October 28, 2007 - November 3, 2007
Frank Newport blogs
on the importance of immigration to Democrats and promises
a new Gallup
poll on the presidential race early next week.
Martin blogs comments from Winthrop
University professor Scott Huffman on
the methodology of his recent poll
of South Carolina.
McManus warns of the shaky predictive value of polls "purporting to say
who's winning the race."
Frankovic considers how religious faith will affect this year's
Cillizza parses some recent CNN poll tabulations of perceptions of Hillary
Clinton by gender.
Connolly examines the independents in a recent CBS News poll that expect to
"weigh in on the selection of presidential nominees next year."
Hill considers the political viability of the No Child Left Behind Act.
Mellman reports results of two surveys on "looming crisis of long term care"
(surveys were sponsored by Americans
for Secure Retirement and Genworth
ponders the subgroup shifts in the Democratic presidential race found in the
latest Pew Research Center
Bialik questions (appropriately) another Zogby online survey about another
College senior Mara
Gordon considers the implications of cell-phone only users excluded from
And speaking of cell-phone-only
households: The recent Pew Research Center survey used a combined sample of respondents interviewed by landline phone and
cell-phone. They promise "a
detailed analysis of the landline and cell phone samples in the coming weeks."
A new EMILY'S List survey (release, results) of 900 Democratic women likely primary voters in New Jersey, Georgia, and Arizona (conducted 10/16 through 10/22 by Garin Hart Yang (D) and The Feldman Group (D) ) finds:
- In the combined three-state sample, Sen. Hillary Clinton leads Sen. Barack Obama (52% to 17%) while Edwards trails at 11%. All other candidates receive less than five percent each.
- When prompted with "Hillary Clinton voted to authorize the use of force in Iraq and has refused to apologize for her vote," 10% say it bothers them a great deal, 23% say somewhat, 22% say not very much, and 42% say not at all.
A new Winthrop/ETV statewide survey of likely primary voters in South Carolina (conducted 10/7 through 10/28) finds:
- Among 522 Republicans, former Sen. Fred Thompson (at 17.9%) runs slightly ahead of former Mayor Rudy Giuliani and former Gov. Mitt Romney (both at 16.5%) in a statewide primary; Sen. John McCain trails at 9.2%, former Gov. Mike Huckabee at 5.4%.
- Among 534 Democrats, Sen. Hillary Clinton leads Sen. Barack Obama (33% to 22.7%) in a statewide primary; former Sen. John Edwards trails at 9.6%
- All other candidates receive less than five percent each.
A new Rasmussen Reports automated survey of 500 likely voters in Maryland (conducted 10/24) tests Sen. Hillary Clinton against four Republican presidential candidates and finds:
Clinton 46%, Giuliani 41%
Clinton 47%, McCain 40%
Clinton 49%, Thompson 37%
Clinton 52%, Huckabee 31%
A new AP-Ipsos national survey (story, results) of 1,004 adults (conducted 10/23 through 10/25) finds 37% who prefer the public schools in their community to "provide birth control only to those students who have the consent of their parents;" 30% prefer the schools to provide it "to all students who want it" and 30% prefer the schools to "not provide birth control to any student."
A new Public Policy Polling (D) automated survey (story; results) of 795 likely general election voters in North Carolina (conducted 10/30) finds:
- 45% approve of the way Sen. Elizabeth Dole is handling her job; 36% disapprove.
- Dole leads State Sen. Kay Hagen (46% to 33%) in a statewide general election match-up for U.S. Senate.
Earlier today, Zogby International released what it calls a national
"blind bio" telephone poll of 527 "likely Democratic primary voters" that was
sponsored by AlGore.org, an independent group dedicated to convincing former
Vice President Gore to join the race for president.
Here's the gist of the results from the Zogby release:
When Democratic likely voters were
given brief biographical descriptions of the top three Democratic candidates -
New York Sen. Hillary Clinton, Illinois Sen. Barack Obama, and former North
Carolina Sen. John Edwards - along with the biography of Gore, the former Vice
President won 35% support, while Clinton
won 24%, Obama won 22% and Edwards trailed with 10% support.
