Deck 17: Business Analytics

Question 1

True or False: In real-world business analytics, filtering is typically performed on large data based
on complex conditional relationships.

Answer 1

True

Question 2

True or False: Some consider bullet graphs little more than examples of chartjunk, even as many
decision makers request them due to their visual appeal, due to the amount of the space they
consumes.

Answer 2

False

Question 3

Which of the following disciplines is typically NOT involved in business analytics?

A) Economics
B) Statistics
C) Information system
D) Management science

Answer 3

A

Question 4

True or False: Some business analytics involve starting with many variables, followed by filtering
the data by exploring specific combinations of categorical values or numerical range.In Excel, this
approach is mimicked by using gauges.

Question 5

True or False: Some business analytics involve starting with many variables, followed by filtering
the data by exploring specific combinations of categorical values or numerical range.In Excel, this
approach is mimicked by using a slicer.

Question 6

True or False: Bullet graphs that use color to represent the value of a second variable, thereby
increasing the data density of the displays, is an example of chartjunk.

Question 7

True or False: Some business analytics involve starting with many variables, followed by filtering
the data by exploring specific combinations of categorical values or numerical range.In Excel, this
approach is mimicked by using a drill-down.

Question 8

True or False: Treemaps that use color to represent the value of a second variable, thereby
increasing the data density of the displays, is an example of chartjunk.

Question 9

Which of the following finds relationships in data that may not be readily apparent?

A) Predictive analytics
B) Prescriptive analytics
C) Productive analytics
D) Descriptive analytics

Question 10

True or False: Most information design specialists prefer bullet graphs over gauges because bullet
graphs foster the direct comparison of each measurement.

Question 11

Dashboards may contain all but which of the following?

A) Treemaps
B) Gauges
C) Contingency table
D) Bullet graphs

Question 12

True or False: Some consider gauges little more than examples of chartjunk, even as many decision
makers request them due to their visual appeal, due to the amount of the space it consumes.

Question 13

True or False: Double-clicking a cell in a PivotTable causes Excel to drill down and display the
underlying data in a new worksheet.

Question 14

Which of the following is NOT among the three broad categories of analytic methods?

A) Predictive analytics
B) Prescriptive analytics
C) Productive analytics
D) Descriptive analytics

Question 15

Which of the following investigates what should occur and suggest the best course of action
For the future?

A) Predictive analytics
B) Prescriptive analytics
C) Productive analytics
D) Descriptive analytics

Question 16

Dashboards may contain all but which of the following?

A) Contingency table
B) Sparklines
C) Gauges
D) Bullet graphs

Question 17

True or False: Some business analytics involve starting with many variables, followed by filtering
the data by exploring specific combinations of categorical values or numerical range.

Question 18

Which of the following explores business activities that have occurred or are occurring in the
Present moment?

A) Predictive analytics
B) Prescriptive analytics
C) Productive analytics
D) Descriptive analytics

Question 19

True or False: Some business analytics are performed by adding variables to see if unforeseen
relationships are uncovered.

Question 20

True or False: You can compute any of the numerical descriptive statistics for the variables of the
new worksheet that a drill-down in a PivotTable creates.

Question 21

SCENARIO 17-2
The treemap below shows the amounts (size)measured in billions of US dollars and percentage
changes from prior year (color)of business-to-consumer ecommerce sales last year for North
America, Asia Pacific, Western Europe, Central & Eastern Europe, Latin America, and Middle East
& Africa.
True or False: Referring to Scenario 17-2, the Asia Pacific region has the largest amount of
business-to-consumer ecommerce sales last year.

Question 22

Which of the following is NOT among the predictive analytics methods covered in the book?

A) Principle component analysis
B) Neural networks
C) Cluster analysis
D) Multidimensional scaling

Question 23

SCENARIO 17-1
Referring to Scenario 17-1, the pattern of the rates of return of stock ____ and stock ____ are similar.

