the units of measurement on both sides of the constraint match.

if k = 1

then the classification of a new observation is set to be equal to the class of the single most similar observation from the training set

if k = n

then the new observation's class is naïvely assigned to the most common class in the training set

A disadvantage of the simple what-if analyses is that a. there is no indication of the likelihood of various output values. b. the optimal solutions are not guaranteed. c. there are errors induced as a result of rounding. d. it cannot compute alternate optimal solutions.

there is no indication of the likelihood of various output values.

All of the following are examples of discrete random variables except a. marital status. b. time. c. number of tickets sold. d. population of a city.

time.

Problems with infeasible solutions arise in practice because a. of errors in objective function formulation. b. too many restrictions have been placed on the problem. c. management doesn't specify enough restrictions. d. there are too few decision variables.

too many restrictions have been placed on the problem.

A set of values for the random variables is called a(n) a. event. b. permutation. c. trial. d. combination.

trial.

All the values of computer-generated random numbers are a. uniformly distributed. b. lognormally distributed. c. Poisson distributed. d. normally distributed.

uniformly distributed.

The event containing the outcomes belonging to A or B or both is the __________ of A and B. a. intersection b. union c. Venn diagram d. complement

union

The process of determining that a computer program implements a simulation model as it is intended is known as a. verification. b. correlation. c. optimization. d. validation.

verification.

A __________ analysis involves considering alternative values for the random variables and computing the resulting value for the output. a. random b. risk c. what-if d. cluster

what-if

The shadow price of nonbinding constraints a. will always be a positive value. b. can never be equal to zero. c. is no longer valid if the right-hand side of the constraint remains the same. d. will always be zero.

will always be zero.

The slack value for binding constraints is a. zero. b. a negative integer. c. always a positive integer. d. equal to the sum of the optimal points in the solution.

zero.