F.4. Data Visualization

Question 1

What is data visualization or data discovery?

Answer 1

It is the visual representation of information, used for better understanding data and predictions from data.

Question 2

What is data discovery analysis?

Answer 2

The process by which businesses collect data from various sources and analyze it by detecting patterns and trends within datasets and outliers in the data using advanced analytics and visual analysis of the data.

Question 3

What are the two uses for data visualization?

Answer 3

• Data mining process
• To communicate information to users of data

Question 4

In which steps of the data mining process is visualization primarily used?

Answer 4

In the exploration and cleansing of the data in the preprocessing step and in the data dimension reduction step of the process.

• In data exploration - helps determine which variables to include in the analysis
• In data cleansing - helps find erroneous and missing values, duplicate records, and so forth
• In data reduction - helps determine which categories can be combined

Question 5

What are some benefits of data visualization?

Answer 5

• Makes data more understandable
• Promotes quick assimilation of large amounts of data
• Helps to identify correlations by illustrating relationships between data items and events
• Facilitates faster decision-making
• Communicates business insights
• Useful in data mining
• Enables identification of trends and better interpretation of data
• Helps in recognizing patterns

Question 6

What are some limitations of data visualization?

Answer 6

• May lead to speculative conclusions when used to make projections and estimates
• Meaningful data may be excluded, leading to biased results
• Information presented may be oversimplified
• Users may rely too much on visuals and miss important insights
• Potential for misrepresentation or distortion of data through choices made in the way it is presented

Question 7

What are characteristics of a well-designed dashboard?

Answer 7

• All required information is available on a single screen
• Uses visual components such as charts to highlight information
• Easy to use with minimal training
• Allows for further exploration
• Draws data from multiple systems and combines them into a summarized view
• Does not perform complex calculations
• Provides ability to drill down to underlying data
• Information is refreshed in a timely manner
• Provides benchmarks for comparison of key performance indicators

Question 8

What are some best practices for table and chart design to avoid distortion?

Answer 8

• Don’t omit important data
• For a time series, ensure sequential and consistent dates on the x-axis
• Use appropriate scale on the y-axis
• Begin y-axis scale with zero when practical
• Use consistent increments on the y-axis
• Ensure pie chart percentages sum to 100%
• Keep pie chart items to a minimum
• Indicate sampling error with confidence intervals when appropriate
• Provide comparison to external benchmarks when available
• Use the right chart for the job
• Consider whether a table might work better than a chart or graph

Question 9

What should be considered when using color in charts and graphs?

Answer 9

• Use color meaningfully, not just for decoration
• Consider needs of viewers with visual disabilities:
  
  • Ensure colors have sufficient contrast
  • Avoid using red and green together

Question 10

What is a scatterplot used for?

Answer 10

It is used to show all the values for a dataset, typically when there are two variables, and illustrate the relationship between the variables.

Question 11

What does a scatterplot reveal about variables?

Answer 11

A correlation or a lack of correlation between variables.

Question 12

What is a dot plot used for?

Answer 12

It is used to visualize summarized data points for each category on the x-axis.

Question 13

What are the measures of central tendency?

Answer 13

• Mean
• Median
• Mode

A measure of central tendency is a value that represents the center point of a set of data.

Question 14

Define:

Dispersion in a dataset

Answer 14

It describes how much individual values in a set of data are scattered or spread out about their center.

Question 15

What is the purpose of a bar chart?

Answer 15

It is useful for comparing a statistic across groups.

Question 16

What is a pie chart primarily used for?

Answer 16

It is primarily used for showing proportions.

Question 17

What is a line chart used to depict?

Answer 17

• Can be used to visualize several observations for each category, using one line for each series of observations.
• Can also depict change over time, such as in a time series.

Question 18

What additional dimension does a bubble chart add compared to a scatterplot?

Answer 18

A bubble chart replaces data points with bubbles that vary in size according to the size of the values they depict, thus adding the relative sizes of the values plotted as an additional dimension to the chart.

Question 19

What does a histogram show?

Answer 19

The frequencies of a variable using a series of vertical bars.

Question 20

What is the difference between a histogram and a bar graph?

Answer 20

A bar graph relates two variables to one another, whereas a histogram communicates only one variable, and a histogram is used to depict the frequency distribution of that variable.

Question 21

What does a box plot display?

Answer 21

The full distribution of a variable, including the minimum, maximum, mean, median, quartiles, and outliers.

Question 22

What is an outlier in a dataset?

Answer 22

Outliers are values that are far away from most of the other values in the dataset.

Question 23

How is the interquartile range (IQR) of a dataset calculated?

Answer 23

Third quartile (Q3) minus the first quartile (Q1).

IQR = Q3 − Q1

Question 24

How is an outlier determined in a dataset?

Answer 24

An outlier is any value that is either:

• Less than Q1 − (1.5 × IQR) or
• Greater than Q3 + (1.5 × IQR)

Q1 and Q3 are the first and third quartiles, respectively, and IQR is the interquartile range calculated as Q3 − Q1.

Question 25

What is the interquartile range (IQR) of a dataset if the first quartile (Q1) is 17.5 and the third quartile (Q3) is 29?

Answer 25

11.5 ## Footnote The interquartile range is calculated as Q3 − Q1, which in this case is 29 − 17.5.

Question 26

# Fill in the blank: For a dataset where the first quartile (Q1) is 17.5 and the third quartile (Q3) is 29, an outlier on the high end of the dataset would be any value greater than \_\_\_\_\_\_\_\_.

Answer 26

46.25 ## Footnote The interquartile range is 29 − 17.5, which equals 11.5. An outlier on the high end of the dataset would be any value greater than (29 + [1.5 × 11.5]), which equals **46.25**.