Pollster.com

June 6, 2010 - June 12, 2010

 

US: National Survey (Fox 6/8-9)

Topics: Generic House Vote , National , Oil , Poll

Fox News / Opinion Dynamics
6/8-9/10; 900 registered voters, 3% margin of error
373 Democrats, 5% margin of error
305 Republicans, 5% margin of error
165 independents, 8% margin of error
Mode: Live telephone interviews
(Oil Release)
Update: Generic Ballot

National

Congressional Job Approval
22% Approve, 69% Disapprove (chart)

2010 Congress: Generic Ballot
41% Democrat, 38% Republican (chart)

Obama Job Approval
46% Approve, 45% Disapprove (chart)
Dems: 79 / 13 (chart)
Reps: 13 / 81 (chart)
Inds: 38 / 48 (chart)

"Do you favor or oppose increasing offshore drilling for oil and gas in U.S. coastal areas?"
44% Favor, 48% Oppose

"Do you approve or disapprove of how the Obama administration is dealing with the oil spill in the gulf coast?"
38% Approve, 51% Disapprove

"Do you approve or disapprove of how British Petroleum or BP, the oil company in charge of the oil rig, is dealing with the oil spill in the gulf
coast?"

13% Approve, 79% Disapprove

"Do you think President Obama is spending too much time, too little time, or about the right amount of time on the oil spill in the Gulf of Mexico?"
4% too much, 40% too little, 45% right amount

"Which one of the following groups do you think is most responsible for the oil spill?"
58% "The oil company British Petroleum for not being prepared for a leak"
7% "The federal government for allowing offshore drilling in deep coastal waters"
10% "Environmental groups for opposing drilling on land and in shallow waters closer to the shoreline"
8% "American consumers for relying on such large quantities of oil and gas"
10% All

Party ID
41% Democrat, 34% Republican, 18% independent (chart)


Transparency and Pollster Ratings

Topics: Del Ali , Disclosure , Nate Silver , Poll Accuracy , Research2000 , Taegan Goddard

My column for next week has been posted a little earlier than usual. It covers the controversy over Nate Silver's pollster ratings, and bloggy exchange over the last day or two between Silver, Political Wire's Taegan Goddard and Research 2000's Del Ali over the transparency in the FiveThirtyEight pollster ratings. I have a few important footnotes and another aspect of transparency to review, but real life intrudes. So please click through and read it all, but come back to this post later tonight for an update.

***

I'm going to update this post in two parts. First I want to add some footnotes to the column, which covers the questions that have been raised about the database of past polls that Nate Silver created and used to score pollsters. The second part will discuss the transparency regarding additional aspects of Nate's model and scoring.

I want to emphasize that nothing I learned this week leads me to believe that Silver has intentionally misled anyone or done anything intentionally sinister. I have questions about the design and interpretation of the models used to score pollsters, and I wish he would be more transparent about the data and mechanics, but these are issues of substance. I'm not questioning his motives.

So on the footnotes: Earlier today, Del Ali of Research 2000 sent us a list of 12 of his poll results he claimed that Silver should have included in his database and 2 more that he said were in error. Later in the morning he sent one more omitted result. We did our best to review that list and confirm the information provided. Here is what we found.

First, the two polls included in Silver's database with errors:

  • 2008-FL President (10/20-10/22) - Error (+3 Obama not +4)
  • 2008-ME President (10/13-10/15) - Error (+17 Obama not +15)

These are both relatively small errors, and we noticed that the apparent mistake on the Maine poll was also present in the DailyKos summary of the poll published at the time.

There were four three more polls in the omitted category that were either more than 21 days before the election (Hawaii and the Florida House race) our outside the range of races that Silver said he included (he did not include any gubernatorial primaries before 2010). [Correction: We overlooked that the NY-23 special election was omitted intentionally because of Silver's criteria of excluding races "where a candidate who had a tangible chance of winning the election drops out of it prematurely"].

