As a designer, understanding how we all problem solve and why our brains are responsive to certain information more than others can be very helpful in the design process. Multivariate testing is crucial in the evolution of your website to attract new leads and convert existing ones. Unlike A/B testing, multivariate tests many aspects of a system at a time to learn of the relative impact of that change. Through utilizing this optimization tool, you can learn the best combination of page elements – things like headlines, product images, and price points – to increase your sales and conversions.
While the aim of your site may vary from others, most business sites strive to generate revenue by selling their products (an e-commerce site), generating sales leads, or providing free information in hopes a sale will come at a later date.
Who Should Use Multivariate Testing?
If your website is already generating plenty of traffic (and hopefully some conversions), multivariate testing may be the perfect option for you. You’ll find the optimum combination of website elements in a shorter span of time and achieve significant improvements in the website’s performance. If you’re not sure about the optimum amount of traffic required to test, there are estimation tools available to help you find out an effective number.
Determining Which Areas to Test
Since not all sections have equal impact on the conversion rate in a multivariate test, first determine which elements play a pivotal role of turning visitors into conversions. One of the biggest factors for most businesses is the call to action. The headline is also what draws people in, so it’s worthwhile to test that as well.
Headline: headline 1 and headline 2
Text: text 1 and text 2
Image: image 1 and image 2
The multivariate tests aims to see which combination of these versions achieves the highest conversion rate. Traffic is split between the following to see which combination produces the highest conversion rates.
Headline 1 + Text 1 + Image 1
Headline 1 + Text 1 + Image 2
Headline 1 + Text 2 + Image 1
Headline 1 + Text 2 + Image 2
Headline 2 + Text 1 + Image 1
…you get the idea. All possible combinations of elements are tested to see which is the most effective. Effectiveness covers two areas: conversions and visitor experience. Obviously more conversions are the ultimate goal of any test, but this will also lead to a better experience for visitors, as they are better able to find what they are looking for in terms of content, products, etc.
Multivariate Testing Tools
To create your multivariate test, first choose a framework that supports it. Afterwards, choose which sections to include in it.
Website Optimizer is a free basic multivariate testing tool from our friends at Google. It’s the easiest way to see how making changes to page elements has on conversion rates. As with most of their products, there is plenty of online support and how-tos to help newcomers get started.
Multivariate testing holds a lot of potential for positively impacting a company’s revenue and profits. The success of a multivariate test can really only be measured quantitatively in the results it brings the site. Proper implementation and analysis of data will prove to be huge game changers for first time participants. Take these ideas into account while measuring the effectiveness of your own website and the rewards could be abundant. Have you used variable testing to make more money?
Blake Sanders is a writer for Maxymiser and an expert on multivariate testing and other variable data. Blake enjoys discussing various topics on increasing website conversions.
Note: Photo courtesy of stevendepolo, redplastic, and mil8 via FlickR Creative Commons.