24 March 2011
If you just take a pile of data that shares one common element (the thing you are interested in), you will likely find some other common elements purely by chance. Until you prove otherwise, these are associations, not necessarily correlations.
Well worth reading the full post. It highlights the reason I’m cautious about the general body of ‘research’ that comprises conjecture about what people are up to on the web. These facts are very much of the “and if you laid them all end-to-end they would stretch from here to the moon” type of analysis, hence not useful for formulating genuinely useful strategy.
The author rightly emphasises that ‘best practice’ is what is best for you. Unfortunately this tends to be time-consuming to discover and is based on what you can see and understand through the microscope of your own analytics and not what you might surmise from general observations.
Research is key, understanding the limits of this research is even more important and extensively testing your hypotheses is more important still.