  • 2010-HI-01 Special Election House (4/11-4/14)
  • 2006-FL-16 House (10/11-10/13)
  • 2002-IL Dem Primary Governor (3/11-3/13)
  • 2009-NY-23 Special (10/26-28)

Some may quarrel with Silver's decisions about the range of dates he sets as a cut-off, and I'm hoping to write more about that aspect of his scoring system. But as long as Silver applied his stated rules consistently, these examples do not qualify as erroneous omissions.

That leaves nine ten more Research 200 polls that appear to be genuine omissions in the sense that they meet Silver's criteria but were not included in the database:

  • 2000-IN President (10/28-10/30)
  • 2000-NC President (10/28-10/30)
  • 2000-NC Governor (10/28-10/30)
  • 2002-IN-02 House (10/27-10/29)
  • 2004-IA-03 (10/25-10/27)
  • 2004-NV Senate (10/19-10/21)
  • 2008-ID Senate (10/21-10/22)
  • 2008-ID-01 (10/21-10/22)
  • 2008-FL-18 (10/20-10/22)
  • 2009-NY-23 Special (10/26-28)

Do these omissions indicate sloppiness? We were able to find the NY-23 special election results on Pollster.com and elsewhere, the 2004 Nevada Senate and 2002 Indiana House on the Polling Report and the Iowa 3rd CD poll from 2004 with a Google search at KCCI.com. So those examples should have been included but were not.

However, we could not find the 2000 North Carolina poll anywhere except the subscriber-only archives of The Hotline (although, oddly, with different field dates: 10/30-31). The Hotline database is not among Silver's listed resources.

We also checked and the three results (from two polls) missing for 2008 and found they were also missing from the compilations published by our site, RealClearPolitics and the Polling Report during the campaign (though we did find mention of the Idaho poll on Research2000.com). We could not find the Indiana presidential result from 2000 anywhere.

The point of all of this is that there are really only a small number of examples that qualify as mistakes attributable to Silver's team. Most of the other oversights were also made by their sources. And even if we correct all of the errors and include all of the inside-the-21-day-window omissions, it changes the average error for Research 2000 hardly at all (as summarized in the column [and leaving out NY-23 does not change the average error]). These examples still represent imperfections in the data that should be corrected, and we can assume that more exist for the other pollsters, and as argued in the column, I'm all for greater transparency. But if you are looking for evidence of something "sinister," it just isn't there.

We created a spreadsheet that includes both the original list of Research 2000 polls included in the Fivethirtyeight database and a second tab that includes the corrections and appropriate omissions. It is certainly possible that our spreadsheet contains errors of it's own, so in the spirit of transparency, we've made it available for download. Feel free to email us with corrections.

[I corrected a few typos and cleaned up one mangled sentence in the original post above -- Part II of the update coming over the weekend.]

Update (6/14): Since I did not finish the promised update until Monday afternoon, I posted it as a separate entry. Please click through for more.


World Cup 'Outliers'

Topics: Outliers Feature

Gallup finds Hispanic voter preferences unchanged after passage of the Arizona immigration law.

Jennifer Agiesta reviews the Post/ABC data on opinions on Afghanistan

Mike Mokrzycki finds support for Elena Kagan in line with previous nominees.

John Sides examines whether if race or ballot order explains Alvin Greene's suprise win in South Carolina; Tom Schaller catches a whiff of "something fishy."

Tom Jensen reminds us that Vic Rawl was almost totally unknown in South Carolina.

Neil Newhouse, Stan Greenberg and Carroll Doherty discuss voter anger and the 2010 elections at a National Journal panel. Chris Bowers doesn't buy a new Gallup poll greater concern about the deficit than other issues.

National Journal's Republican insiders think the oil spill will help them in November; On Call has more.

Kristen Soltis returns for season three of "The Right Idea"

Harry Enten critiques a Nate Silver analysis of the relationship between divorce and same sex marriage.

Slate launches a new "polling" feature that asks readers for predictions "about stuff in the news."

Connecticut likes both the Yankees and Red Sox.