Question 24

SCENARIO 17-2
The treemap below shows the amounts (size)measured in billions of US dollars and percentage
changes from prior year (color)of business-to-consumer ecommerce sales last year for North
America, Asia Pacific, Western Europe, Central & Eastern Europe, Latin America, and Middle East
& Africa.
Referring to Scenario 17-2, which region has the slowest growth in business-to-consumer
ecommerce sales last year?

Question 25

SCENARIO 17-1
True or False: Referring to Scenario 17-1, the sparklines enable you to predict that the rates of
return of the stock market in 2014 will be higher than in 2013.

Question 26

True or False: There is no significant difference between filtering performed in a complex real-
world business analytic and filtering performed using the slicers in a PivotTable in Excel.

Question 27

SCENARIO 17-2
The treemap below shows the amounts (size)measured in billions of US dollars and percentage
changes from prior year (color)of business-to-consumer ecommerce sales last year for North
America, Asia Pacific, Western Europe, Central & Eastern Europe, Latin America, and Middle East
& Africa.
True or False: Referring to Scenario 17-2, the Western Europe region has the largest amount of
business-to-consumer ecommerce sales last year.

Question 28

SCENARIO 17-1
True or False: Referring to Scenario 17-1, the sparklines enable you to draw conclusions on the
historical trend of the rates of return of the three stocks.

Question 29

Which of the following is NOT one of the categories of predictive analytics methods?

A) Classification
B) Clustering
C) Association
D) Description

Question 30

SCENARIO 17-2
The treemap below shows the amounts (size)measured in billions of US dollars and percentage
changes from prior year (color)of business-to-consumer ecommerce sales last year for North
America, Asia Pacific, Western Europe, Central & Eastern Europe, Latin America, and Middle East
& Africa.
Referring to Scenario 17-2, which region has the largest amount of business-to-consumer
ecommerce sales last year?

Question 31

Which of the following is NOT among the predictive analytics methods covered in the book?

A) Neural networks
B) Cluster analysis
C) Factor analysis
D) Multidimensional scaling

Question 32

SCENARIO 17-2
The treemap below shows the amounts (size)measured in billions of US dollars and percentage
changes from prior year (color)of business-to-consumer ecommerce sales last year for North
America, Asia Pacific, Western Europe, Central & Eastern Europe, Latin America, and Middle East
& Africa.
True or False: Referring to Scenario 17-2, the Middle East & Africa region has the slowest
growth in business-to-consumer ecommerce sales last year.

Question 33

Which of the following is NOT one of the categories of predictive analytics methods?

A) Clustering
B) Recommendation
C) Association
D) Prediction

Question 34

SCENARIO 17-2
The treemap below shows the amounts (size)measured in billions of US dollars and percentage
changes from prior year (color)of business-to-consumer ecommerce sales last year for North
America, Asia Pacific, Western Europe, Central & Eastern Europe, Latin America, and Middle East
& Africa.
True or False: Referring to Scenario 17-2, the North America region has the fastest growth in
business-to-consumer ecommerce sales last year.

Question 35

Which of the following is NOT among the predictive analytics methods covered in the book?

A) Neural networks
B) Simple component analysis
C) Cluster analysis
D) Multidimensional scaling

Question 36

SCENARIO 17-1
Referring to Scenario 17-1, the rates of return of stock ____ have the smallest variation among the
Three.

Question 37

SCENARIO 17-1
True or False: Referring to Scenario 17-1, the sparklines enable you to conclude that the rates of
return of the stock market in general is volatile from 2007 to 2013.

Question 38

SCENARIO 17-2
The treemap below shows the amounts (size)measured in billions of US dollars and percentage
changes from prior year (color)of business-to-consumer ecommerce sales last year for North
America, Asia Pacific, Western Europe, Central & Eastern Europe, Latin America, and Middle East
& Africa.
Referring to Scenario 17-2, which region has the fastest growth in business-to-consumer
ecommerce sales last year?

Question 39

SCENARIO 17-1
True or False: Referring to Scenario 17-1, the sparklines enable you to predict that the rates of
return of the stock market in 2014 will be about the same as in 2013.

