Benford's Law

Pick any spreadsheet of real-world numbers. Doesn't matter what kind — the populations of cities, the lengths of rivers, the prices of houses sold last year, the daily trading volumes of stocks. Any collection of numbers that describes the world. Now look at the leading digit of each number. The first digit. And ask yourself: how often does each digit appear in that first position? Your instinct says roughly equal. One through nine, each showing up about one in nine times. About eleven percent each. The world doesn't favor any particular digit, so why would it favor one? That instinct is completely reasonable. And it is wrong in a way that will change how you look at every dataset you ever encounter. One appears in the first position roughly thirty percent of the time. Two appears about seventeen percent of the time. Three, about twelve. The percentages keep falling, all the way down to nine, which leads the pack barely five percent of the time. This is not a coincidence, not a quirk of one particular dataset.