California Results Expose Bad Polling

03/28/2008 02:45 am ET | Updated May 25, 2011

In the wake of Hillary Clinton's decisive victory Tuesday in the California Primary, one pre-election poll from C-SPAN/Zogby/Reuters that showed Barack Obama up by 13 points in the Golden State is getting a lot attention Wednesday morning.

On the morning of Super Tuesday, Zogby released its final tracking poll, showing Obama at 49 percent and Clinton at 36 percent, with 9 percent undecided, with a margin of error of 3 percent.

Pollster John Zogby said this as his poll was released:

In California, we have Obama polling into a 13-point lead. Monday was another big single day of polling for him there. What has happened here is that in addition to building leads among almost every part of his base of support, he has dramatically cut into Clinton's lead among Hispanic voters.

According to the Los Angeles Times on Wednesday, with 97 percent of the precincts reporting, Clinton won the Golden State with 51 percent of the vote, compared to Obama's 42 percent.

Andrew Sullivan called Zogby "Another Big Loser." Matthew Yglesias wrote about filtering out "the most-exuberant Zogby-filled dreams." Even the Brits are pointing out the error.

On Tuesday, in a post entitled "Somebody's Gonna Be Wrong," Pollster.com's Mark Blumenthal wrote about Zogby's lack of transparency about his methodology.

In his post, Blumenthal compared Zogby's results those of another pre-California poll from SurveyUSA that showed wildly different results.

Blumenthal writes:

If ever there was a case for better methodological disclosure by pollsters, this is it. If one poll, conducted entirely over the last 48 hours, shows a candidate leading by 10 points, while another conducted in the same state over the same time period, shows a another candidate leading by 13, and we cannot see enough of the details of how the polls were done to at least explain why they differ, why should we trust what any of these polls tells us?

On Wednesday, Zogby released a post-Super Tuesday analysis that includes this note about California:

Some of you may have noticed our pre-election polling differed from the actual results. It appears that we underestimated Hispanic turnout and overestimated the importance of younger Hispanic voters. We also overestimated turnout among African-American voters. Those of you who have been following our work know that we have gotten 13 out of 17 races right this year, and so many others over the years. This does happen.

John Zogby is a Huffington Post blogger.

Suggest a correction