Question 40

SCENARIO 17-2
The treemap below shows the amounts (size)measured in billions of US dollars and percentage
changes from prior year (color)of business-to-consumer ecommerce sales last year for North
America, Asia Pacific, Western Europe, Central & Eastern Europe, Latin America, and Middle East
& Africa.
Referring to Scenario 17-2, which region has the smallest amount of business-to-consumer
ecommerce sales last year?

Question 41

True or False: Successful use of a regression tree requires a precise description of the
parameters of the tree.

Question 42

True or False: Data mining is used mostly in the mining industry.

Question 43

True or False: The LogWorth statistic is used to decide when to split a node of a regression
tree.

Question 44

True or False: The result of the regression tree is affected by the distribution of the
independent variables.

Question 45

True or False: The Akaike information criteria (AIC)or the corrected Akaike information
criteria (AICc)can be used to compare alternative models chosen by the classification tree.

Question 46

True or False: Successful implementation of a classification tree requires rules for splitting the
data at each node based on a dependent variable.

Question 47

SCENARIO 17-3
The tree diagram below shows the results of the classification tree model that has been constructed to
predict the probability of a cable company's customers who will switch ("Yes" or "No")into its
bundled program offering based on the price ($30, $40, $50, $60)and whether the customer spends
more than 5 hours a day watching TV ("Yes" or "No")using the data set of 100 customers collected
from a survey.
True or False: Referring to Scenario 17-3, the highest probability of switching is predicted to
occur among customers who watch more than 5 hours of TV a day and are offered the bundled
price of between $30 and $40.

Question 48

True or False: Data mining uses various techniques to extract useful information from huge
depositories of data.

Question 49

True or False: The G 2 statistic is a measure of the probability that can be attributed to the
response that has occurred.

Question 50

True or False: The Akaike information criteria (AIC)or the corrected Akaike information
criteria (AICc)is a measure of the probability that can be attributed to the response that has
occurred.

Question 51

True or False: In a regression tree, the dependent variable is a categorical variable.

Question 52

True or False: Classification tree is not sensitive to the distribution of the independent
variables.

Question 53

True or False: The LogWorth statistic is a measure of the probability that can be attributed to
the response that has occurred.

Question 54

SCENARIO 17-3
The tree diagram below shows the results of the classification tree model that has been constructed to
predict the probability of a cable company's customers who will switch ("Yes" or "No")into its
bundled program offering based on the price ($30, $40, $50, $60)and whether the customer spends
more than 5 hours a day watching TV ("Yes" or "No")using the data set of 100 customers collected
from a survey.
True or False: Referring to Scenario 17-3, the highest probability of switching is predicted to
occur among customers who watch more than 5 hours of TV a day and are offered the bundled
price of higher than $50.

Question 55

True or False: Successful implementation of a regression tree requires rules for deciding when
a branch of the tree cannot be split any more.

Question 56

True or False: In a classification tree, the dependent variable is a categorical variable.

Question 57

True or False: Splitting is always followed by pruning in a classification tree.

Question 58

True or False: Successful implementation of a classification tree requires rules for splitting the
data at each node based on an independent variable.

Question 59

True or False: Successful implementation of a regression tree requires a method to provide
prediction for the target variable at each of the nodes.

Question 60

True or False: Splitting of a node might be followed by pruning if necessary in a classification
tree.

Question 61

True or False: Neural networks can suffer from poor quality of data, insufficient data, or
overfitted models.

Question 62

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
True or False: Referring to Scenario 17-4, the first split occurs at 25 TV appearances a day of
the advertisement.

Question 63

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
Referring to Scenario 17-4, how many cities were used in generating the regression tree?

Question 64

SCENARIO 17-3
The tree diagram below shows the results of the classification tree model that has been constructed to
predict the probability of a cable company's customers who will switch ("Yes" or "No")into its
bundled program offering based on the price ($30, $40, $50, $60)and whether the customer spends
more than 5 hours a day watching TV ("Yes" or "No")using the data set of 100 customers collected
from a survey.
True or False: Referring to Scenario 17-3, the highest probability of switching is predicted to
occur among customers who watch more than 5 hours of TV a day and are offered the bundled
price of lower than $50.

