23. Quiz: Shape and Outliers (Comparing Distributions)

Image Summary

In the below image, we have three box-plots. Each box-plot is for a different Iris flower: setosa, versicolor, or virginica. On the y-axis, we are given the sepal length. Notice that virginica has an outlier towards the bottom of the plot. Therefore, the minimum is not given by the bottom line here; rather, it is provided by this point.

Quick Refresher: The measures of center and spread we can determine from a Box Plot are as follows. Let's use Setosa for these examples.

Median is the center line inside the box and is 5

IQR is space between the first and third quartile which are the edges of the box. They are about 4.8 for the first quartile and 5.2 for the third

QUIZ QUESTION::

Match the appropriate Iris type to the statement(s) that are true for its Sepal Length.

ANSWER CHOICES:



Sepal Length

Iris Type

The largest Range

The smallest Interquartile Range

Median is approximately 5

Third quartile is approximately 6.3

Approximately Symmetric

The largest sepals on average.

SOLUTION:

Sepal Length

Iris Type

The largest Range

The largest sepals on average.

Third quartile is approximately 6.3

The smallest Interquartile Range

Median is approximately 5

The smallest Interquartile Range

Median is approximately 5

The largest Range

The largest sepals on average.

Approximately Symmetric

Box Plot

Using the same flower data, select all of the below statements that MUST be true.

SOLUTION:
  • More than 75% of the virginica flowers have a larger sepal length than the largest setosa flower.
  • More than 50% of setosa flowers have larger sepal length than the shortest versicolor flower.