107k views
4 votes
When analyzing a scatterplot with a cluster, why should outliers generally be excluded when interpreting the relationship of the variables?

2 Answers

6 votes

Answer:

Outliers are often extreme values that are not as representative of the data set as the other points in the cluster. If the outliers are included, a description of the data set might be misrepresented.

Explanation:

I don't know if this is late sorry if it is, and hope this helps :D

User StilgarBF
by
6.0k points
4 votes

Answer:

Outliers are often extreme values that are not as representative of the data set as the other points in the cluster. If the outliers are included, a description of the data set might be misrepresented.

User Jucajl
by
6.8k points