Optimizing Mobile Sites Through Multivariate Testing and A/B Testing

What is Mobile Multivariate Testing?

Common methods for running controlled experiments on mobile web pages range from simple A/B testing to sophisticated multivariate testing, also known as multivariable testing. In A/B testing, one or more new versions of a page or single site element compete against an existing control version. For example, two versions of a headline might compete against an existing headline. Mobile multivariate testing, on the other hand, is like running many A/B tests at the same time, where there are multiple elements being tested at the same time. For example, two different product images, plus two different headlines, plus two different product copy text, for a total of 27 possible combinations (including the original control versions).

What's important to understand about mobile multivariate testing is that it not only shows you which combination of elements lead to more sales or pull more leads, but it reveals which individual elements influence visitor behavior vs. those that do not. For example, did variations in product image influence visitor behavior more, less, or the same as the wording? Understanding how each site element causes visitors to interact with your mobile site is the essence of a test-learn-repeat process that marketers can use to synthesize new ideas and continually improve their mobile site's ability to achieve and exceed their marketing goals.

Mobile Multivariate Testing as a Process for Ongoing Optimization

The process of mobile multivariate testing reveals not only what works and should be implemented, but also what does not work and should be avoided. Every new idea, whether content, feature or marketing campaign related, should be put to the test to determine if it helps or hurts the visitor experience. While some new ideas lift conversions, others fail - sometimes substantially. But even with these failures, there is knowledge gained in what to avoid the next time. The ability to test a new idea and "look before you leap" is a definite advantage that breaks the constraints on mobile marketing innovation. Only once a solid testing capability is in place, and the impact of any mobile site change able to be quantified, can mobile marketers truly optimize their mobile site's effectiveness.

What are Common Mistakes to Avoid When Testing Mobile Content?

There are five types of common errors that are easy to make when running mobile multivariate tests. Fortunately, they can be avoided with some careful thought:

1. Improper factoring caused by little or no isolation of individual test changes; for example, changing a headlines text, font color, and font style, all at the same time as a mobile A/B test instead of a multivariate test. Why is this problematic? Because many changes grouped into an A/B testing makes it impossible to isolate the impact of each individual change. For example, was it the font color and/or the text that caused the visitor to behave differently?

2. Running a test for too much or too little time. Stopping a mobile multivariate test early because you think you have a winner can increase the risk for statistically invalid data, and may increase time bias from external events and/or conversion cycles. Running a test too long increases the risk of wasting time waiting for nominal results and consumes user sample that could be applied towards another test.

3. Tracking or analyzing wrong user behavior (KPI's). For example, measuring a KPI that is too far upstream (i.e., in a conversion funnel) from the ultimate goal, or measuring only one KPI when there are multiple indicators and/or goals that matter. There's also the risk that a measured KPI improves, but at the expense of another (untracked) KPI, or that the measured KPI is actually a bad predictor of the ultimate goal.

4. Not using behavioral targeting or audience segmentation. This means optimizing your mobile site or campaign for "anyone and everyone" by not targeting tests to include good visitors (and exclude bad visitors) and not slicing the results by meaningful segments. Why is this problematic? Because not all visitors are the same - they're at different stages of the customer lifecycle, using different mobile devices, and some may be mistakenly in the wrong site altogether.

5. Not taking action on results of the test! This could range from not making the winning changes to your mobile site, or not taking what you've learned in one test and running another follow-on test (i.e., the essence of an iterative test-learn-repeat methodology). The risk here is that there is no momentum gained, no ongoing strategy applied, no realization of test results, and worst of all underwhelming ROI.

How can Multivariate Testing Optimize my Mobile Web Marketing?

Multivariate testing can yield some very meaningful results in enhancing mobile marketing results. For example, we worked with a well-known online auction house to perform a series of multivariate test campaigns to understand which elements were most impactful in visitor bidding conversions. The team tested variations in elements such as mobile page layout and messaging, individual item landing pages, and calls-to-action, resulting in the following results:

* 429% increase in bidder activity
* 83% increase in catalog browsing activity
* 166% increase in individual product views
* 590% increase in opt-in registrations

If you are looking optimize your mobile marketing efforts, multivariate testing can and should be part of your arsenal of analytics and optimization products.