Data Science 1.02 Choosing Visualizations based on your Data

Which image best portrays your current mood?

• 
• 
• 
• 
• 

Organize these options into the right categories

Groups:

(a) Structured Data

,

(b) Unstructured Data

,

(c) Semi-Structured Data

• Tabular Data (like spreadsheets)

• Data that does not have a predefined or organized data model

• Easiest to Analyze

• Data that contains mixed data types

• Often found in Survey results

• Most Useful to Business

Organize these options into the right categories

Groups:

(a) Qualitative

,

(b) Quantitative

• Categorical Data

• Numerical Data

• Ex: Age, Height, Number of Contacts

• Ex: Color, Flavor, Marital Status

Answer explanation

Think of "Quantity" to remember that Quantitative data is Numerical data. Quantity means how many?

Organize these options into the right categories

Groups:

(a) Discrete Data

,

(b) Continuous Data

• Typically fractions or decimals

• Exact figures you can count

• Example: Number of players on a baseball team

• Typically integers or whole numbers

• Measurable values over a range

• Example: Heights of players on a baseball team

Discrete or Continuous?

• Discrete

• Continuous

Answer explanation

While a curve has been drawn in to show the trend of the data, the actual table is providing a COUNT of baseball hitters that are "300 Hitters." The graph type is a scatterplot with a curve of best fit drawn in.

Discrete or Continuous?

• Discrete

• Continuous

Answer explanation

The graph type is a scatterplot with a line of best fit drawn in. The data itself is not a count, but a range of values for the BMI and the Weight. These will be decimal values and so this represents continuous data.

What chart type best identifies relationships between two numerical attributes within a data set?

• Pie Chart

• Scatter Plot

• Histogram

• Box Plot

• Bar Chart

Answer explanation

Scatterplots have strength in quickly showing correlations between two attributes.

Which of the following graphs would be most helpful in answering the following question?

"In the sample of 100 individuals, how satisfied were people in general?"

• 
• 
• 

Answer explanation

In this visualization, it shows the counts for each satisfaction rating. Therefore, it could provide more insight than the other two visualizations on how satisfied people were in general.

Which of the following questions cannot be answered by this visualization?

• What is the mean BMI?

• How many people are in the Sample?

• What is the relationship between BMI and weight?

• How many people have a BMI above 50?

Answer explanation

A scatterplot would be able to help answer the question "What is the relationship between BMI and weight?" You can see by the plot that as weight increases, so does the BMI, so there is a strong correlation/relationship here.

Tags

CCSS.8.SP.A.1

What type of data would be used with a bar chart or a pie chart?

• Categorical

• Quantitative

Answer explanation

Categorical data can be easily grouped which is best represented in a pie chart or a bar chart.