Are weekend polling numbers really skewed?

Answers to your questions about the news.
Nov. 2 2006 6:16 PM

Saturday-Night Democrats

Are weekend polling numbers really skewed?

Download the MP3 audio version of this story here, or sign up for The Explainer's free daily podcast on iTunes.

Democrat Jim Webb has taken the lead over Sen. George Allen of Virginia, according to a pre-election poll released on Tuesday. Allen's polling consultant rejected the latest results: "Any survey conducted Fridays and Saturdays, everybody knows they're skewed toward Democrats." Similar claims have surfaced in news reports about polling data since at least as far back as 2000. What's so suspicious about weekend polls?

It's harder to get people on the phone on Friday and Saturday nights. Pollsters try to collect a fair sample of potential voters by dialing phone numbers selected at random. But the people who are most likely to answer their phones may not be representative of all Americans. For example, the poll samples could have a bias toward the older people who are more likely to be at home on any given night.

Daniel Engber Daniel Engber

Daniel Engber is a columnist for Slate

Advertisement

Pollsters don't want to skip anyone with an active social life, so they try to call back when people don't pick up the first time. A typical opinion poll might be conducted over five school nights, from Sunday to Thursday, with up to 10 calls made to each number. (They keep calling—during the day and at night—until they get through.)

As an election approaches, pollsters try to gather data more quickly. They might run a two-day poll instead of a five-day poll, and they might conduct it over weekend nights instead of during the week. (Some magazines, like Newsweek, time their polls to coincide with a weekend publication deadline.) In theory, younger people are more likely to be out on Friday and Saturday nights, which would make them less likely to be included in the sample.

What would that mean for the results of a given study? Weekend polling would skew the sample away from the young and active types and toward the oldsters who sit at home. That doesn't mean the weekend poll gives more credence to the elderly vote. It might mean just the opposite: Pollsters can correct for having too many old people by giving extra weight to everyone else. In that case, the opinions of the few young people who are in the sample would count extra.

That means one possible source of bias in a weekend poll comes from the young voters who happen to be staying in on Friday and Saturday nights. If they happened to vote more Democratic than their more socially active cohorts, the poll will skew toward the Democrats.

While it's a common claim that weekend polls favor the Democrats, there isn't much hard evidence to support that idea. One of the best studies of this question was conducted by two polling experts at ABC News. Gary Langer and Daniel Merkle looked at the data from ABC's tracking polls for the last three presidential elections. They compared results from people reached on Sunday through Thursday with those reached on Friday and Saturday and found no difference. Among the Sunday-to-Thursday people polled in 2004, 49 percent supported Bush and 46 percent supported Kerry. Polls of the stay-at-home, Friday-to-Saturday crowd produced similar numbers—48 and 46.

Got a question about today's news? Ask the Explainer.

Explainer thanks Scott Keeter of the Pew Research Center for the People and the Press and Mark Blumenthal of Pollster.com. Thanks also to reader Rob Formica for asking the question.

  Slate Plus
Slate Picks
Dec. 19 2014 4:15 PM What Happened at Slate This Week? Staff writer Lily Hay Newman shares what stories intrigued her at the magazine this week.