Scribd
Upload
18 views

E 2 Cae 2 BC

This document discusses assessing relationships between numeric variables. It describes using scatter plots to visualize relationships, covariance to measure how variables move together, and correlation to quantify the strength and direction of linear relationships between -1 and 1. Scatter plots help determine if relationships are linear or nonlinear, while covariance and correlation are interpreted as positive or negative depending on the direction of movement between variables. Correlation specifically measures linear association after standardizing covariance.

Uploaded by

Karan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
18 views

E 2 Cae 2 BC

This document discusses assessing relationships between numeric variables. It describes using scatter plots to visualize relationships, covariance to measure how variables move together, and correlation to quantify the strength and direction of linear relationships between -1 and 1. Scatter plots help determine if relationships are linear or nonlinear, while covariance and correlation are interpreted as positive or negative depending on the direction of movement between variables. Correlation specifically measures linear association after standardizing covariance.

Uploaded by

Karan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

ETF1100 Business Statistics

Week 6
Summarizing Relationships Coding on Laptop by Matthew Henry

Charanjit Kaur https://burst.shopify.com/photos/coding-on-laptop?c=software-development


Week 6: Assessing Relationship between Numeric Variables

Learning Outcomes:
• Identifying the presence and direction of relationship between two
numerical variables.
• Quantifying the strength and direction of the relationship through
correlation.
• Visualising the relationship through a scatter plot and determine
whether the relationship is linear.
Finding Relationship between Two Numeric Variables

Finding relationship between variables:


For categorical variables, the relationship can be assessed by
examining whether variables were independent or not.

For numeric variables, we will use different techniques:


▪ scatter plots
▪ covariance
▪ correlation
Scatter Plots
It shows visually on how two two numerical variables relate to each other.
e.g. Price of real estate vs total land area
Scatter Plots
It is generally used for exploring a few key questions:
• Is there a relationship between variable X and Y ?
• What direction is the relationship?
• How strong is the relationship?
• Does the relationship appear to be linear or non-linear?

However, the interpretation can be somewhat subjective!


Covariance
It measures how two variables move together.
The sample covariance of two variables, X and Y, is given by the formula:
𝑛
1
𝐶𝑜𝑣 𝑋, 𝑌 = ෍ 𝑋𝑖 − 𝑋ത 𝑌𝑖 − 𝑌ത
𝑛−1
𝑖=1

Covariance is the average of the products of paired deviations from the


mean for the two variables, X and Y.

In Excel, =COVARIANCE.S (range of X data , range of Y data)


How to Interpret Covariance
A positive covariance indicates the two variables move in the same direction.
As X increases, Y also increases.
A negative covariance indicates the two variables move in the opposite
direction. As X increases, Y decreases.

The covariance value itself has no meaningful interpretation as it is measured in


squared units of the variables (like the variance).
It is also influenced by the units of the variables.
e.g. Cov(Price,Area) = 51447
Correlation
It is a standardized measure of the covariance.
𝐶𝑜𝑣(𝑋, 𝑌)
𝐶𝑜𝑟𝑟 𝑋, 𝑌 =
𝑠𝑥 𝑠𝑦

• It is the covariance divided by the standard deviation of X (sx) and Y (sy).

• Its values range from -1 to +1, so it is unit-free measurement.

In Excel, =CORREL (range of X data , range of Y data)


CORREL(Price, Area) = 0.566
Correlation
• The magnitude reflects the strength of the relationship.
• Closer to either -1 or 1 the stronger the relationship, closer to 0 the weaker
the relationship
• The sign indicates the direction of the relationship
Notes on Interpreting the Correlation
Correlation is a measure of linear association.

The correlation does not work well, or at all when there are non-linear
relationships in the data.
Scatter Plot of Non-Linear Data
Correlation ≠ Causation

“As ice cream sales increase,


the rate of drowning deaths
increases sharply.

Therefore,
ice cream consumption
caused drowning.”

Ice Cream Cone with Two Scoops by Thomáš Hustoles


https://burst.shopify.com/photos/whiteboard-chart?q=graph
Assessing Relationship between Numeric Variables
❖ Scatter Plot
▪ Visualising the relationship between two numeric variables.
▪ Assessing whether the relationship is approximately linear or not.
❖ Covariance
▪ Indicating how the two variables move together.
▪ It is influenced by the units of the variables.
❖ Correlation
▪ A measure of linear association. Only works for relationships that
approximately linear.
▪ Unit-free measurement between -1 and +1.
▪ Magnitude indicative of strength.

You might also like