Question 65

SCENARIO 17-3
The tree diagram below shows the results of the classification tree model that has been constructed to
predict the probability of a cable company's customers who will switch ("Yes" or "No")into its
bundled program offering based on the price ($30, $40, $50, $60)and whether the customer spends
more than 5 hours a day watching TV ("Yes" or "No")using the data set of 100 customers collected
from a survey.
True or False: Referring to Scenario 17-3, the highest probability of switching is predicted to
occur among customers who do not watch more than 5 hours of TV a day and are offered the
bundled price of higher than $50.

Question 66

SCENARIO 17-3
The tree diagram below shows the results of the classification tree model that has been constructed to
predict the probability of a cable company's customers who will switch ("Yes" or "No")into its
bundled program offering based on the price ($30, $40, $50, $60)and whether the customer spends
more than 5 hours a day watching TV ("Yes" or "No")using the data set of 100 customers collected
from a survey.
True or False: Referring to Scenario 17-3, the highest probability of switching is predicted to
occur among customers who do not watch more than 5 hours of TV a day and are offered the
bundled price of lower than $50.

Question 67

True or False: Neural networks use the validating data to uncover a model and then the training
data to see if the model can make the correct prediction or classification.

Question 68

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
Referring to Scenario 17-4, what percentage of the variation in weekend box office revenue
can be explained by the amount spent on TV advertising and the number of times a day the
advertisement appear on TV?

Question 69

True or False: Neural networks does not make any a priori assumption about the distribution of
the data and, hence, are nonparametric methods.

Question 70

True or False: Neural networks require only training data but not validating data.

Question 71

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
True or False: Referring to Scenario 17-4, the highest mean weekend box office revenue is
predicted to occur with $30 thousand spent on TV advertisement and 30 advertisement
appearances a day.

Question 72

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
True or False: Referring to Scenario 17-4, the highest mean weekend box office revenue is
predicted to occur with at least $45 thousand spent on TV advertisement and at least 25
advertisement appearances a day.

Question 73

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
True or False: Referring to Scenario 17-4, the first split occurs at $45 thousand spent on TV
advertising.

Question 74

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
True or False: Referring to Scenario 17-4, the highest mean weekend box office revenue is
predicted to occur with $55 thousands spent on TV advertisement and 35 advertisement
appearances a day.

Question 75

True or False: The forward-and-backward computation among the three layers of a multilayer
perceptron is repeated until the output layer detects that the difference between the predicted
results and the target values has been minimized or is at an acceptable level.

Question 76

SCENARIO 17-3
The tree diagram below shows the results of the classification tree model that has been constructed to
predict the probability of a cable company's customers who will switch ("Yes" or "No")into its
bundled program offering based on the price ($30, $40, $50, $60)and whether the customer spends
more than 5 hours a day watching TV ("Yes" or "No")using the data set of 100 customers collected
from a survey.
True or False: Referring to Scenario 17-3, the highest probability of switching is predicted to
occur among customers who watch more than 5 hours of TV a day and are offered the bundled
price of higher than $40.

Question 77

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
True or False: Referring to Scenario 17-4, the highest mean weekend box office revenue is
predicted to occur with $55 thousand spent on TV advertisement and at least 25 advertisement
appearances a day.

Question 78

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
True or False: Referring to Scenario 17-4, the highest mean weekend box office revenue is
predicted to occur with less than $45 thousand spent on TV advertisement and fewer than 25
advertisement appearances a day.

Question 79

True or False: Multilayer perceptrons usually contain an input layer, a hidden layer and an
output layer.

Question 80

SCENARIO 17-4
The regression tree below was obtained for predicting the weekend box office revenue of a newly
released movie (in thousands of dollars)based on data collected in different cities on the expenditure
(at $25, $30, $35, $40, $45, $50, $55, $60, $65 or $70 thousand)spent on TV advertising and the
number of times (10, 15, 20, 25, 30 or 35)a day the advertisement appear on TV.
Business Analytics 17-15
True or False: Referring to Scenario 17-4, the highest mean weekend box office revenue is
predicted to occur with at least $45 thousand spent on TV advertisement and fewer than 25
advertisement appearances a day.