Scatter Plots: Outliers and Clusters

Scatter Plots: Outliers and Clusters

What is an outlier?

• An outlier is a point on the graph that is outside of the range of data

• You can think of it in terms of kids. The teacher gives everyone in class bonus points and cookies and everyone is happy except for one or two students. Those students would be the outlier(s)

Outlier #1

Notice how the point at (30, 6000) is an outlier and does not fit with the data

Not an Outlier

This is NOT an Outlier because it falls on the TREND LINE or Line of BEST FIT.

Note: the line of best fit is a line that goes through the middle of the points

How to label and outlier

• An outlier should be labeled using its points for example (3,4)

Multiple Select

Which points would be considered outliers? Check all that apply.

• (3, 9)

• (4,4)

• (6,5)

• (7,1)

• (11, 2)

Multiple Select

What data points are outliers in the scatter plot?

• A

• B

• C

• D

Multiple Choice

Is there an outlier in this data set?

• Yes

• No

Multiple Choice

Which point is the outlier?

Multiple Choice

Is the point in red an outlier?

• Yes

• No

CLUSTERS

• A Cluster is data that is group or packed tightly together

• Think of a huddle in a football game or a group of friends near one locker

• Clusters should be identified by their domain and range or x and y values

• Notice the clusters at certain ages

Multiple Choice

Which scatter plot shows obvious clusters?

Multiple Choice

In a scatterplot, an outlier...

• ...is something we didn't learn 8th grade
• ...is a puppet with a long nose named Pinocchio
• ...is a point that is far outside the main cluster of points/ordered pairs
• ...is a really naughty point who doesn't tell the truth when outside

Multiple Select

Which scatterplots have clusters? Check all that apply.

Multiple Choice

Which best describes the data in the table?

• There are no outliers, but there is a cluster

• There is a cluster and outliers

• There are no clusters or outliers

• There are no clusters, but there are outliers

Multiple Choice

This graph has...

• a gap

• an outlier

• a cluster

• a nonlinear association

Linear Association vs Non-Linear

• Linear - The data shows a line or forms a line

• Non-Linear - the data does not form a line

Multiple Choice

About how many male math teachers were there in 2006?

• 15
• 30
• 35
• 45

Multiple Choice

What type of association does this scatter plot represent?

• positive linear association
• negative linear association
• no association
• nonlinear association

Multiple Choice

What type of association does this scatter plot show?

• positive linear association
• negative linear association
• no association
• nonlinear association

Multiple Choice

What type of association does this scatter plot represent?

• positive linear association
• negative association
• no association
• nonlinear association

Multiple Choice

If a scatterplot has no association then...

• ...it has no ordered pairs
• ...it has ordered pairs that have a negative pattern
• ...its ordered pairs have no predictable pattern
• ...if it makes a lion on a graph (roar!)

Multiple Choice

As the age of the car increases, its value decreases. Which scatterplot represents this relationship?

• A
• B
• C
• D

Multiple Choice

What is the correlation?

• Negative correlation
• No correlation
• Positive correlation
• All of the above

Multiple Choice

Which scatter plot shows a linear relationship between x and y?

• Graph A
• Graph B
• Graph C
• Graph D

Multiple Choice

What type of correlation does graph C have?

• Positive Linear

• Negative Linear

• Non-Linear

• No Correlation

Multiple Choice

What type of correlation does this graph have?

• Negative

• no association

• positive

Multiple Choice

What type of correlation does this graph have?

• Negative

• no association

• positive

A GAP

• A Gap is when data fits the trend line or line of best fit but has a gap of time or data in between

• Notice the Gap in the graph

Multiple Choice

Which game did 500 people attend?

• Game 1

• Game 2

• Game 3

• Game 4

Multiple Choice

Did more people attend game 2 or game 3?

• Game 2

• Game 3

• It's not possible to tell.

Multiple Choice

Identify any clusters.

• Cluster at x = 14

• Cluster at x = 18

• Cluster at x = 24

• There aren't any noteworthy clusters in this graph.

Multiple Choice

Identify any gaps.

• gap between x = 10 and x = 15

• gap between x = 35 and x = 40

• gap between x = 15 and x = 25

• There aren't any significant gaps in this graph.

Multiple Choice

Identify any outliers.

• Outlier at x = 10

• Outlier at x = 15

• Outlier at x = 30

• There aren't any outliers in this graph.

Multiple Choice

Identify any outliers, gaps, or clusters.

• There are no outliers, gaps, or clusters

• Outlier at x = 12, no gaps, cluster at x = 24

• No outliers, gap between x = 3 and x = 12, cluster at x = 18

• There are no outliers, no gaps, cluster at x = 9

Multiple Choice

Identify any gaps.

• gap between x = 6 and x = 9

• gap between x = 18 and x = 21

• gap between x = 0 and x = 3

• There aren't any significant gaps in this graph.

Multiple Choice

Describe the relationship between the data.

• Positive Linear

• Negative Linear

• Non-Linear

• No Relationship

Multiple Choice

Describe the relationship between the data.

• Positive Linear

• Negative Linear

• Non-Linear

• No Relationship