Picking your test type: A/B or Multivariate?

Tuesday, July 28, 2009 7/28/2009 01:44:00 PM

Google Website Optimizer lets you run two types of experiments: A/B and Multivariate. Both types help refine your website to increase conversions, but some tests are better suited for A/B while others are better suited for Multivariate. Choosing the appropriate type for your test can save you time and help your test run more smoothly.

If you want to test two (or more!) completely different pages against each other, we recommend using an A/B test. For example, you can change the content of a page, alter the look and feel, or move around the layout. Visitors will be shown the alternates and Website Optimizer will keep track of how each page is converting.

Multivariate experiments work best when you want to refine different sections on your webpage. For example, you can test different headlines, images, and buy buttons all at the same time. Website Optimizer will show the combinations to visitors and keep track of each combination's performance.

We've created a short video that can serve as your reference guide to selecting the appropriate test type:



And, of course, you'll find many more videos on our Website Optimizer YouTube channel.

Posted by Trevor Claiborne, Website Optimizer team