I was reading a blog post on boat names because it was on Hacker News this morning. The post contained a link to a data set on dog names in NYC and I poked around the data a little. The top names were not at all what I expected, but then again this is limited to NYC; it’s not a sample across the US. These were the top 10 names:
- Bella
- Luna
- Max
- Charlie
- Coco
- Lola
- Rocky
- Milo
- Teddy
- Lucy
I wondered if the name frequencies might fit a power-law distribution. They do not, but they follow a log-normal distribution remarkably well.
Interesting: My mother’s dog is Bella (Arkansas), and our dog is Charlie (which we chose finally over Max); we’re in Mongolia. (And my wife’s second dog was Rocky; this was in Australia.)
Were you surprised that it was not a power law? Or did you suspect it would be actually be lognormal?
I was a little surprised. I thought a power law would fit better than it did. But I was very surprised that the log-normal fit so well.