I have two sets of data taken from a marketing exercise.
Set 1. 1000 ad views created 200 clicks on the advert
Set 2. 1624 ad views created 950 clicks on the advert.
I want to learn if the two sets of data are significantly different or not. If not, how much data do I need to learn that they are significantly different. I don't have the actual performance behind each ad view (therefore I can't find the actual standard deviation) but I believe the data is normally distributed.
Any ideas?
Thanks in advance