The best use of statistics ever?

I love candy.  And I love this 538 feature using head-to-head comparisons and statistics to figure out what makes various candy appealing.  For myself, I’m all about chewy.  Love laffy taffy, gummies, twizzlers.  And, of course, chocolate.  What kind of failed human doesn’t love chocolate.  Anyway, here’s the top of the ranking (whole thing at the link):

I do love both twix and kit kat, which are near the top.  I enjoy Reese’s, but did not realize the combination of chocolate and peanut butter was so beloved.  What makes this extra cool, though, is the OLS regression model to determine which features make candy most appealing.

So, there you go, not just chocolate and peanut butter, but fruit flavors.  Now, what the statistician in me really wants to see is an interaction term for chocolate and peanut butter together.  I strongly suspect that would be statistically significant.

Anyway, happy Halloween!  Rest assured, I will be plucking twix, kit kat, and twizzlers right out of my kids’ Halloween pumpkins tonight as candy tax.

Advertisements

About Steve Greene
Professor of Political Science at NC State http://faculty.chass.ncsu.edu/shgreene

One Response to The best use of statistics ever?

  1. R. Jenrette says:

    Call me oppositional. I love both peanut butter and chocolate but I don’t like them mixed at all.

Leave a Reply

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 )

Connecting to %s

%d bloggers like this: