Both US presidential campaigns are banking a lot on "getting out the vote" -- pumping money into door-to-door campaigns and phone banks aimed at making sure their base, and many new voters, head to the polls. But how useful will this really be?

Two Yale professors did a fascinating study to figure out how much, precisely, it costs to rustle up a vote. They analyzed data from state and local elections in a intriguing way: They compared the turnout of those who had received a get-out-the-vote appeal -- a phone call, a door visit, etc. -- versus those who didn't.

The result? Door-to-door visits managed to bring out one additional vote per 14 people visited, which works out to a price of about $7 and $19 for that vote. Leaflets created only one new vote per 66 votes, for a cost-per-vote of about $14 to $42. Telephone calling was incredibly ineffective, costing anywhere from $45 to $200 for a vote.

But here's where things get interesting. The two parties say they're spending about $200 million on get-out-the-vote techniques this year. The professors figure that on average, each vote costs $50 to get out. That means, as the New York Times reports ...

... that the tremendous mobilization efforts under way will increase turnout by about four million people, or 2 percent of eligible voters. Although unseasonable weather or other unforeseen events could throw this forecast off - and the expected close contest should arouse heightened participation - this year's turnout is likely to fall between 2000's rate of 54 percent of eligible voters and 1992's rate of 61 percent. This moderate forecast stands in contrast to the image of unprecedented voting implied by reports of record numbers of people registering in many states.

Maybe we won't see as many new voters as we'd hoped to.