Did you consider whether density of pizza places inversely correlated with ratings?
C. J. Newton

It’s definitely a possibility! There could be regional standards in play like you mention: if there’s only one pizza place in town, it’s by definition the best. So let’s run the numbers…

correlation = -0.027

Alas, they appear uncorrelated. However, looking at the graph demonstrates a fundamental statistical truth about sample size. As the count gets bigger, the range gets shrinks from anything in the 1–5 range to between 3–4. So as we pull a larger sample size, we get reined in toward the mean, as you’d expect.

Like what you read? Give Walker Harrison a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.