The key twist here is that the question provided "brief
biographical descriptions" of candidates, but not the names of the candidates (something less than obvious in the spiffy animated
graphic of the poll results produced by AlGore.org). That practice is not
unheard of, but is typically used by internal campaign polls to test campaign
messages. This sort of test can be a powerful tool, though the results are
very sensitive to the descriptions tested. Were these fair? Fortunately, Zogby
provided the full text:
- Candidate A (Gore) is an experienced candidate from the South who
has been Vice President of the United States
and a US
Senator. This person has won several awards, including an Oscar, a Grammy,
and an Emmy for his documentary about global climate change. This person
has won the Nobel Peace prize and is recognized as an international authority
on foreign policy, energy, the environment, and technology. This candidate
has opposed the Iraq
war from the beginning.
- Candidate B (Clinton) is a candidate with roots in the South and the
Midwest, but is currently a US
Senator from a Northeastern
candidate is well known for work on many domestic issues, including
education, children's issues, and health care. As a US Senator, this candidate voted to
authorize the Iraq
war. This candidate is critical of how the war has been handled by the
- Candidate C (Obama)is a first-term US
Senator from the Midwest who has
emphasized efforts to reach out to include in the political process many
people who are disaffected and unused to involvement in politics. This
candidate brings a fresh face to Washington
and draws huge crowds to campaign rallies. This candidate has opposed the Iraq
war from the beginning.
- Candidate D (Edwards)is a former US Senator from a southern
state. This candidate also has run as a Vice Presidential candidate in the
past. This candidate champions health care and education for the poor, and
has experience running a national political campaign. As a US Senator, this candidate voted to
authorize the Iraq
war but has since said it was wrong to vote for authorization.
Again, keep in mind
that respondents were not told that Candidate A is Gore, Candidate B is Clinton and so on,
although some presumably made that connection on their own. However, one could argue that a few pertinent facts that are missing. The gender and race of the candidates for one. Another is that the "work on domestic issues"
for which Candidate B is "well known for" occurred when she was First Lady of
the United States.
The question also assumes that the only issue differences among the candidates
worth noting are their positions on the Iraq war authorization. Readers
will undoubtedly spot other issues.
What is really unusual
about this survey is that campaign pollsters typically use descriptive paragraphs
like this to test the potential of unknown
candidates with the resources to become much better known (such as Chris Dodd,
Joe Biden, Mike Huckabee or even Ron Paul in Iowa or New Hampshire). Even then,
I know of few campaign pollsters that go to the trouble of testing truly "blind"
bios. Most include the real names to make the test as realistic as possible.
Of course, Hillary
Clinton and Al Gore are two of the best known Democrats in the United States.
Even on a recent CBS
News survey that prompts respondents to say when they "have not heard
enough to have an opinion," 92% of Democratic primary voters can rate Gore and
99% can rate Clinton.
So the need for a "blind bio" serves little obvious purpose here, other than allowing
the pollster to try to conceal the identity of "Candidate B."
A better test might
involve a question like the following:
Suppose Al Gore decided to run for
President. If the race for the Democratic party's nomination in 2008 comes down
to a choice among Hillary Clinton, John Edwards, Al Gore, and Barack Obama, who
would you like to see nominated -- Clinton, Edwards, Gore, Obama, or someone
The good news is,
that question actually appeared at the end of the same recent CBS News survey. And
the results? "Were he to enter the race," as the CBS release puts it,
"Al Gore could be a serious contender," running just five points behind Clinton (an advantage that
is not quite statistically significant assuming the usual 95% confidence
These results suggest
that a Gore candidacy would shake up the race and cut deeply into Clinton's current support. But "reveal" Gore "as
frontrunner," as the AlGore.org poll claims about their poll? No. To do that, Gore might have to
convince Senator Clinton to change her name to "Candidate B."
PS: The filing deadline for the New Hampshire primary is tomorrow. Opportunities to file for primaries in other states will remain open for some time, but as a practical matter, the window of opportunity for an actual Gore candidacy is closing fast.
