-
From DAVE BROOKS, Nashua (NH) Telegraph: I don't want to get too mathematical here, but John Maggs is very wrong in his note when he says a polling advantage which is less than the margin of error is somehow still an advantage. It's not, and to imply otherwise is to get the story just as wrong as if you'd misspelled a name.
Reporters are correct to use the dull term "statistical dead heat" or its equivalent if, say, a poll of 500 people shows Bush leading Kerry 48 percent to 46 percent, with a 4 percentage point margin of error. This example does not show that "it is far more likely that Bush is ahead," as Maggs thinks, because *any* result within the margin of error, including a Kerry win, is *equally* likely.
Uh, in a word, no.