Here's Waldo

This kind of spatial scan statistics is really easy to misuse without careful multiple-comparison corrections. Would they have reported a 52% effect? a 51% effect? What about 1.4 inch bands? or 1.2 inch bands? That "remarkably thin" 0.3 percent will disappear pretty quickly.

Sorry that this is dismissive, but this piece is just a slightly more complicated case of http://xkcd.com/882/

Re: Here's Waldo

#6

Post by nwh » Wed, Nov 20, 2013, 4:07 PM UTC

He's not at the edges of the page partially due to the print process. You need a large border of disposable material that can be cut from the edges (bleed) should the alignment of the pages be slightly out when the book is bound and trimmed. It wouldn't be much finding half of Wally, so they don't put him where he might be cut in two with a guillotine.

(He's still better as Wally than Waldo.)

Re: Here's Waldo

#7

Post by Kalki » Wed, Nov 20, 2013, 4:09 PM UTC

As A kid I could not get enough of finding Waldo. I even had the Nintendo game.

Re: Here's Waldo

#8

Post by jffry » Wed, Nov 20, 2013, 4:09 PM UTC

Reminds me of this great StackOverflow thread on how to programmatically find Waldo using Mathematica: http://stackoverflow.com/questions/8479058/how-do-i-find-wal...

Re: Here's Waldo

#9

Post by praptak » Wed, Nov 20, 2013, 4:13 PM UTC

I remember a mathematician's advice about playing lottery (other than "don't play it") - pick numbers near the edges of the coupon, as people avoid those places. This way you minimize the chance of having to split the jackpot with someone else (and yeah "don't play it" still holds :-) )

Re: Here's Waldo

#10

Post by knoepfle » Wed, Nov 20, 2013, 4:14 PM UTC

This is a silly example of ex post evaluation of an ex post model. You need to have a holdout sample.

It's made more silly by the fact that they use the universe of Waldo books, so their "strategy" is essentially just "here's approximately the answer".