The Absolute and Egregious Malpractice of the Quinnipiac Poll

Their headline:

April 21, 2010 – Obama’s Bounce Goes Flat, Quinnipiac University National Poll Finds; But Voters Confident He Will Pick Good Judge

The first paragraph of the press release:

President Barack Obama’s job approval, which bounced slightly to a 45 – 46 percent split March 25 in the wake of his health care victory, has flattened out at 44 – 46 percent, his lowest approval rating since his inauguration, according to a Quinnipiac University national poll released today.

Let’s be clear: I have nothing against the Quinnipiac Poll in principle. As far as I know, their polls are conducted soundly; they once kindly sent me some cross-tabs.

But their description of this “finding” is what the subject line says it is: malpractice. Here is the percent approving of Obama in each of their polls since January:

January 13: 45
February 11: 45
March 25 (pre-vote): 46
March 25 (post-vote: 45
April 21: 44

There is no “bounce. ” There is no “flattening out.” There is nothing but a big fat flat line. It doesn’t make for a good press release, but that’s the truth.

What’s mystifying is that, later in the release, Peter Brown of Quinnipiac says:

The White House had predicted passage of the health care overhaul would boost his fortunes, but that has not been the case…

I don’t know what the White House did or didn’t predict, but this statement is correct that there has been no boost. It is completely supported by the flat line in Obama approval. So why not simply make that point without conjuring up some mythical movement in the numbers?

Quinnipiac should retract its press release and issue a statement correcting its error.

The mistakes in the interpretation of poll results—including and even especially by the sponsors of those polls—are far greater than mistakes in the execution of the polls themselves.

One Response to The Absolute and Egregious Malpractice of the Quinnipiac Poll

  1. William Ockham April 23, 2010 at 5:41 pm #

    Is it any worse than this article?

    Given that the poll has +-2 point margin of error, the results given for the quarterly polls are consistent with stable values for all the partisan-leanings except “Lean Republican”. Why do pollsters always treat “gap” measurements has so significant when they clearly amplify the “noise” in polling data?