whump.com | More Like This WebLog

Consider this: The Oakland A’s, with a payroll of around 40 million, win as many or more games than the New York Yankees, whose payroll is over three times as large. Why did this happen? Billy Beane, the A’s general manager, has discovered three things: Bill James, arbitrage, and that the intuition of a Major [...]

What to do when someone starts using stats as a rhetorical weapon.

The Limited Pie (whose banner with Chairman Greenspan in drag just creeps the heck out of me) introduces the notion of expected value to its readers.
I will, however take the certain payoff of $9K. Risk is something you can pay to reduce, and I’m happy to pay $500 in LP’s example.
The Pie is ecumenical, but [...]

How bad did Eisenhower whup up on Stevenson in 1956? Not as badly as the Electorial College tally would make you think. Check out the historical and geographical atlas of US presidential elections to see how important the Electorial College can be.

The sidebar to a New York Times article on how Benford’s Law is used to detect fraud has a clear explaination of why it describes the frequency distribution of digits in non-random data.

The zipf distribution, where log(frequency) = log(rank), used describe the size distribution of firms, and the popularity of web sites is related to Benford’s law, which describes the frequency distribution of digits in non-random data (prices, for example.) Interesting stuff.