[Polling] Disclosure Project: Results from Iowa

Pollster.com ^ | 12/12/07 | Mark Blumenthal

[Route66]

It is time -- actually long past time -- to summarize the returns from the Pollster.com "Disclosure Project." Back in September I declared my intent to request disclosure of key methodological details from pollsters doing surveys in Iowa, New Hampshire, South Carolina and the nation as a whole. I sent off the first batch of requests to the Iowa pollsters, and then began a long slog, delayed both by other activity and, frankly, by a surprising degree of resistance from far too many pollsters. The result is that now, nearly three months later, I can report results from Iowa only.

I should note that many organizations (particularly ABC/Washington Post, CBS/New York Times, Los Angeles Times/Bloomberg, the Pew Research Center, Rasmussen Reports and Time/SRBI) either put much of the information into the public domain or responded within days (or hours) to my requests. With others, however, the responses were slower, incomplete or both. A few asked for more time or assured me that responses were imminent, yet ultimately never responded despite repeated requests. Sadly, such is the state of disclosure in my profession, even upon request.

So while the results described below are far from a complete review of all the polls in Iowa, they do tell a very clear story: No two Iowa pollsters select "likely caucus goers" in the same way. Moreover, each pollster has a unique conception -- sometimes radically unique -- of the likely electorate.

This post is a bit long, so it continues after the jump...

[Route66]

Though the author is a former Democrat pollster, there is nothing but information in this report which examines major pollster's Iowa polling methods in great detail. While this information will probably be of more interest to the hard core political junkies who like to pour over the kind of specifics included in this report, I hope most will at least scroll through it and skim it as it helps to put the voodoo called "polling" into perspective.

[eureka!]

Will do so later. Thanks for the post...

[Brad from Tennessee]

[Finally, most of the Iowa pollsters use live interviewers, but two — Rasmussen Reports and Public Policy Polling (PPP) — use the “interactive voice response” (IVR) method that calls with a recorded message that asks respondents to answer questions by pressing on their touch tone phones.]

This is why I tend to trust Rasmussen more than the others. When you have live interviewers there is a chance they will inject bias into the results. Who would have faith in a voting system where an employee from an elections office called each registered voter on election day and asked the voter to vote verbally over the phone?

Human bias apparently skewed the results of the National Election Pool on election day 2004 giving a false lead to Kerry. The skewed data was leaked early by a New York Times employee which motivated the TV networks to release it, likely costing Bush some votes. I don’t know who the pollsters hire as interviewers but some could be covert partisans.

[Route66]

I was not aware of the interactive voice response system used by Rasmussen until I read this report. I do agree that we probably see a large human bias factor in these polls, and clearly the methodology varies widely.

While poll results have always been questionable, I think they are destined to become more and more so. All indications are that pollsters are scrambling to find ways to remain relevant as more and voters become harder and harder to reach. Cell phones, call screening, and even just unwillingness to talk to a pollster or respond to a request is making it increasingly difficult for them to even pretend that they are capturing meaningful voter opinion prior to the election.

[Kevmo]

bmflr

.

.

.

.

According to Intrade, the winner of the December 12th GOP debate was... Duncan Hunter.
http://www.freerepublic.com/focus/f-news/1938773/posts

[Brad from Tennessee]

Yeah, I agree. The people who should be polled don’t want to be polled. The people who want to be polled may not be representative.

Polls are important to the news media because they can do many different stories—depending on how many questions—on one poll detailing the results and then the demographic differences in answers. I’ve notice Fox News will do one poll and then work the results into all their news programing for weeks. This fills air time or newspaper columns and it has high news value, whether the results are accurate or not.