Nate Silver is thinking about soccer


CA: 2010 Sen, Gov (Rasmussen 6/9)

Topics: California , Governor , poll , Senate

Rasmussen
6/9/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen release)
Update: Senate

California

2010 Senate
48% Boxer (D), 43% Fiorina (R)

2010 Governor
45% Brown (D), 44% Whitman (R) (chart)

Favorable / Unfavorable
Barbara Boxer: 43 / 52 (chart)
Carly Fiorina: 44 / 43
Meg Whitman: 51 / 41
Jerry Brown: 48 / 47

Job Approval / Disapproval
Pres. Obama: 59 / 39 (chart)
Gov. Schwarzenegger: 30 / 67 (chart)


US: National Survey (Economist 6/5-8)

Topics: Generic House Vote , national , poll

Economist / YouGov
6/5-8/10; 1,000 adults, 3.5% margin of error
Mode: Internet
(Economist release)

National

Obama Job Approval
44% Approve, 49% Disapprove (chart)
Dems: 80 / 17 (chart)
Reps: 12 / 84 (chart)
Inds: 39 / 55 (chart)
Economy: 38 / 54 (chart)
Health Care: 41 / 52 (chart)
Oil spill in the Gulf of Mexico: 28 / 43

Congressional Job Approval
14% Approve, 62% Disapprove (chart)

2010 Congress: Generic Ballot (chart)
Likely Voters: 47% Republican, 46% Democrat
Registered voters: 47% Democrat, 43% Republican (n=710, MOE=3.8%)
All adults: 44% Democrat, 39% Republican

State of the Country
31% Right Direction, 53% Wrong Track (chart)


OR: 2010 Gov, Sen (SurveyUSA 6/7-9)

Topics: Governor , Oregon , Poll , Senate

SurveyUSA
6/7-9/10; 566 likely voters, 4.2% margin of error
Mode: Automated phone
(SurveyUSA release)

Oregon

2010 Governor
47% Dudley (R), 40% Kitzhaber (D), 6% Wilson (P)

2010 Senate
51% Wyden (D), 38% Huffman (R)


MD: 2010 Gov (Rasmussen 6/8)

Topics: Governor , Maryland , poll

Rasmussen
6/8/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen release)

Maryland

2010 Governor
45% O'Malley (D), 45% Ehrlich (D)

Favorable / Unfavorable
Martin O'Malley: 53 / 43
Bob Ehrlich: 53 / 42
Barbara Mikulski: 48 / 42
Benjamin Cardin: 44 / 35

Job Approval / Disapproval
Pres. Obama: 54 / 44
Gov. O'Malley: 56 / 43


US: Elena Kagan (ABC News/Washington Post 6/3-6)

Topics: National , Supreme Court

ABC News/Washington Post
6/3-6/10; 1,004 adults, 3.5% margin of error
Mode: Live telephone interviews
(ABC release)
Update: ABC Story, Washington Post Release, Washington Post Story

National

"Do you think the U.S. Senate should or should not confirm Kagan's nomination to the Supreme Court?"
58% should, 24% should not

"At her confirmation hearing, do you think Kagan should or should not answer questions about how she would have ruled on past cases that have come before the Supreme Court?"
66% should, 29% should not

"Do you think Kagan should or should not publicly state her position on abortion before being approved by the U.S. Senate for the job?"
54% should, 42% should not


Pets and Money 'Outliers'

Topics: Outliers Feature

Nate Silver responds to criticism of the transparency of his pollster ratings.

Jonathan Chait criticizes a poll on economic knowledge.

Chris Bowers takes Ezra Klein to task for his interpretation of a Gallup poll.

Gary Langer and Jon Cohen say most Americans support regulating greenhouse gases.

Joshua Green argues that the oil spill is killing the Tea Party movement.

Tom Jensen sees no change in public opinion on the health reform law.

Andrew Sullivan points to a CBS poll showing an increase in people saying they know someone who is gay or lesbian.

AP finds that the recession may be hurting pets, too.


