Margin of Error Coverage

Margin of Error will help readers understand polls in the news and pay particular attention to survey research conducted on North Carolina political races.

Bloomberg's impact on presidential race in doubt

Former New York Mayor Michael Bloomberg's potential run as an independent may not make a big impact in the presidential race.

Diagnosing the Carson surge

A recent Elon University Poll shows Dr. Ben Carson surging past Republican Donald Trump among North Carolina Republican primary voters. Do the numbers reflect a real change in fortunes or differences in how surveys are conducted.

Trumped up poll numbers for Carson

Recent news reports say Ben Carson has pulled ahead of Donald Trump in the GOP primary. But that's far from a consensus among those polling the race.

Marriage survey story leaves scholar dissatisfied

Are self-identified Republicans happier than Democrats about their marriages? Yes, according to a recent study that was reported in the New York Times blog, The Upshot. Not only is the conclusion NOT supported by the survey data, but it also is improperly magnified by the blaring media headline.

Trump(ed): Reading the fine print

Would Donald Trump really beat Hillary Clinton next year? A look inside the polls raises questions.

Think of 'Deez Nuts' as a protest vote

"Deez Nuts" isn't going to win the presidential election, but how he's polling tells you something about what voters are thinking right now.

Why polls were wrong about NC Senate race

Democrats did worse than polls predicted in nearly every state this election cycle.

Poll of polls: Hagan likely to win re-election

Data from a number of polls suggests U.S. Sen. Kay Hagan will keep her seat once the votes are tallied Tuesday night.

Data on non-citizen voters offers questions, not answers

Despite claims, national polling data provides little evidence that non-citizens are casting ballots.

What NC's polls tell us on gay marriage

Polling shows that attitudes in North Carolina and across the country are shifting on gay marriage.

Why are we overestimating the Ebola threat?

Polls show a quarter of Americans are concerned about the threat of Ebola, despite bigger risks of exposure to other more mundane threats. Studies show we overestimate "dreadful" risks.

Voter ID support depends on question wording

Republicans are touting Voter ID legislation on the campaign trail. But voters' enthusiasm for the legislation varies depending on how the question is asked.

Recent polls may overstate voter concerns about Senate control

Voters sampled in recent surveys say who will control of Congress influences their votes, but other polls suggest most don't know which party controls the U.S. Senate.

What's your attitude toward not having an opinion?

Survey researchers ask Americans about their opinions on a variety of topics every day. But sometimes, what seems like a firm data reflects squishy opinions.

Be skeptical of Rasmussen's recent poll result

The most recent NC Senate poll by Rasmussen has Tillis leading Hagan, 45 percent to 40 percent. I have significant doubts about the validity of this poll, and you should too.

Trust an Internet poll? The New York Times did

The poll is controversial because of how it was conducted, and the decision by The New York Times to stand behind it. YouGov conducts its surveys online. Completely.

Proceed with caution on early poll results

Pollsters may need to change how they handle poll numbers for third-party candidates if they want to accurately measure voter attitudes in North Carolina's U.S. Senate race.

Libertarian voters could swing close Senate race

Although polls show Sean Haugh, the Libertarian candidate for U.S. Senate, has about 10 percent support, most libertarian-minded voters will likely vote for Democratic Sen. Kay Hagan or Republican challenger Thom Tillis in November.

Early poll may reflect voter discontent

The most recent Public Policy Polling (PPP) survey has Kay Hagan leading Thom Tillis, 39 percent to 34 percent in the North Carolina Senate race. I saw two things about the results that are worth discussing.

Why did pollsters miss Cantor's slide?

Why did Cantor lose? Perhaps more germane to this blog, how did his pollsters miss the possibility that he would?

On right, left, polling data doesn't prop up partisan conclusions

The conclusions drawn from a pair of recent polls on attitudes toward teacher pay increases show the perils of how question order and wording can affect answers and the conclusions pollsters will draw.

Do people lie to pollsters?

When asked, people tend to agree with socially acceptable positions and disagree with those they deem less desirable, even if that means lying about true beliefs.

Do more people believe in ghosts than racism?

Former NBA great Kareem Abdul-Jabbar claims more white people believe in ghosts than racism. Polling data suggests that's not quite right.

Polls show Tillis poised for win despite baffling name ID data

Recent polls seem to show House Speaker Thom Tillis is likely to win the Republican U.S. Senate primary despite wide variances in name recognition.

The good, bad and indifferent in last week's polls

Is there a correlation between social media preferences and political preferences? Is President Obama at a new approval rating low? And why should Democrats be worried about this midterm election?