Web analytics platforms such as Omniture (Adobe Marketing Cloud), WebTrends and Google Analytics are amazing tools. They are trending tools of your websites actions and conversions. In a web analytics tool you can pull forward paths to conversion, pages users saw prior to conversion, and many other reports that allow you to assume conversion. However, you cannot assume causality with statistical significance.
In order to have a causal relationship, you need to have association. Once a strong association has been created, you can infer a causal relationship between two variables. In other words, Page A caused Conversion A. For this, you need raw data and access to IBM SPSS, SAS or R.
Why Should You Care About Causality?
Because the trending tool is a one size fits all solution, and you are making assumptions about the data without statistical significance. There is no strength of relationship that stands behind the data. Your analysts could easily be sending your team on a wild goose chase to try something that may not work. This is a waste of your organizations time and money.
This simplistic view of pages and conversions shows that there is a moderate relationship between Page D and Conversion A. Thus, Page D causes Conversion A with a moderate statistical significance. There are several important questions you can ask yourself from this finding.
- How do I make the relationship stronger between Page D and Conversion A ?
- Is a form to Conversion A clearly visible on Page D?
- Why are users that visit Pages A, B, C not converting on Conversion A?
With a relationships matrix, you can derive many hypothesis about your website based on statistically significant data. This model can be created for web data, mobile data, and social data to create valuable insights. Everything on your technical environments is somehow related, but it takes some strong statistical knowledge to derive causal relationships to conversion.