You’ve probably heard that split testing elements of your website can improve your conversion rates. And that’s true. But there are many kinds of split testing out there. And there are many ways to set up split tests on your website.
I can’t discuss every feature of every testing tool out there, but I can give you a major overview of the different kinds of split testing software.
The first main division is between simple split testing (single variable) and multivariate testing.
Simple split testing is easy. You’re just “trying stuff” one thing at a time. You want to try a different headline? Split test it. When that test finishes, you want to “try” something else? Split test that. You can test one alternative version or many. As long as it’s a single element of your page you’re testing, that’s simple split testing. All you need is a tool that rotates the different versions of the headline (or whatever) on your page, and keeps track of which one produces the most sales.
There are a few simple split testing tools available. Some are free and some cost money. Google offers a free tool, though you do have to have an Adwords, and an Analytics account to use it.
But simple split testing can be discouraging. When you test a new idea against your control version, sometimes the control version wins. In fact, it often wins. You can get a string of disappointing tests all in a row. What would it be like if you could test 10 things at once? Well, Free51.net ’d be bound to find at least one or two ideas that led to improvement. And what if you could test all those ideas simultaneously with the same amount of traffic it takes to test one idea with simple split testing? Well, it sounds like magic, but that’s exactly what multivariate testing can do for you.
There are further distinctions among multivariate split testing tools. There are hosted solutions, and solutions you install on your server. Typically a split testing program can run a little more quickly if it’s on the same server as your webpage. Installed programs tend to be less expensive, too. You also will have complete control of your data. On the other hand, with a hosted solution, you don’t have to do an installation.
The Split Test Accelerator is a good choice if you want to install the software on your server. Kaizentrack is another optoin. If you want a hosted solution, you can look at Sitespect and Vertster.
Another 3-way distinction among multivariate split testing tools is between Taguchi-based systems, Full factorial systems, and Random independent rotation of factors. With a Taguchi system, you run traffic to only a small, carefully-selected subset of the possible combinations of your factor levels. This allows you to cycle through every combination every 12, 18, or 36 pages, whichever the case may be for the test design you’re using. This allows you to find the best combination very quickly. Some care does have to be taken to avoid interaction effects among the factors. Taguchi-based tools include the Split Test Accelerator and Vertster.
Full factorial tools allow you to cycle through all the combinations for your factors. So if you have 3 headlines, 3 offers, 3 P.S. statements, and 3 images you’re testing, you will cycle through 81 pages. One advantage of full factorial testing is that you don’t have to worry as much about interaction effects. Good and bad interactions should show up in the data. However, if you want to receive this advantage, you have to run many times the traffic through your test as you would with a Taguchi test. You also can’t run as many combinations. Google’s website optimizer is a full factorial tool.
Some multivariate tools randomly serve the options for each factor independently from what is served for the other factors. This can lead to more flexible test design, but also to more interaction effects and other statistical noise, leading to longer tests.
There are other distinctions and features worth noting. And each solution has a different mix of pros and cons. But this should get your oriented a bit before you make your decision.
Dominic DeLong has used split testing tools for years to improve landing pages.