Insight, Part 1: Correlation is *Something*

I was shamed by their good will and mortified by their cooking. There seemed to be some correlation between devotion to God and a misguided zeal for marshmallows.

– David Sedaris, c.o.g.

Planners, analysts and researchers of all shapes and sizes take pleasure in preaching, ad nauseam, that correlation and causation are not even distant mathematical cousins. That said, a client once put me in my place with a pithy truth on the topic: “It may not prove causation, but correlation is something!”

He, of course, was absolutely correct: correlation does not prove causation, but correlation damn sure is something. And not only is it something but, truth be told, correlation is often presisely what we look for when we collect and analyze consumer data.

Put another way, not only is correlation most definitely something, but that something might very well be the seed of a defining customer insight about a targetable segment.

Sedaris’ observation about religious faith and marshmallow culinary ingenuity – from his delightfully scathing essay, c.o.g. (book here, movie here) – is easy to frame as a research objective and test quantitatively. If correlation between faith, marshmallows, and, say, some rudimentary demographics proves to exist, this correlation alone might form the foundation for a sound marshmallow marketing strategy: think occasion-based messaging, premium and loading tactics, product development (marshmallows that melt at specific temperatures for specific purposes, marshmallows mixed with different spices), and product extensions (see cooks.com, not to mention Amazon).

Consumer insight? Yes!

Is it an actionable insight? Most definitely!

What of causation? Totally irrelevant at this early phase in our marshmallow renaissance scenario, but also a subject of crucial importance for later research waves.

This reminds me of an interesting factoid I heard a few years back by way of the Harvard Business Review:

  • Blondes earn 7% more than brunettes
  • The husbands blonde women marry earn an average of 6% more than the husbands of women with other hair colors

Consumer insight? To be continued…

Advertisements

Published by

PlasticSpoon

Hapa writer looking for the American Dream in all the wrong places.

One thought on “Insight, Part 1: Correlation is *Something*”

connect the dots...

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

w

Connecting to %s