If you want to determine if average spending varies for customers coming from different channels, it's not enough to simply compare the numbers for a given period. Until you carry out the correct test, you can’t say that the difference between the means is random, and you also can't say that the difference is large enough to posit that spending between the two populations does indeed vary (i.e. that the difference is significant).
In order to test your hypothesis that the means of the two statistical populations are equal based on samples taken from them, apply the method scipy.stats.ttest_ind(array1, array2, equal_var).
Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.