A Note About Polling

Newsweek's Sharon Begley has some indispensable reminders about polling methods as you peruse the onslaught of numbers in the coming weeks.

Her first tip: Likely voters. Polls that count "likely" voters, rather than "registered" voters are usually more accurate. But Begley argues, maybe not this year, because if it's a historic, transformative turnout, "likely," won't be reliable:

"Pollsters determine who is likely to cast a ballot by asking questions such as whether they voted 2004, are following the campaign and plan to vote . . . The bottom 40 percent don't count as "likely." This can produce inaccurate results in many ways. For one thing, if 70 percent, rather than 60 percent of voters cast a ballot this time, pollsters may be ignoring (a considerable) percent of their sample. For another, because the millions of newly registered voters score zero on the "did you vote last time?" question, they might not count as likely. But if they do turn out on Nov. 4, polls are failing to count a group that could determine the outcome in several states."

Also, on cell phones. It's estimated that Cell-only voters now make up 13 percent of the population. When ABC News called cell numbers, the impact was "negligible," but the Pew Research Center finds that Obama gains about 2 to 3 points if cell-phone-only voters are included.