Intuition behind statistical significance
In this exercise you will work to gain an intuitive understanding of statistical significance. You will do this by utilizing the get_pvalue() function on a variety of parameter sets that could reasonably arise or be chosen during the course of an A/B test. While doing this you should observing how statistical significance results vary as you change the parameters. This will help build your intuition surrounding this concept, and reveal some of the subtle pitfalls of p-values. As a reminder, this is the get_pvalue() function signature:
def get_pvalue(con_conv, test_conv, con_size, test_size):
lift = - abs(test_conv - con_conv)
scale_one = con_conv * (1 - con_conv) * (1 / con_size)
scale_two = test_conv * (1 - test_conv) * (1 / test_size)
scale_val = (scale_one + scale_two)**0.5
p_value = 2 * stats.norm.cdf(lift, loc = 0, scale = scale_val )
return p_value
This exercise is part of the course
Customer Analytics and A/B Testing in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Get the p-value
p_value = get_pvalue(con_conv=____, test_conv=____, con_size=____, test_size=____)
print(p_value)