A/B/n testing is a method of comparing more than two versions of a webpage or other user experience to see which performs best. It's an extension of A/B testing where 'n' represents the number of versions being tested.

How it Works

In an A/B/n test, you compare things A, B, C, D, … N against each other. These could be different versions of a webpage, different headlines, different images, or any other element that you want to test.

For example, if you're testing a landing page, you might have:

• Version A: The original page

• Version B: The page with a different headline

• Version C: The page with a different image

• Version D: The page with a different call-to-action

Each version is shown to a different group of users at the same time, and the performance of each version is measured using metrics that you choose.

Choosing Metrics

The metrics used to determine success can be whatever the experimenters choose. For example, in a webpage test, a metric might be the number of clicks on a call-to-action button, or the number of pageviews per session.

In the historical example of Dr. Lind's scurvy trials, the metric was whether or not the scurvy symptoms went away.

Forming a Hypothesis

To avoid testing too many random things, it's recommended to form a communicable hypothesis for each variant of an A/B/n test. This means you should have a clear idea of what you expect to happen when you make a certain change.

For example, your hypothesis might be: "If we change the call-to-action button from grey to gold, then more users will click on it, because the gold color is more eye-catching."

Real-World Example

A real-world example of A/B/n testing is the case of YoYoFuMedia, who earned a client 28% more revenue on their Shopify site by ultimately changing the sitewide “complete purchase” button from grey to gold. This is a perfect example of how small changes can make a big difference in user behavior.