Means and proportions
Mean and proportion estimates usually serve as great primary metrics when aligned with the business goals.
The checkout
DataFrame is loaded for you, where every row corresponds to a unique user visiting the respective checkout_page
along with their actions and additional attributes. A '1'
value in the purchased
column corresponds to a user purchasing an item, and a '0'
means they have abandoned the page without purchasing. You will examine the data and calculate both mean and proportions as an exploratory step towards evaluating which design performs best.
This exercise is part of the course
A/B Testing in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Calculate the mean order value for each group
checkout.____('____')['____'].____()