Pages and conversion
What is A/B testing?
A/B testing is showing two versions of a page or element to split traffic and measuring which one converts better.
Formula
Lift = (variant rate − control rate) ÷ control rate
A control converting at 3.0% and a variant at 3.8% is a 26.7% lift. A significance test tells you whether the gap is likely real or chance.
Work out yours with the significance calculator.
A real store example
Nero polyester listicle: over 60 Meta ads linked here.
Nero runs more than one version of the same argument: this listicle, a second copy of it and a separate "5 reasons to ditch your polyester gym clothes" page. Comparing what each version sells is the idea behind an A/B test.
Put A/B testing to work
Replo Experiments A/B tests the pages you publish with Replo. Theme Builder tests pages in your Shopify theme.
Go deeper
How to A/B test landing pagesA/B testing questions
- How long should an A/B test run?
- Until each version reaches the sample size you planned, and at least a full week so weekdays and weekends both count. Plan the sample size first with a significance calculator.
- Can I A/B test pages in Replo?
- Yes. Replo A/B tests the pages you publish with it, on one link, with results next to your sales. Theme Builder, Replo's Shopify page builder, tests pages in your theme. See A/B testing with Replo.
Related terms
Browse the glossaryConversion rate
Conversion rate is the share of visitors who complete a goal, usually a purchase: conversions divided by sessions.
Heatmap
A heatmap is a picture of a page that shows where visitors click, move and how far they scroll, with hot colors for the most activity.
CTA
A CTA (call to action) is the button or line that tells a visitor the next step to take, such as "Shop now" or "Build your pillow".
Landing page
A landing page is a page built for one campaign or audience, with one goal, usually where ad or email traffic lands.