Relationships between continuous variables

Exploratory Data Analysis in Power BI

Maarten Van den Broeck

Content Developer at DataCamp

What are scatter plots?

A scatter plot with "Total Bill" on the x-axis and "Tip" on the y-axis.

What are scatter plots?

A scatter plot with "Total Bill" on the x-axis and "Tip" on the y-axis. Two red rectangles are highlighting the x- and y- axis.

What are scatter plots?

A scatter plot with "Total Bill" on the x-axis and "Tip" on the y-axis. A red rectangle is highlighting the chart area and data points.

Interpreting a scatter plot

A scatter plot with "Total Bill" on the x-axis and "Tip" on the y-axis. The dots representing each observation are tightly clustered towards the origin and disperse more for higher values of "Total Bill" and "Tip".

Interpreting a scatter plot

A scatter plot with "Total Bill" on the x-axis and "Tip" on the y-axis. A red line dissects through the cluster of data points to show a general increasing trend.

Interpreting a scatter plot

Strong-positive

A scatter plot with a red line showing a positive, increasing relationship. A red circle highlights the data points and shows they are tightly clustered together.

Strong-negative

A scatter plot with a red line showing a negative, decreasing relationship. A red circle highlights the data points and shows they are tightly clustered together.

Weak-positive

A scatter plot with a red line showing a positive, increasing relationship. A red circle highlights the data points and shows they are more dispersed and therefore a weak relationship.

No relationship

A scatter plot with a red line showing a flat, or no, relationship. A red circle highlights the data points and shows they are more dispersed and therefore a weak relationship.

Correlation coefficient

Used to quantify the relationship
Represented by the letter, r

r =	Relationship description
-1	Strong-negative
0	No relationship
1	Strong-positive

Calculating the correlation coefficient is beyond the scope of this course

Correlation coefficient and scatter plots

Strong-positive r=0.9

A scatter plot with a red line showing a positive, increasing relationship. A red circle highlights the data points and shows they are tightly clustered together.

Strong-negative r=-0.9

A scatter plot with a red line showing a negative, decreasing relationship. A red circle highlights the data points and shows they are tightly clustered together.

Weak-positive r=0.35

A scatter plot with a red line showing a positive, increasing relationship. A red circle highlights the data points and shows they are more dispersed and therefore a weak relationship.

No relationship r=0.0

A scatter plot with a red line showing a flat, or no, relationship. A red circle highlights the data points and shows they are more dispersed and therefore a weak relationship.

Adding context to a scatter plot

A scatter plot with "Total Bill" on the x-axis and "Tip" on the y-axis. "Party Size" is used to color the data points based on the value. For example, a party size of 1 are dark blue and a party size of 6 are bright yellow.

Let's practice!

Exploratory Data Analysis in Power BI