I want to know if I need delta method for the below 3 scenarios for online experiment:
- % change of clicks per user between control and test group, (test clicks per user - control clicks per user)/control clicks per user
- % change of click through rate, click through rate is defined as (total clicks/user)/(total impressions /user). % change of this metric is: (test click through rate - control click through rate)/control click through rate
- this is the one that makes me confused the most, i want to know if I only calculate absolute diff between click through rate of test and control group, for example, (test click through rate - control click through rate), does delta method applicable in this case?