A new SurveyUSA automated survey of 520 registered voters in Florida (conducted 10/24) tests Sen. Hillary Clinton against six potential Republican candidates for President and finds:
Clinton 49%, McCain 46%
Clinton 49%, Giuliani 45%
Clinton 53%, Thompson 43%
Clinton 55%, Romney 40%
Clinton 55%, Huckabee 39%
Clinton 54%, Paul 36%
A new Pew Research Center national survey (Primary analysis, General Election analysis, Issues analysis, Trends analysis, results) of 2,007 adults (conducted 10/17 through 10/23) finds:
- 30% approve of the way George W. Bush is handling his job as president; 63% disapprove.
- Among 837 registered Democrats and those who lean Democratic; Sen. Hillary Clinton leads Sen. Barack Obama (45% to 24%) in a national primary; former Sen. John Edwards trails at 12%. All other candidates receive less than five percent each.
- Among 648 registered Republicans and those who lean Republican, former Mayor Rudy Giuliani leads Sen. John McCain (31% to 18%) in a national primary; former Sen. Fred Thompson trails at 17%, former Gov. Mitt Romney at 9%, former Gov. Mike Huckabee at 8%. All other candidates receive less than five percent each.
- Among 1,607 registered voters, Sen. Hillary Clinton leads former Mayor Rudy Giuliani (51% to 43%) in a national general election match-up.
Five weeks ago, I kicked off our Disclosure
Project by sending email messages to the pollsters that have released
surveys in Iowa
this year. I asked pollsters to identify their sample frame and their procedure
for selecting likely voters (or in this case, their likely caucus goers) and to
report both the demographics of their likely caucus-goer samples and the
percentage of Iowa
adults that likely caucus-goers represent. A fair number of pollsters replied
within days, others ignored my requests while a handful requested more time or
reported that they were working to provide answers. Now that five weeks have
gone by, a report our progress is more than overdue.
Let me start today by reviewing which pollsters have worked
to comply, and which have not. All together, we sent requests to the seventeen
pollsters that have released Iowa
surveys listed below.
The pollsters divide into four categories. The first are the
media pollsters that are members of the American Association for Public Opinion
Research (AAPOR), plus the academics at the University of Iowa
that put out this week's "Hawkeye" poll. As the AAPOR Code of Professional
Ethics requires disclosure of this sort of information on request, it is
gratifying that most of the AAPOR members on the list cooperated fully within a
few days of our request.** One partial exception is Newsweek. Although they answered all other questions, they have so
far refused multiple requests to provide demographic profile data.
This week's release by the University of Iowa's
Hawkeye poll included a detailed methodology
statement that answered all questions but did not provide a demographic
profile. We have requested the latter, although obviously the Univ. of Iowa
pollsters have had far less time to respond than the others on the list.
Another category includes the two "automated" pollsters -
those that conduct surveys using the "interactive voice response" IVR methodology
that has respondents answer questions by pressing keys on their touch-tone
phones. The two that have been active in Iowa
- Rasmussen Reports and Public Policy Polling (PPP) - have both provided
complete responses. We were especially pleased to see Rasmussen Reports provide
a complete methodology
page for their October survey that walked through answers to all of our
questions, making the need for a formal request unnecessary.
Among other organizations, unfortunately, cooperation has
been more disappointing. I am not particularly surprised at the less than complete
disclosure from the partisan pollsters. The two campaign pollsters that had
released internal surveys campaign surveys - Paul Maslin for the Richardson campaign and Jan
van Lohuizen for the Romney campaign - responded via email and were willing to
describe their sampling procedures generally and provide the text of their
trial heat questions. However, both politely refused to provide demographic
profiles, the specifics of how they defined likely caucus-goers or the percentage
of adults those samples represent. On the other hand, the two pollsters for the
One Campaign poll - Democrat Geoff Garin and Republican John McLaughlin - did
provide complete responses for their Iowa
Perhaps I have a bias (as a former campaign pollster and
long ago employee of Paul Maslin), but I am sympathetic to the reluctance of
campaign pollsters to share these details. The sample design of an internal
campaign poll will provide hints of a campaign's strategy - in this case what
sort of atypical caucus goers the campaign may be targeting. Moreover,
campaigns know that their releases will be met with skepticism, that many will
dismiss their findings as propaganda regardless of what they choose to
disclose. If they refuse to disclose their methodology, we are free to question
or ignore their results. That is the chance they take.
