Tag Archives: Statistics

“Anything but country”: What factor analysis reveals about our tastes for tunes [at Scientific American]

When asked to indicate their favorite type of music, plenty of people say they like “anything but country.” Is this really accurate? Why do rock music fans also tend to like punk and heavy metal? And why on earth would Pandora play a Britney Spears song on a Lil’ Wayne station?

I have a post over on the Scientific American guest blog today about musical preferences that answers all of these questions. Here’s a quick blurb from the beginning of the post:

There’s a strong appeal to the idea that we can study and categorize music preferences, and that these categorizations are somehow deeply unique and meaningfully representative of who we are as individuals. But what if I told you that when it boils down to it, we’re not all that different from each other – in fact, most of those seemingly “nuanced” differences in musical taste can be boiled down to a mere five musical factors?

In the rest of the post, I discuss the findings of the study, what it means for websites like Pandora, and how we can better predict our musical likes and dislikes. I also attempt to write a “general audience”-friendly explanation of how to interpret a factor analysis, step by step.
Click here to go read the entire post!


Rentfrow PJ, Goldberg LR, & Levitin DJ (2011). The structure of musical preferences: a five-factor model. Journal of personality and social psychology, 100 (6), 1139-57 PMID: 21299309