US: 2012 Pres (PPP 6/4-7)


Public Policy Polling (D)
6/4-7/10; 650 adults, 3.8% margin of error
Mode: Automated phone
(PPP release)

National

2012 President
46% Obama, 44% Huckabee
50% Obama, 41% Palin
47% Obama, 39% Gingrich
46% Obama, 36% Paul
45% Obama, 42% Romney

Obama Job Approval
48% Approve, 47% Disapprove (chart)

Favorable / Unfavorable
Mike Huckabee: 27 / 31 (chart)
Sarah Palin: 34 / 53 (chart)
Newt Gingrich: 28 / 46
Ron Paul: 22 / 36
Mitt Romney: 31 / 36 (chart)


NV: 2010 Gov, Sen (Rasmussen 6/9)

Topics: Governor , Nevada , poll , Senate

Rasmussen
6/9/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen release)
Update: Governor

Nevada

2010 Senate
50% Angle (R), 39% Reid (D) (chart)

2010 Governor
54% Sandoval (R), 31% Reid (D) (chart)

Favorable / Unfavorable
Harry Reid: 46 / 54 (chart)
Sharron Angle: 48 / 45
Brian Sandoval: 62 / 29
Rory Reid: 42 / 50

Job Approval / Disapproval
Pres. Obama: 48 / 51 (chart)
Gov. Gibbons: 35 / 64 (chart)


CO: 2010 Sen Primary (Magellan 6/8)

Topics: Colorado , poll

Magellan
6/8/10; 1,026 likely Republican primary voters, 3% margin of error
Mode: Automated phone
(Magellan release)

Colorado

2010 Senate: Republican Primary
42% Buck, 32% Norton (trends)


AL: 2010 Gov (Rasmussen 6/3)

Topics: Alabama , poll

Rasmussen
6/3/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen release)

Alabama

2010 Governor
49% Byrne (R), 40% Sparks (D)
56% Bentley (R), 37% Sparks (D)

Favorable / Unfavorable
Bradley Byrne: 57 / 29
Robert Bentley: 66 / 20
Ron Sparks: 51 / 34

Job Approval / Disapproval
Pres. Obama: 40 / 58
Gov. Riley: 57 / 42


IL: Brady 47, Quinn 36 (Rasmussen 6/7)

Topics: Illinois , poll

Rasmussen
6/7/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen release)

Illinois

2010 Govenror
47% Brady (R), 36% Quinn (D) (chart)

Favorable / Unfavorable
Pat Quinn: 42 / 52
Bill Brady: 47 / 33


CT: 2010 Sen (Quinnipiac 6/2-8)

Topics: Connecticut , poll


Quinnipiac
6/2-8/10; 1,350 registered voters, 2.7% margin of error
500 Democrats, 4.4% margin of error
343 Republicans, 5.3% margin of error
Mode: Live telephone interviews
(Quinnipiac release)

Connecticut

2010 Senate: Republican Primary
45% McMahon, 29% Simmons, 13% Schiff (chart)

2010 Senate: General Election
54% Blumenthal, 33% Simmons (chart)
55% Blumenthal, 35% McMahon (chart)
56% Blumenthal, 29% Schiff (chart)

2010 Governor: Democratic Primary
39% Lamont, 22% Malloy

2010 Governor: Republican Primary
39% Foley, 12% Fedele, 2% Griebel

Favorable / Unfavorable
Richard Blumenthal: 59 / 29
Rob Simmons: 36 / 13
Linda McMahon: 38 / 35
Peter Schiff: 15 / 5

Job Approval / Disapproval
Gov. Rell: 62 / 32 (chart)
Sen. Lieberman: 41 / 50 (chart)
Sen. Dodd: 36 / 58 (chart)
Pres. Obama: 53 / 42 (chart)


FL: 2010 Sen, Gov Primary (Quinnipiac 6/2-8)

Topics: Florida , poll

Quinnipiac
6/2-8/10; 814 likely Republican primary voters, 3.4% margin of error
785 likely Democratic primary voters, 3.5% margin of error
Mode: Live telephone interviews
(Quinnipiac release)

Florida


2010 Governor: Republican Primary
44% Scott, 31% McCollum

2010 Senate: Democratic Primary
29% Meek, 27% Greene, 3% Ferre


More on the Arkansas Surprise

Topics: Arkansas , Bill Halter , Blanche Lincoln , Daily Kos , Likely Voters , Research2000 , Turnout

Before moving on to the more important issues raised by both Nate Silver's new pollster accuracy ratings and their apparent role in parting of ways between DailyKos and pollster Research 2000, I want to consider some possible lesson's from last night's Arkansas surprise.

