Mann-Whitney U test
Let's assume that you are an Analytics Engineer at an early-stage start-up where the traffic size to your website is small. Since in many cases you will need to run the tests for a long duration to gather a sample size that is large enough to satisfy parametric tests' assumptions, you may need to lean on non-parametric tests to make faster decisions.
One of these tests is the Mann-Whitney U test, which is a statistical significance test used to determine if two independent samples were drawn from a population with the same distribution. You will leverage this test to analyze the difference in time_on_page
between two groups of the checkout dataset. The checkout DataFrame is available for you and pingouin
has been loaded along with pandas
and numpy
.
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 and count of time on page by variant
print(checkout.____('checkout_page')['____'].____({'____', '____'}))