But that rationale is entirely absent for the other independent
"public" polling organizations on our list that have still not responded after
five weeks time. To be fair, the American Research Group (ARG) did answer our
questions about one of its polls in August (just before we kicked off the
formal Disclosure project). ARG's Dick Bennett also emailed two weeks ago to
say they planned to add incidence data and more demographic profile data to
their online reports. Strategic Vision's David Johnson also emailed ten days
ago to say he is "working on" providing a response. I sincerely hope to hear
from both organizations soon, as we all are quite busy, and late is better than
never. However, we have had no for-the-record response - and in most cases, no
response at all -- from Insider Advantage, Research2000, Mason Dixon or Zogby
Unfortunately, the pollsters in this last group, the ones
that have so far not disclosed the information we requested, have conducted the
majority of polls released in Iowa so far this year. The table below, which
adds two columns to the one above, shows that we lack disclosure for three
quarters of the Iowa
conducted this year.
What is particularly disappointing is that organizations
like Mason-Dixon, Research2000 and Zogby International earn their revenue
through contracts with news organizations. When politicians stonewall and
refuse requests for greater transparency, reporters howl. But when the news
organizations that hire these pollsters conduct surveys, they allow their
vendors to use the same rationale to stonewall disclosure as partisan campaign pollsters.
Does that make any sense?
In my next post on this topic, I will review the answers we
have received and talk about where we go from here.
**My own interests disclosed: I currently serve on AAPOR's Executive Council.
A new Courier-Journal Bluegrass statewide survey of 710 likely voters in Kentucky (conducted 10/26 through 10/29) finds Democratic Challenger Steve Beshear leading Gov. Ernie Fletcher (56% to 33%) in a statewide general election match-up for Governor.
A new SurveyUSA automated survey of 500 adults in San Fransisco, Oakland, and San Jose (conducted 10/30 for KPIX-TV) finds:
52% believe in ghosts; 45% do not.
55% think it is possible to "communicate with the afterlife;" 40% do not.
A new AP/Ipsos national survey of 1,013 adults (conducted 10/16 through 10/18) finds:
34% believe in ghosts; 65% do not.
34% believe in UFOs; 63% do not.
Additional results from the AP/Ipsos survey also tested which of the presidential candidates would make the scariest Halloween costume and found 37% saying a Hillary Clinton costume would be the scariest; 14% say a Rudy Giuliani costume would be the scariest.
A new SurveyUSA automated survey of 520 registered voters in Massachusetts (conducted 10/12 through 10/14; released 10/31) and tests Sen. Hillary Clinton against six Republican Presidential candidates in statewide general election match-ups and finds:
Clinton 58%, McCain 37%
Clinton 59%, Giuliani 36%
Clinton 65%, Romney 31%
Clinton 66%, Thompson 28%
Clinton 67%, Paul 24%
Clinton 68%, Huckabee 24%
A new SurveyUSA automated survey of 562 likely voters in Kentucky (conducted 10/27 through 10/29) finds Democratic challenger Steve Beshear leading Republican Gov. Ernie Fletcher (60% to 36%) in a statewide general election match-up for Governor.
A new Zogby national survey of 527 likely Democratic primary voters nationwide (conducted 10/24 through 10/27) finds Sen. Hillary Clinton leads Sen. Barack Obama (38% to 24%) in a national primary, while former Sen. John Edwards trails at 12%. All other candidates receive less than five percent each.
A new Quinnipiac University national survey of 1,636 registered voters (conducted 10/23 through 10/29) finds:
- Among 678 Republicans, former Mayor Rudy Giuliani leads former Sen. Fred Thompson (27% to 17%) in a national primary; former Gov. Mitt Romney trails at 14%, Sen. John McCain at 13%, former Gov. Mike Huckabee at 6%. All other candidates receive less than five percent each.
- Among 742 Democrats, Sen. Hillary Clinton leads Sen. Barack Obama (47% to 21%) in a national primary; former Sen. John Edwards trails at 12%. All other candidates receive less than five percent each.
- General Election Match-ups:
Giuliani 45%, Clinton 43%
Obama 43%, Giuliani 42%
Giuliani 44%, Edwards 41%
Clinton 48%, Romney 38%
Obama 46%, Romney 36%
Edwards 47%, Romney 34%
Full results here.
