I wonder how much this is a measure of the diligence of various inspectors versus a measure of roaches being present. Something like this could be highly influenced by a sampling bias...

Nice idea but looks pretty random .. perhaps too little data ?

The copy doesn't make it clear enough, but we're actually doing our best to adjust for small samples with a little empirical Bayesian magic. As the number of samples (inspections) goes down, the result is closer to the mean for the whole city.

I thought the same thing... It needs a finer scale, and maybe some adjustment for density of restaurants, since that probably influences the frequency of health inspector calls.

It looks like there's a nice gradient along Long Island, though. :)

Doesn't this really track where the city health inspectors have been?

Yeah, would be interesting to see a map colored with overall health inspector visits and see if there's a correspondence.

There's a cooler interface for tracking bedbugs in NYC at http://samizdat.cc/bdbgs/

I'd love to see this animated over a few months.

Yeah, I tried clicking on the archives, hoping I could put something together myself, and the buttons don't work (I'm using Chrome). :(

So the answer is, everywhere. =)

i clicked expecting something like roach marking and tracking hack. Reading the comments it looks though that even marking and tracking of health inspectors would already be a start.