Correlation coefficient
Correlation coefficients can give a starting assessment to a correlation test and can be used to determine the proportion of variance explained in variable x that can be attributed to variable y.
A company with a website is interested in the activity of their website users, and believes the amount of time the users spent searching on the site is positively correlated with the amount of time spent checking out on the site. Assess the company's assumption in the webdata
dataset.
The webdata
data set and ggplot2
package have been loaded for you.
This exercise is part of the course
A/B Testing in R
Exercise instructions
- Create a scatter plot of
Time
on the x-axis andTimeSearching
on the y-axis. - Determine the correlation coefficient of
Time
andTimeSearching
and store it ascoeff
. - Derive the proportion of variation in
Time
that can be attributed toTimeSearching
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Create a scatter plot
ggplot(___) +
___
# Determine the correlation coefficient
___
# Determine the proportion of variance
___