We have been at work on a number of projects here at
Pollster.com, some you can see and some - so far at least-that you cannot. The
project you cannot see is an upgrade of our back-end systems that will allow us
to provide tables and charts for all the races (including general election
pairings) and more frequent updates of the charts we have now. Unfortunately,
in the short run, we have a let a few daily tasks fall through the cracks. We
apologize for that.
One such omission has been the torrent of recent statewide
general election polls from SurveyUSA. Since October 16, they have released results
from fourteen new automated statewide surveys in battleground states, each
testing six general election matchups: Hillary Clinton against six different
Republicans: Rudy Giuliani, Fred Thompson, Mitt Romney, Mike Huckabee, John
McCain and Ron Paul. Most also test a hypothetical match-up of Rudy Giuliani
against Al Gore. The results are available at the following links:
While many are skeptical of their automated methodology,
SurveyUSA has consistently led the field in terms of their willingness to
disclose both methodological details and to make available both demographic cross-tabulations
and demographic profiles of their registered and likely voter subgroups
available free of charge on their website.
There have been several polls since my last update, and they have varied much more than usual. But the bottom line, with all the data, is a small decline in the trend estimate, and that well within the uncertainty of the trend.
The newly added polls are:
Fox: 10/23-24/07, Approve 35%, Disapprove 55%
LATimes/Bloomberg: 10/19-22/07, Approve 35%, Disapprove 60%
ARG: 10/18-21/07, Approve 25%, Disapprove 67%
CBS News: 10/12-16/07, Approve: 30, Disapprove 61%
CNN/ORC: 10/12-14/07, Approve 36%, Disapprove 61%
Zogby/Reuters: 10/10-14/07, Approve 25%, Disapprove 75%
That is quite a range from two at 25% to a top of 36%. Zogby and ARG are well below the trend estimate, while the two at 35% and one at 36% are only a bit above trend. (An older NPR poll at 38% is well above expectations, but as I explained in an earlier post this has something to do with the likely voter sample NPR favors, compared to the adult samples of most approval polls.)
If we look at the residuals, NPR looks like a high outlier and Harris a low one. But Zogby/Reuters and ARG are even more extreme low outliers. Zogby uses the same 4 point job rating measure that Harris uses, so that partially explains their low value (a persistent question wording effect) but as the plot makes clear, the Zogby reading is even lower than we'd expect from that. The ARG reading is also extremely low, at the same 25% approval rating, and the points and labels are overwritten by each other.
The curiosity is why two (three with Harris) outliers? Did opinion change and these caught it early? Apparently not, judging by other recent polls that are at or even a bit higher than the trend estimate of 32.6%.
In general I think it is a bad idea to seek a substantive explanation for outliers. The most reasonable story is simply "random variation" and we should leave it at that. There ARE some systematic elements, such as the question wording variation or sampling issues I pointed out, but I'm not inclined to say more. To do so becomes a post hoc search for what are most likely statistical phantoms. (Though when history keeps repeating itself we might look into house effects for a systematic effect, possibly due to question wording, sampling, or treatment of don't know responses.)
The bottom line is approval may have shifted down a tad, from 33.0% to 32.6%. BUT, one should consider the gray region around the trend line below. This gives you a good idea of the uncertainty in the trend estimate itself, after squeezing out as much random variation in the polls as possible (at least until next week! Stay tuned for that!). Clearly the change of .4 percentage points is not a clear indication of movement in approval. In fact, given the wide range of current polling, we have an unusually wide uncertainty about where approval actually is at the moment, with 32.6% being our best estimate, but an uncertain one.
We are in a period of relative stability in President Bush's approval rating but considerable polling variation. Waiting for the next "thing" to happen.
Cross-posted at Political Arithmetik.
A new Rasmussen Reports automated survey of 500 likely voters in Virginia (conducted 10/24) finds:
- Former Gov. Mark Warner leads former Gov. Jim Gilmore (53% to 37%) in a statewide general election match-up for U.S. Senate.
- General Election Match-ups for President:
Giuliani 46%, Clinton 43%
Thompson 46%, Clinton 45%
McCain 44%, Clinton 43%
Clinton 48%, Huckabee 39%
A new Rasmussen Reports automated survey of 1,200 likely voters nationwide (conducted 10/26 through 10/28) finds:
- Running as a Democrat, Stephen Colbert edges out Rep. Ron Paul (36% to 32%) in a national general election match-up for President.