Let's start with the assertion that Del Ali, president of Research 2000, made to me earlier today. He says that the final result -- Blanche Lincoln prevailed by a 52.0% to 48.0% margin -- fell within the +/- 4% margin of error of his final poll, which showed Halter at 49% and Lincoln at 46%. That much appears to be true. However, Research 2000 did three polls on the Lincoln-Halter run-off, including a survey conducted entirely on the evening of the first primary, and all three gave Halter roughly the same margin as the final poll.

2010-06-09-AR polls.png

I'll spare you the math (and the argument about how we might calculate the margin of error for such a pooled sample), but if you treat all three polls as if they were one, the difference between the vote count and the consistent Research 2000 result looks far more statistically meaningful.

One big problem in this case is that Research 2000 was the only pollster releasing results into the public domain. Had other pollsters been active, producing the sort of pollster-to-pollster variation we typically see, those who follow the race may have been less surprised by the outcome.

I am told, however, that there the Lincoln campaign and allies of the Halter campaign (presumably organized Labor) did conduct internal polling that was not publicly released. I communicated with senior advisors to both campaigns today who say that each side polled immediately after the first primary and showed Lincoln ahead. Lincoln's internal poll showed her leading by ten points, while two post-primary polls conducted by Halter's allies showed Lincoln leading by six and four points. The advisors also claim that neither campaign fielded a tracking poll in the final week, as all remaining resources were devoted to advertising and efforts to get out the vote.

Now in fairness to Research 2000, all of these claims were made to me today, on background, and I have no way to verify them independently. So take this information with a grain of salt.

Are there lessons to be learned here?

First, let's remember the point I made a week ago, with the help of Nate Silver's data: Whatever the reason, polls show far more error in primaries, especially primary elections in southern states.

Second, consider something largely overlooked: Arkansas has one of the largest cell-phone only populations in the nation. A year ago, the Center for Disease Control's National Center for Health Statistics (NCHS) published estimates of wireless-only percentages by state. Arkansas ranked fourth for the percentage of cell phone only households (22.6%) and seventh for the percentage of cell phone only adults (21.2% -- for rankings, see the charts in our summary). And the national level NCHS estimates of the cell phone only population have risen another 4.5 percentage points over the past year.

Nationally, the cell-phone-only population is largest among younger Americans, those who rent rather than own their homes and among non-whites. Those patterns could have made a difference in Arkansas.

Third is a point I made in my column earlier this week: The results of pre-election surveys are sometimes only as good as the assumptions that pollsters make in "modeling" likely voters.

For example, many pollsters stratify their likely voter samples regionally based on past turnout. In other words, they divide the state up into regions and use past vote returns to determine the size of each region as a percentage of the likely electorate. As should be obvious, these judgements are often subjective and rely heavily on the assumption that past turnout patterns will apply to future elections.

For the Arkansas runoff, however, pollsters could rely on a very proximate turnout model: The first primary on May 18 between Lincoln, Halter and D.C. Morrison. In fact, according to Del Ali, that's exactly what Research 2000 did for their runoff polls. They used the regional distribution of voters on May 18 to set regional quotas. They also conducted a survey of self-identified voters on primary election night, weighted the survey so their self-reported preferences matched the result, and relied on the resulting demographics to guide their demographic weighting on subsequent polls.

But here's the problem: As is typical, total turnout declined between the two elections. Roughly 70,000 voters (21% of those who voted in the first primary) did not vote in the runoff. But more important the pattern in the fall-off was not consistent throughout the state and the pattern favored Lincoln: Turnout was high in her base and fell off most where she was weakest.

