October 23, 2008

AP Poll Report: A 3.5-Point MOE Means a 14-Point Spread

Filed under: MSM Biz/Other Ignorance,Taxes & Government — Tom @ 2:49 pm

UPDATE, 9:45 p.m.: Commenters are saying AP is correct in its interpretation.

I don’t think so, because if the commenters are right, newspapers would routinely write up, say, a 6-point lead by McCain or Obama as being “within the 3.5-point margin of error.” That is, the one trailing could be 3.5 points higher, and the one leading could be 3.5 points lower, meaning that the person reported as leading could conceivably be trailing. But I don’t think I’ve ever seen it reported that way, because, as I understand it, the margin of error is 3.5% for the entire poll, not 3.5% for each poll component.


(original post)

Associated Press lead reporter Liz Sidoti, other contributors (AP Director of Surveys Trevor Tompson, AP News Survey Specialist Dennis Junius and AP writer Alan Fram), and the wire service’s supposedly vaunted editors apparently don’t understand what a polling margin of error is.

In a Wednesday story I found in four different places (CBS News, AP-Google, Breitbart, Yahoo! News), Sidoti et al let a paragraph stand claiming that a 3.5% margin of error in the poll results they were reporting meant that the real results could vary by as many as 14 points.

Here are the key paragraphs found in each story (bold is mine):

The presidential race tightened after the final debate, with John McCain gaining among whites and people earning less than $50,000, according to an Associated Press-GfK poll that shows McCain and Barack Obama essentially running even among likely voters in the election homestretch.

The poll, which found Obama at 44 percent and McCain at 43 percent, supports what some Republicans and Democrats privately have said in recent days: that the race narrowed after the third debate as GOP-leaning voters drifted home to their party and McCain’s “Joe the plumber” analogy struck a chord.

….. Polls are snapshots of highly fluid campaigns. In this case, there is a margin of error of plus or minus 3.5 percentage points; that means Obama could be ahead by as many as 8 points or down by as many as 6. There are many reasons why polls differ, including methods of estimating likely voters and the wording of questions.

Uh, no. A 3.5% margin of error means Obama could be ahead by as many as 4.5 points or down by as many as 2.5. That’s a seven-point spread.

Zheesh. If I didn’t know better, I would be thinking, with their apparent failure to grasp basic math, that Sidoti et al are auditioning to join Martin Crutsinger and Jeannine Aversa as AP business reporters.

Cross-posted at NewsBusters.org.



  1. I don’t think you quite have it right either.

    It’s not hard to see how they arrived at those numbers. A 3.5-point error means that Obama could range anywhere between 40.5-47.5, while McCain could range from 39.5-46.5. Taking the extremes on both ends puts Obama between 6 points down and 8 points up.

    Now that’s not right; the margin of error on the difference doesn’t double. But is it the same as the MOE? According to this guide, for instance, it’s not: the MOE of the difference is larger than the MOE of the individual numbers. They recommend a multipler of 1.7, which means the difference is about 6 points. Thus Obama could be up by 7 or down by 5.

    Comment by mcg — October 23, 2008 @ 3:18 pm

  2. [...] post by WP-AutoBlog Import var AdBrite_Title_Color = ’0000FF’; var AdBrite_Text_Color = ’000000′; var [...]

    Pingback by AP Poll Report: A 3.5-Point MOE Means a 14-Point Spread — October 23, 2008 @ 3:18 pm

  3. From what they had written, here is how I gather how they got the 14-point spread. The 3.5% MOE is for each candidates percentage meaning that McCain could be from 39.5% to 46.5% and Obama could be anywhere from 40.5% to 47.5%.

    If McCain was at 46.5% and Obama was at 40.5%, then McCain is 6 points up.
    If Obama was at 47.5% and McCain was at 39.5%, then Obama is 8 points up.
    Thus, a possible 14 point difference.

    I was under the impression that the margin of error is what they were saying. Each candidate could be 3.5% +/- of the reported number. I have seen similar graphs in actual polls that would agree with this.

    What you seem to be saying is the that MOE is to be applied to the total difference between the two. Are you sure that is correct?

    Comment by Ben — October 23, 2008 @ 3:18 pm

  4. Actually, in this case, the AP is right. The MOE is applied to each candidate individually, so of Obama is at 44%, the MOE means he could be as high as 47.5 or as low as 40.5, and McCain, at 43%, can be as high as 46.5 or as low as 39.5. These figures are independent, so if McCain is actually a point higher, it does not mean that Obama is necessarily a point lower.

    Comment by davorider — October 23, 2008 @ 3:39 pm

  5. Normally I’d nod in agreement with your post on margin of error, but I just read another blogger I normally agree with who in this case agrees with the (gack) AP on this. I don’t know enough to referee this issue, but you might want to check each other’s rationale and conclusions. The other blog is at http://engram-backtalk.blogspot.com/ and the post I’m referring to is today’s. I’m also posting this same comment over there, with your URL, in hopes of a fruitful discussion & resolution. Thanks for the good work you both do, it’s nice to have a few outposts of sanity and reason to rely on for facts.

    Comment by David Macys — October 23, 2008 @ 4:25 pm

  6. Media members are so stupid.


    Comment by Gordon — October 23, 2008 @ 4:38 pm

RSS feed for comments on this post.

Sorry, the comment form is closed at this time.