- Running as a Republican, Colbert narrowly leads Rep. Dennis Kucinich (37% to 32%) in a national general election match-up for President.
Sorry to blog one more time on the University
of Iowa "Hawkeye" poll, but we want to clarify a few issues. Attentive
readers may have noticed that we added the latest results from the Hawkeye poll
to our Democratic
presidential charts for Iowa,
despite having excluded
the poll from the charts previously and despite my words of caution
about its methodology yesterday. Why the change?
The main reason for our prior exclusion had nothing to do
with their method of sampling or likely voter selection. We left it out because
it used an open-ended vote question, which required respondents to volunteer
the name of the candidate they support. Earlier in the year, we were concerned the
idiosyncrasies of the open-ended vote question would skew our trend lines given
the small number of polls available. At this point, however, the undecided percentages
reported by University
of Iowa poll are in line
with other recent surveys, and we now have sufficient polls that any one survey
does not make a noticeable difference in the trends.
Our bigger concern, particularly with Iowa, was the perception that we were "drawing
a line" in seeming to condemn one survey while including others of either largely
unknown or questionable methodology. Yes, the University of Iowa
survey has a relatively loose screen but it is not alone in that regard. And
other pollsters continue to withhold the necessary details which would allow a
fair comparison of all Iowa
Our philosophy for Pollster.com is to track all polls that claim
to provide representative, projective measurements of vote preferences and
provide the tools and analysis to let readers sort out good from bad. So we
decided that further exclusion of the University of Iowa
poll serves no useful purpose.
But that brings me to the Disclosure Project. I have
delayed an update in hopes that a few pollsters that have promised to do so
would provide answers to our questions. But at this point, we have delayed too
long. I will have a Disclosure Project update either later today or first thing
Three new American Research Group statewide surveys of 600 Democratic and 600 Republican likely caucus/primary voters each in Iowa, New Hampshire, and South Carolina (conducted 10/26 through 10/29) find:
- New Hampshire
- South Carolina
All other candidates receive less than five percent each.
A new Lexington Herald-Leader/Action News 36/Research 2000 statewide survey of 600 likely voters in Kentucky (conducted 10/22 through 10/24) finds:
- 45% approve of the job Mitch McConnell is doing as Senator; 46% disapprove.
- General election match-ups for U.S. Senate:
McConnell 46%, Ben Chandler 41%
McConnell 45%, Crit Laullen 40%
McConnell 46%, Greg Stumbo 37%
McConnell 45%, Andrew Horne 34%
we have a new Iowa
poll today. But be sure you read the fine print below.
Let's start with the basic "poll update" that the estimable
Eric Dienstfrey usually posts in this space. A new University of Iowa "Hawkeye"
poll of 689 likely caucus goers in Iowa (conducted 10/17
through 10/24; summary,
- In an
open-ended question where 306 Democrats had to volunteer, without
prompting, the name the candidate they are supporting, Sen. Hillary
Clinton (at 29%) edges out Sen. Barack Obama (at 27%) in a statewide
caucus; Sen. John Edwards runs at 20%, Gov. Bill Richardson at 7%, Sen. Joe Biden
at 5%. All other candidates receive less than five percent each.
- In an
open-ended question where 282 Republicans had to volunteer the name of the
candidate they are supporting, former Gov. Mitt Romney leads former Mayor
Rudy Giuliani (36.2% to 13.1%) in a statewide caucus; former Gov. Mike
Huckabee trails at 12.8%, former Sen. Fred Thompson at 11%, former Sen.
John McCain at 6%. All other candidates receive less than five percent
Readers should consider that the methodology of this survey,
as in August, is different from most of the other Iowa caucus surveys we have seen. According
to Professor David Redlawski, who spoke at a Washington press briefing this morning, the
October Hawkeye this most recent survey used essentially the same methodology
as their August survey. That is, it used an open-ended vote question, the same
screening questions and sampled from a list of telephone numbers drawn from listed
telephone directories (i.e. not a registered voter list and not using a random
digit dial methodology).
posted by the Hawkeye pollsters includes information on their screening
procedure. They report that the two "likely caucus goer" samples represented 55.8%
of their "registered voter contacts" (that is, of adults who said they were
registered to vote), that 58.6% of these said they would attend the Democratic
caucus and 41.4% would attend the Republican* caucus.
