Sunrise at Spider Rock

Thursday, September 24, 2009


Carl Bialik wrote a fascinating article in the Wall Street Journal yesterday on lotteries and probability.  The numbers  shown above won the Bulgarian lottery. Twice. Consecutively. In the same week. Statisticians place the probability of this occurence at somewhere between 1 in 5.2 million and 1 in 14 million.

Experts note that with the sheer numbers of lotteries being played, such coincidences are bound to occur.  What would be improbable is if they did not. Still as a fan of Jung, synchronicity and all sorts of hocus pocus, I wonder if there are any other plausible explanations?

NPR had a great article a few years ago about Pakistani cabdriver Ihsan Khan, who dreamt the numbers 2-4-6-1-7-2-5 - Powerball 31 that went on to win the 55 million dollar Maryland Powerball prize. He went back to Battagram, Pakistan and was elected mayor.  Days later an earthquake hit and he doled out hundreds of thousands of dollars from his personal fortune to save his village. As was foretold in his dream. Curious.

There is a fascinating story in the article  about an incident with the Oregon lottery in the year 2000.  Detectives visited a Washington newspaper after they published the next day's winning numbers. The paper had mistakenly downloaded results from Virginia. Which happened to win the next day. Go figure.

The graph shows that low numbers tend to be picked much more often so that one might have a better chance against the competition by picking between 31 and 45. Don't fall on people's birthdays. And why is lucky 7 so popular? And don't the even numbers take a bit of a pounding?

Found the interesting REvolution Computing blog while checking into this - check it out - all kinds of pointy headed probability work.  They are the creators of an open source language for statistics called R - I quote:
REvolution R is based on R, a language and environment for statistical computing and graphics. The R Project for Statistical Computing is an ongoing initiative by the open source community, involving an international ecosystem of academics, statisticians, data miners and others committed to the advancement of statistical computing. Through the contributions of this community, innovations in methodology can be rapidly incorporated and disseminated.

No comments: