Richard Florida has put some of his data to use to answer an important question: what are the best cities in the united States for trick or treating on Halloween?

According to National Retail Federation projections, Americans will spend $6.86 billion on Halloween this year, up from $3.3 billion in 2005 when a lot fewer of us were out of work. But even as Halloween edges up on Christmas as a shopping opportunity, the trick-or-treating experience is a lot less universal than it was. In some towns, you see hardly any unsupervised trick-or-treaters after dark; in other places—Brooklyn Heights or my neighborhood in Toronto leap to mind—there are more kids than you can imagine.

Herewith the 2011 edition of the Trick-or-Treater Index developed with the ever-able number-crunching of my Martin Prosperity Institute colleague, Charlotta Mellander. The 2011 Index is based on the following five metrics: the share of children aged 5 to 14; median household income (figuring the haul will be better in more affluent metros), population density, walkability (measured as the percentage of people who walk or bike to work) and creative spirit (which we measured as the percentage of artists, designers, and other cultural creatives). The data are from the American Community Survey and cover all U.S. metro areas, both their cores and suburbs…

As for the top ranking metros, Bridgeport-Stamford-Norwalk, Connecticut, comes in first again this year. Greater New York has moved up to second place, followed by Chicago, greater Washington, D.C., and the twin cities of Minneapolis-St. Paul. Los Angeles, last year’s runner-up, has dropped to 7th place. Big metros dominate the top spots, but Lancaster, Pennsylvania, has moved all the way up from 16th last year to 6th on our 2011 rankings. And college towns like Ann Arbor, Michigan, Boulder, Colorado, and New Haven, Connecticut, also rank among the top 25.

This reminds me of another recent odd use of data that ranked the luckiest cities. So people with more money, who are more creative, and live in more walkable areas necessarily give more or better candy? Might they also be the people who are more likely to give substitutes to candy? Could this also be related to health measures, like obesity or life expectancy? This seems like opportunistic, atheoretical data mining meant to get a few page clicks (like me).

And since there are probably few people who would go to a whole new metropolitan area just to get candy, wouldn’t this be a better analysis if it was at a zip code, community, or census block level?