If we assume that 87% of Iowa adults are registered to vote
"active" registered voters divided by 2,264,010 Iowa adults),
that means that the Democratic sample represents 28% of Iowa adults and the
Republican sample represents 20% of Iowa adults. [Correction: The screening information initially provided by the University of Iowa and quoted above was in error and skewed these calculations. The correct percentages of Iowa adults represented were 17% for the Democrats and 13% for the Republicans. See the update at the end of this post for more details].
The problem with that is that it projects to a "likely caucus goer" universe
of nearly half the adults in Iowa
- more than a million. The estimated Democratic turnout in 2004 was 124,000
- the previous all-time high was 126,000 in 1988. The all-time high for
Republicans was 106,000, also in 1988. So this poll is sampling a considerably
broader population of Iowa
adults than has turned out to attend past caucuses.
So interpret these results in that context and with great
caution. The trends observed by comparing
the August an October Hawkeye polls are meaningful - because they used the same
methodology for both polls - but apply only to the very broad population of Iowa adults sampled. It
helps that the trends in this poll bear
a resemblance to what we have seen lately on other Iowa polls,
but we advise huge grains of salt before comparing the support for any
particular candidate on this survey to that measured by any other survey.
*Typo corrected. Thanks James.
Update - 12/16/2007: The original PDF release put out by the University of Iowa that I used in making the above calculations included the following sentences:
Respondents were asked whether they were very likely, somewhat likely, not very likely, or not at all likely to attend their party’s caucus in 2008. Responses of “not at all likely” were screened out of the sample. Remaining respondents were further asked which party's caucus they would attend. Those unable to name which party were also screened out of the sample. Of registered voter contacts, 36.2 percent were eliminated on the initial screen. Another 8.0 percent were screened out because they could not name the party with whom they would caucus.
On December 13, 2007, The University of Iowa's Caroline Tolbert notified me via email that the paragraph above was incorrect. They subsequently revised the paragraph in their summary to read as follows:
Respondents were asked whether they were very likely, somewhat likely, not very likely, or not at all likely to attend their party’s caucus in 2008. Among all registered voters contacted, 37.2% said they were "not at all" likely to caucus, while another 21.3% said they were "Not very likely". These two groups were not considered "likely caucus goers". The remaining 41.5% said they were "Very Likely" (24.1%) or "Somewhat Likely" (17.4%) to caucus. A second screen then asked which party's caucus the voter planned to attend. Of the initial screen of likely caucus goers, 4.4% could not name a party, and were dropped. Approximately 35% of the original registered voter sample is thus classified as "likely caucus goers". Of the total original registered voter sample, about 19.1% are likely Democratic caucus goers and 14.4% are likely Republican Caucus Goers.
Since my calculations were based on the erroneous information included in the first release, they too were in error. The correct statistics, based on this new information, are as follows: The Democratic sample represented 17% of Iowa adults, the Republican sample represented 13% of Iowa adults.
Via Mark Halperin's The Page
comes word that University
of Iowa political
scientist David Redlawsk will
release a new Hawkeye Poll of likely caucus goers tomorrow. Just a reminder: The methodology of
U. of I. poll was unusual in a few respects: they asked an open-ended vote
question (that asks respondents to volunteer their choice without prompting),
they sampled from a directory of listed telephone households (rather than from
registered voter lists or via random digit dial or voting list) and used a
screen that was wider
than other polls. More details in my post on their August poll.
We have not included the previous Hawkeye polls in our Iowa chart because of the
use of the open-ended question. This is not a statement about the quality of
the survey. As I wrote
back in August:
This [open-ended question] undoubtedly
provides a tougher test of voter commitment, but also produces a much bigger
undecided and renders the results incomparable to other Iowa polls.
Of course, we do not know what methodology the Hawkeye poll used
this time, but the news advisory does promises that the new results will show
how candidate support "has changed since August." So presumably the methodology
has been held constant.