I took the vote by county as reported by the Associated Press (here and here) and calculated turnout in each county for the runoff as a percentage of the total vote cast in the first primary. As the scatterplot below shows, the fall-off in turnout was typically greatest in counties where Lincoln's percentage of the vote on May 18 was lowest (I omitted results from Baxter and Newton counties which showed increases in the total vote suggesting clerical errors or omissions in AP's vote total).

2010-06-09-arksansas-turnout-scatter.png

The pattern is most likely explained by the fact that there were also Congressional run-off elections held yesterday in the 1st and 2nd Districts of Arkansas, which kept turnout higher in areas that are also Lincoln's base of support.

I don't want to make too much of the turnout pattern since, by my calculations, re-weighting the May 18 vote to match yesterday's county level turnout would add less than percentage point to Lincoln's lead. But hopefully it gives you some idea of what can happen when assumptions can go awry. Region is just one variable. Other assumptions, such as those for race and age, may have been even more consequential. Other pollsters making different assumptions may have produced very different results. When just one public pollster is active in the race, the odds of misreading the horse-race are greater.


Stephen Strasburg 'Outliers'

Topics: Outliers Feature

Steve Shepard reports on the firing of Research 2000 by Daily Kos; Steve Lombardo ponders Nate Silver's influence; Taegan Goddard questions Silver on transparency.

Gary Langer notes a decline in support for offshore drilling post-oil spill.

Mark Mellman argues that the spill will not be Obama's Katrina.

David Hill says Whitman and Fiorina mark a step forward for Republican women.

Glen Bolger wants to stay focused on the economic "big picture."

Mark Ambinder points to new maps of vote percentage for the winners of last night's primaries.

Bob Groves explains how the Census recontacts households for quality assurance.

Greenberg Quinlan Rosner releases a straw poll of America's Future Now! conference attendees.

Del Ali is thinking about baseball.


US: National Survey, Oil Spill (PPP 6/4-7)

Topics: National , poll

Public Policy Polling (D)
6/4-7/10; 650 registered voters, 3.8% margin of error
Mode: Automated phone
(PPP release)

National

Obama Job Approval
48% Approve, 47% Disapprove (chart)
Dems: 83 / 13 (chart)
Reps: 11 / 84 (chart)
Inds: 38 / 55 (chart)
Handling Oil Spill:38 / 47

Do you support or oppose President Obama's health care plan, or do you not have an opinion?
43% Support, 49% Oppose (chart)

Are you buying gas at BP more often, less often, or about the same as you were two months ago?
5% More often, 38% Less often, 57% Same


US: News Interest, Oil Spill (Pew 6/3-6)

Topics: National , poll

Pew Research Center
6/3-6/10; 1,002 adults, 4% margin of error
Mode: Live telephone interviews
(http://people-press.org/reports/pdf/621.pdf)

National

Most Closely Followed Story
66% A major oil leak in the Gulf of Mexico
9% Reports about the condition of the U.S. economy
4% Israel intercepting boats carrying supplies to Gaza, killing nine aboard
4% The NHL Stanley Cup finals
1% Former Vice President Al Gore and his wife Tipper announcing that they are separating after 40 years of marriage
1% Reports that the White House discussed the possibility of administration jobs with Democratic Senate candidates to get them to not run against its preferred candidates

How much do you trust information about the Gulf Coast oil leak that comes from...
BP: 8% A lot, 31% Some, 29% Not too much, 28% Not at all
The federal government: 12% A lot, 39% Some, 25% Not too much, 21% Not at all
News organizations: 20% A lot, 47% Some, 20% Not too much, 11% Not at all


US: Elena Kagan (Rasmussen 6/7-8)

Topics: National , poll

Rasmussen
6/7-8/10; 1,000 likely voters, 3% margin of error
Mode: Automated phone
(Rasmussen release)

National

Favorable / Unfavorable
Elena Kagan: 36 / 42

The U.S. Senate has the constitutional authority to confirm all Supreme Court nominees. Based upon what you know at this time, should the U.S. Senate confirm Elena Kagan as a Supreme Court Justice?
33% Yes, 41% No


DailyKos Fires Research 2000

Topics: Arkansas , Daily Kos , Del Ali , Pollsters , Research2000

Markos ("Kos") Moulitsas has opted to "part ways" with DailyKos polling partner Research 2000 and seek "a new polling partner to finish out this election cycle." And if that were not enough, he explains that "The decision was made, in part, on the results of Nate Silver's new pollster rankings."

