An Overview of Landing Page Testing
The primary objective of landing page testing is to predict the behavior of your audience given the specific content on the landing page that they see. It involves collecting a limited sample of data during your test, summarizing and describing it, and then predicting how people from the same traffic sources will act when viewing the page. The ultimate goal, of course, is to find the best possible version of the landing page among all of the variations that you are testing.
How is Testing Done?
If you're new to the idea of website conversion optimization, you'll want to familiarize yourself with the different types of tests (also called "tuning methods") that can be used to measure the impact of your landing page changes. Each method has benefits, and limitations, and you should consider some of these factors before determining which to use:
- The size of your search space - Some tuning methods can only handle search spaces with a few total recipes, while others can routinely find the best answer out of millions of possible recipes.
- Your available landing page traffic levels - Simple tuning methods can work with as few as ten conversions per day (assuming that you are willing to wait months to collect enough data), while others require higher minimum traffic levels.
- The desired level of confidence in the test outcome - The desired statistical confidence level is completely up to you, and depends on the severity of the consequences from making an incorrect decision. Typically values between 90% and 99% are chosen.
- Whether you want to consider variable interactions - variable interactions play a huge part in online marketing experiments. Some tuning methods do not consider them at all, while others identify them and take them into account in order to produce the best possible results.
No idea what these terms mean? Check out our testing terminology page.
The simplest tuning method is A/B split testing, and is a good starting point for getting your feet wet with landing page optimization. Multivariate testing is much more complicated and has several important variations, twists, and considerations that can radically alter the end results.