A way to test the UX of an application by displaying one version of it to 50% of the users of the application, and displaying another version to the rest of the users. You then compare how the two versions performed by using metrics such as click through rates, the average time on the site, etc.
I'm running A/B split testing using Instapage. My dilemma is whether using clicks or orders versus visitors should be my conversion rate. This is what I had so far A: 556 visitors - 27 conversions ...