Pollster John Zogby Hangs Up on Hugh Hewitt

Hugh Hewitt interviewed John Zogby about his much publicized–and much derided–poll of the attitudes of American troops in Iraq. Hewitt demolished the survey methodology and Zogby hung up in anger.

In his roundup, Hewitt concludes that Zogby is “a shameless self-promoting pretend pollster and that “You can trust John Zogby as much as this poll. Which means, not at all.” He points to Chris Mooney’s February 2003 piece in the liberal The American Prospect, “John Zogby’s Creative Polls,” as further evidence.

Radio Blogger has a full transcript and audio of the interview.

Mark Blumenthal has numerous posts on the poll. This one, in particular, sheds a lot of light on the methodology problems. It is also quite fair to Zogby, noting the incredible difficulty of polling troops in a combat zone and why some of the “creativity” might have been necessary.

Full diclosure: My wife is a VP at Public Opinion Strategies, which does survey research. They are not likely in direct competition with Zogby, however, since POS’ political clients are exclusively Republican. That said, while I have frequently defended Zogby’s work in the past (here, most recently)–and once considered him the best in the business based on a couple of noteworthy dead-on predictions–I am increasingly troubled that he seems to put out polls deliberately aimed at getting results favorable to his clients. That’s not what legitimate pollsters do.

Update: Blumenthal adds another post on this subject,

The survey did not involve a “random probability” sample of all American troops serving in Iraq.

The principle of random sampling is what makes a poll “scientific.” To meet that standard in this case, every member of the U.S. armed services in Iraq should have had some chance of being selected (or to put it statistical terms, the probability of selection had to be either equal or known for every member of the population). As I wrote yesterday, the constraints Zogby faced in gaining access to troops at “undisclosed locations throughout Iraq” made random selection of those locations impossible.

It is also unclear — both from information in the public domain and from what Zogby shared with me in confidence — whether his selection procedures amounted to random probability sampling even at the undisclosed locations.

Much more at the link. Suffice it to say this isn’t a “poll” at all in any meaningful sense.
________

Related:

I have mentioned Zogby’s polls dozens of times. Search the archives for more.

FILED UNDER: Military Affairs, Public Opinion Polls, , , , , ,
James Joyner
About James Joyner
James Joyner is Professor and Department Head of Security Studies at Marine Corps University's Command and Staff College. He's a former Army officer and Desert Storm veteran. Views expressed here are his own. Follow James on Twitter @DrJJoyner.

Comments

  1. Can Zogby declare fatwahs?

  2. Anderson says:

    Useful links, thanks. One would certainly like to believe that a large majority of our troops do NOT think that Saddam was involved in 9/11.

    That said, I’ve seen interviews with troops where they expressed just that view. Statistically meaningless, but enough to make me wish for a decent poll.

  3. Steve Verdon says:

    I’ve been ignoring Zogby ever since he hosted one of the stupidest and most slanted articles that proved, PROVED that Kerry won Florida. From that point on I figured he was nothing more than a partisan hack.

  4. Anderson says:

    Hm. It’s disappointing to compare OTB’s post with Kevin Drum’s:

    here’s Hugh Hewitt doing his usual ambush interview schtick in an interview with Zogby on Thursday:

    HH: [After lengthy hectoring about the poll’s methodology, which Zogby had already said he would only discuss off the record for security reasons.] Why were no demographics released?

    JZ: All the demographics were indeed released, Hugh.

    ….HH: John, I’ve got your entire thing here. You have not released the demographics.

    JZ: You are clearly uninformed.

    HH: You have not released the demographics.

    JZ: (click)

    HH: You have not…he hung up. He hung up. That’s John Zogby, not a pollster.

    Guess what? Zogby had indeed released the demographics. Here is Hugh’s excuse for not knowing this:

    In fairness, his office had sent the demographics info (which had not been released yesterday and still isn’t on the web) but did so in a PDF file that we were only able to read after downloading a new version of Adobe. When we were talking, we didn’t have the demographics. Had Zogby simply told me the demographics were now out after previously being withheld, that would have been fine.

    Could Hugh possibly be any more pathetic? Zogby did send a copy of the demographics directly to Hugh’s office but had the gall to do so in the latest version of Adobe. Hugh’s crack staff was apparently stymied by this, and Hugh thinks that Zogby should have performed some mind reading to figure this out. Telling him that “all the demographics were indeed released” wasn’t enough. Instead, he should have told Hugh that “the demographics were now out after previously being withheld.” Right.

    The entire right wing choir, of course, is now crowing about how Zogby was too gutless to answer Hugh’s questions and hung up on him.

    Present company included?

    N.b. that Drum remains agnostic on the merits of Zogby’s poll. But unfortunately for me, I let my axiomatic contempt for Hewitt be outweighed by my respect for OTB’s take on events. Oops.

    Also, last time I checked, Adobe was free, & it was pretty much impossible to get through 24 hours without being invited to download same.

  5. James Joyner says:

    Anderson,

    This is probably a case where blogging formatting and practices is not best for the discussion. I led with the Hewitt interview because that’s where the trail started rather than the Blumenthal stuff and the good cites (esp. Mooney) Hewitt provides.

    Hewitt gets around the point that Blumenthal makes both much better and in a more balanced way: That Zogby’s poll on military attitudes employed methodologies that aren’t legit.

    The Mooney article–complaining that Zogby is a whore who lets right wing groups buy his reputation, ironically enough–explains that in some good detail as well.

  6. Craig says:

    I would have hung up on Hewitt, too, but I think Blumenthal makes some good points.