Correlation vs Causation: Conversion Rate Optimization Tips

Correlation vs Causation - Conversion Rate Optimization TipsOne statistical concept that Internet marketers often overlook is the difference between correlation and causation. Understanding the difference between the two will allow stakeholders to make a decision on whether to adopt changes site wide or not. Once Internet Marketers have tested a hypothesis with variation pages that included several test elements, the confirmation on whether the test elements were influential in increasing conversion should be confirmed. 

The trick word here is test elements. Since most variation pages will have several test elements, understanding the influence of each element on conversion is critical. Let us assume that the test elements in our variation pages are:

a) Headline

b) Call to Action


Headline Call to Action Conversion
Variation  1 H1  C1 15%
Variation 2 H1   C2 25%
Variation 3 H2   C1 13%
Variation 4 H2   C2 18%

We created four variation pages based on two test elements. As you can see, Variation 2 and Variation 4 are the top two performing pages, contributed by elements H1, C2, H2. The only common element in the top performing variation pages is C2 or Call to Action – 2. This is where understanding the difference between correlation and causation is crucial.

Did Call to Action -2 contribute towards the increase in conversion?

What is correlation?

Correlation in CRO means that the test element and the conversion rate have some kind of a relationship. 

But based on two variation pages, you cannot conclude that Call to Action -2 caused the increase in conversion rate.

So what is causation?

Call to Action-2 contributing towards the increase in conversion rate can only be implied in a true experiment. 

So what is true experiment in Conversion Rate Optimization?

When Internet Marketers have complete control over at least one element of the experiment, then the Call to Action-2 element can be randomly placed in each experiment. Let us say that we are testing two similar pages with Call to Action -2 and the marketer has control over traffic allocation by Country of visitor. So when a visitor from US reaches your website, she is randomly allocated to Page 1 or 2. Now we measure the conversion rate for visitors from US. If we get a similar conversion rate above the actual control with +/- 2% variation, Call to Action-2 caused the increase in conversion.


Pages  Call to  Action Traffic (Random) Conversion
Page 1 C2 US 18%
Page 2 ( Page 1 Duplicate) C2 US 17.5%

 

If you want expert help in conversion rate optimization , contact us or you can call us at: India (Ph): +91 9497189032, UK (Ph): +44 (0)20-3371-9976 or US (Ph): +1 650-491-0004

ByteFive provides Internet Marketing Services (Search Engine Optimization (SEO), Search Engine Marketing (SEM), Develop processes and best practices for Internet Marketing, Manage and Analyze Web Analytics packages, Perform Landing page Optimization, Manage E-Mail Newsletter, Perform Competitor Research, Create & market Content, and provide customized training to help you achieve your revenue and business goals.

Subscribe to ByteFive's Newsletter