Interactions and the Power of Context

What are variable interactions? Simply put, it is when the setting for one variable in your test positively or negatively influences the setting of another variable.

Lets look at a simple example: We are selling cars and want to test two different headlines and two different pictures. So we have a total of four possible combinations of our two variables.

If you believe that there are no interactions, then you must also believe that there is a “best” headline regardless of the accompanying picture, and that there is a “best” picture regardless of the headline used.

Clearly this is not the case. Each variable depends on the context in which it is seen. #1 has a very strong positive interaction (connecting the speed and power in the picture with the word “Fast” in the headline). #2 has a strongly negative interaction (making you think about the consequences of fast driving – “speed kills”). #3 has a mildly positive interaction (supporting the notion that you can go fast and still be safe). #4 has a positive interaction (playing on the fear of accidents and highlighting Volvo’s safety record).

In online marketing we want interactions.

Most creative directors and marketers want the picture to reinforce the headline, and the sales copy, and the offer, and the call to action. But many landing page testing techniques assume that there are absolutely no interactions between variables — that they are completely independent of each other. In fact, multivariate tests are carefully constructed to be as small as possible by ignoring all interactions. Obviously for online marketing this is an absurd assumption. So while you may be able to get some positive results by ignoring interactions, you will not be getting the best results.

The goal of landing page tuning is not to find the best individual variable settings, but rather to find the best combination of variable settings.

“A player who makes a team great is much more valuable than a great player.”

– UCLA Coach John Wooden