Research 2000's past results aren't actually as bad as people will try and make them out to be. In fact, if there's one thing that's striking about the chart, is how closely clumped together those pollsters actually are. The difference in accuracy between the best and worst pollsters (omitting Zogby's genuinely crappy internet poll) isn't very big. As Nate told me via email as he walked me through the results:

The absolute difference in the pollster ratings is not very great. Most of the time, there is no difference at all.

And while many will focus on R2K's misses in Alabama and Arkansas, fact is they nailed several others, like the Hawaii special, the Nevada primaries, NY-23, etc. Every pollster has hits and misses, and R2K was no different. But in an industry measured in percentages, fact is they underperformed their peers.

I believe in accountability, in accuracy, and in making sure we provide the absolute best information not just to this wonderful community, but also to the outside world. As such, Daily Kos will be on polling hiatus the next several months as we evaluate our options and decide how to best proceed.

I reached Del Ali, the president of Research 2000, by telephone a few minutes ago. He said he considered the Kos blog post "very kind to us" although he takes issue with the characterization of their final Arkansas poll as a "miss:"

We're the only polling firm that did this race, so there's no comparison with other pollsters for the record. But, having said it, our final numbers were 49-45 in favor of Halter [with a] four percent margin of error. I do believe the result fell within the margin for error.

Ali also pointed to two factors that "one has too look at" in assessing his final Arkansas poll, which was fielded last week from Wednesday to Friday. First, he gave credit to the "Clinton machine" for being "very effective with the Democratic party establishment over the weekend." Second he mentioned the "controversy that's still lurking even though Halter conceded --- the forty some odd polling areas or polling precincts that people could not vote in the areas of the state that Halter could have done well in." Put that together, Ali says, and "it comes out as, you know, 'Dewey Defeats Truman.'

This news is a likely a blow to the Olney, Maryland based research firm. Ali told me in March that DailyKos and other progressive sites or organizations like the Progressive Change Campaign Committee have sponsored roughly 80 percent of the publicly released polls conducted in recent years by Research 2000. The vast majority of the Research 2000 polls we have logged at pollster have been sponsored by DailyKos.

I will have more to say on this story soon

Update - Del Ali emails with this clarification:

Kos polling and PAC's is about 80% of our political polling only. However, our political polling is less than 15% of our overall business. Overall, 85% of what we do involves consulting for businesses and non political organizations, polling for non state wide candidates around the nation and a great deal moderating focus groups around the nation. That is where we make our money.

If we lived on Kos polling and media polls we would not exist. So, where I will miss polling for Markos, the financial impact is minimal if not non existent.


CO: 2010 Sen (Rasmussen 6/7)

Topics: Colorado , poll

Rasmussen
6/7/10; 500 likely voters, 4.5% margin of error
Mode: Live telephone interviews
(Rasmussen release)

Colorado

2010 Senate
43% Norton (R), 42% Romanoff (D) (chart)
46% Norton (R), 40% Bennet (D) (chart)
45% Buck (R), 39% Romanoff (D) (chart)
46% Buck (R), 41% Bennet (D) (chart)

Favorable / Unfavorable
Ken Buck: 44 / 32
Michael Bennet: 39 / 50
Andrew Romanoff: 45 / 42
Jane Norton: 44 / 44

Job Approval / Disapproval
Pres. Obama: 43 / 57 (chart)
Gov. Ritter: 39 / 62 (chart)


IL: 2010 Sen (Rasmussen 6/7)

Topics: Illinois , poll

Rasmussen
6/7/10; 500 likely voters, 4.5% margin of error
modE: Automated phone
(Rasmussen release)

