Wednesday, November 10, 2004

My Problem with Zogby
Biur Chametz (actually blogger Zman Biur) kindly forwarded me John Zogby's mea culpa for blowing this election. Clearly Biur read my earlier post - since partially retracted - accusing Zogby of being a Democratic partisan. That is one of the issues Zogby addresses:
For those of you so kind to point out that my brother is on the executive committee of the Democratic National Committee, you need to understand that he was an active Democrat when my polling showed George Pataki defeating Mario Cuomo in 1994, when I had Bob Dole doing much better than other polls suggested against Bill Clinton in 1996, and when I polled for the National Republican Congressional Committee in 1998. It seems I spent lots of my time back then denying I was a Republican.

I find that reasonably convincing. He addressed another perception too:
And to those who note my Arab heritage and again my relationship with my brother, please read the Democratic National Committee position on the Middle East. It offered me no comfort.

Here I'm less convinced. Why? Because in the past he's done polls in the Arab world seemingly for the sole purpose of giving Shibley Telhami data, so Telhami can claim that the biggest problem facing the United States in the Middle East is its support of Israel. As Joseph Farah points out about these polls:
As pointed out by James Taranto of the Wall Street Journal, using Freedom House's annual survey of freedom in the world as a guide, only Kuwait among the nations surveyed is ranked even "partly free." Egypt, Lebanon, which is occupied by an Arab neighbor, and the Emirates are all ranked "not free." Saudi Arabia scores even lower in political rights and civil rights.

This context raises three questions unaddressed by Telhami and Zogby:

Are public opinion poll respondents free to express themselves in these countries?

To what extent does the leadership of these countries shape the public opinion through control of the media, the schools and other cultural institutions?

What difference does public opinion make in an authoritarian or totalitarian country?
Often people ask me if Arab public opinion – both in the Arab world and among Arabs living in the West – is as solidly anti-Israel as it appears in international media portrayals. The question is one that cannot be answered with any degree of assurance as Arab leaders do not submit themselves to the will of the people.

Clearly in police states like those named above, the public is not free to express opinions that might run counter to the official government line. Therefore, any such survey of public opinion will not be scientifically accurate or valid.

Secondly, these regimes devote a significant amount of resources to propaganda. And, despite the Internet, satellite television and short-wave radio, unofficial, alternative information sources are at a premium.

Lastly, since meaningful free elections are largely unknown in the Arab world, public opinion is worth about as much as this Zogby poll, which is to say nothing.
Zogby (and Telhami) know all this but they go through the motions of taking a poll to prove their point. They know what the answers will be before they start. They just want to give their own views "scientific" credibility. What they're doing with these polls is dishonest.

And even if I find Zogby's protestation of impartiality convincing, that doesn't necessarily clear him of bad faith. RealClearPolitics noted:
6) Zogby
Failed to Project Winner: 27.3% | Average Error = 3.6

As we all know, Zogby had been on record for months saying that Kerry was going to win this race. Despite his final tracking poll that put Bush ahead by one point nationally, Zogby's polling at the state level reflected his belief that Kerry was going to be the beneficiary of huge turnout - especially among the youth vote. The result is that Zogby missed three of the eleven states he polled in (FL, IA, and NM), had a relatively high error rate across the board (3.8%), and his numbers generally skewed in favor of John Kerry.

Adding insult to injury, Zogby's bizarre election day antics calling for "surprises" in Colorado and Virginia and a decisive 311 electoral vote victory for Kerry suggest he was relying on (not to mention taken in by) the badly skewed early exit poll data.

Let's be honest: Zogby's conduct this year bordered on outrageous. No other independent pollster was out making public predictions of a John Kerry or George W. Bush victory months before hand. And no other pollster decided to wait until 5:30pm Eastern time on election day to post their final numbers.

Yesterday however, RealClearPolitics quotes from Zogby's apology and seems to have softened its stand a little.
So the question is, what purpose is served (other than perhaps self aggrandizement) by polling on election day and releasing "final" numbers at 5:30pm Eastern when the polls in many states on the East Coast start closing shortly thereafter? I'm not sure Zogby has fully explained that one.

NOTE:I found RealClearPolitics ranking of the battleground pollsters rather interesting. Numbers 2 and 3 were Rasmussen and Survey USA. Survey USA as RCP notes:
Some people have questioned methodology and reliability of SurveyUSA's polls.
(Survey USA had a poll in the early fall showing Maryland tied.) Indeed, The Washington Post reported in "In Such a Tight Race, Pollster Sees a Profit" that both firms are criticized for their automatic polling. Rasmussen is criticized because he just polls for profit. *Gasp* (Why that makes him less reliable than someone polling for a political party is not explained by the article.) And Zogby, who was a lot less reliable than Rasmussen and Survey USA this year got to host his own Live Online chat session at the Washington Post right before the election. Go figure.

No comments: