February 9th, 2012 at 12:09:50 PM
permalink
According to an AP article on the ESPN website, a camel in New Jersey went 15-6 this year, including a correct pick of the Giants over the Pats in the Superbowl. With that win, the camel is now 89-51 lifetime.
Would a proper analysis of whether the camel is better than a coin flip need to include the spreads on each game picked? Or is it enought that the expected random results should be divided 50/50?
If the expected result is 50/50, is the camel's record significantly better than random?
Would a proper analysis of whether the camel is better than a coin flip need to include the spreads on each game picked? Or is it enought that the expected random results should be divided 50/50?
If the expected result is 50/50, is the camel's record significantly better than random?
Simplicity is the ultimate sophistication - Leonardo da Vinci
February 9th, 2012 at 12:27:08 PM
permalink
According to my math, the odds of luck this good or better are 1 in 931. That is using the binary distribution, not a Gaussian estimate.
As long as he was randomly picking then his odds wouldn't matter whether it was against the spread or straight up.
If I ran a zoo I would have every single animal make such picks. One of them would probably finish with a record this good and give the zoo some good free publicity.
As long as he was randomly picking then his odds wouldn't matter whether it was against the spread or straight up.
If I ran a zoo I would have every single animal make such picks. One of them would probably finish with a record this good and give the zoo some good free publicity.
"For with much wisdom comes much sorrow." -- Ecclesiastes 1:18 (NIV)