A day after Felix Salmon notes the problem of taking economic studies at face value, we have an excellent example of why deeper analysis is critical. Veronique de Rugy did a study [PDF] of stimulus funding recipients and concluded, after some analysis, "in total, Democratic districts received 73 percent of the total stimulus funds awarded and Republican districts received 27 percent of the total amount awarded." So was the stimulus a big political ploy to funnel money to the Democrats?
No, it was not. Nate Silver finds a glaring flaw in the study: de Rugy did not control for congressional districts that included state capitols. When stimulus funds go to state agencies -- as much of the stimulus did; a big chunk of it falls into the category "aid to states" -- the money is attributed to the congressional district that includes the state capitol. But these benefits were obviously dispersed around the states, as local authorities saw fit. Silver finds that of the top 20 districts receiving funds, only one isn't a state capital. The trend continues down the line.
There are 78 congressional districts that contain all, or part, of a state's capital city. Collectively, they received $118 billion in the fourth quarter. The 357 districts that are not home to a state capital received only $48 billion, however. On a per-district basis, the districts with state capitals received 11 times more funding.
Silver suggests the reason these state capitols have Democratic representatives is simple: They are more urban, have more government employees, and their residents tend to have higher education levels, all factors that correlate with electing Democrats. He suggests that de Rugy redo her study controlling for the state capitol issue and for unemployment; if she does that and still finds a partisan correlation, he'll buy her and three colleagues lunch. Now that's putting your money where your mouth is!*
-- Tim Fernholz