Illinois

2010 Senate
42% Kirk, 39% Giannoulias (chart)

Favorable / Unfavorable
Mark Kirk: 48 / 39
Alexi Giannoulias: 39 / 46

Job Approval / Disapproval
Pres. Obama: 56 / 44
Gov. Quinn: 42 / 57


FL: 2010 Sen, Gov (Rasmussen 6/7)

Topics: Florida , poll

Rasmussen
6/7/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen release)
Update: Governor

Florida

2010 Senate
37% Rubio (R), 37% Crist (i), 15% Meek (D) (chart)
41% Crist (i), 37% Rubio (R), 13% Greene (D)

2010 Governor
40% McCollum (R), 38% Sink (D) (chart)
45% Scott (R), 40% Sink (D)

Favorable / Unfavorable
Charlie Crist: 62 / 37 (chart)
Kendrick Meek: 30 / 39
Marco Rubio: 46 / 38
Jeff Greene: 28 / 41
Bill McCollum: 40 / 43
Alex Sink: 41 / 34
Rick Scott: 45 / 33

Job Approval / Disapproval
Pres. Obama: 46 / 53 (chart)
Gov. Crist: 60 / 37 (chart)


FL: 2010 Sen, Gov (Quinnipiac 6/1-7)


Quinnipiac
6/1-7/10; 1,133 registered voters, 2.9% margin of error
Mode: Live telephone interviews
(Quinnipiac release)

Florida

2010 Senate
37% Crist (i), 33% Rubio (R), 17% Meek (D) (chart)
40% Crist (i),, 33% Rubio (R), 14% Greene (D)

2010 Governor
42% McCollum (R), 34% Sink (D) (chart)
42% Scott (R), 32% Sink (D)
35% Scott (R), 26% Sink (D), 19% Chiles (i)
33% McCollum (R), 25% Sink (D), 19% Chiles (i)

Favorable / Unfavorable
Kendrick Meek: 17 / 13
Jeff Greene: 11 / 11
Marco Rubio: 36 / 28
Charlie Crist: 52 / 33 (chart)
Bill McCollum: 37 / 29
Alex Sink: 28 / 14
Rick Scott: 31 / 22
Bud Chiles: 10 / 7

Job Approval / Disapproval
Gov. Crist: 57 / 35 (chart)
Sen. Nelson: 47 / 31 (chart)
Sen. LeMieux: 21 / 25 (chart)
Pres. Obama: 40 / 54 (chart)

In general, do you support or oppose the United States increasing the amount of drilling for oil and natural gas in offshore waters?
42% Support, 51% Oppose

Do you approve or disapprove of the way Barack Obama is handling - the oil spill in the Gulf of Mexico?
37% Support, 54% Oppose


8:30 P.M Live Election Night Blog


We're live blogging Super Tuesday 2010 Part II right now!

Remember: (1) No exit polls tonight, at least not the ones conducted by the network consortium and (2) we'll have at least one special guest.

<


Going Postal 'Outliers'

Topics: Outliers Feature

Frank Newport asks just what Americans want to be done about the Gulf oil spill.

Gary Langer points to the decreasing popularity of the war in Afghanistan.

CBS debuts a new "hot races" map.

John Sides discusses a weak relationship between voter "re-elect" answers and actual re-election rates (more here).

The Field Poll finds only a third of voters plan to vote in California's primary election.

Nate Silver points out a fishy "knowledge" poll.

A Bloomberg poll of financial elites finds a divide between those inside and outside the US (more here).

Ben Smith reports the Postal Service has asked the RNC to "cease and desist" its census mailers.


AL: 2010 Sen (Rasmussen 6/3)

Topics: Alabama , poll

Rasmussen
6/3/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen release)

Alabama

2010 Senate
58% Shelby (R), 31% Barnes (D)

Favorable / Unfavorable
Richard Shelby: 66 / 26
William Barnes: 37 / 27

Job Approval / Disapproval
Pres. Obama: 40 / 58
Gov. Riley: 57 / 42


NC: 2010 Sen (PPP 6/4-6)

Topics: North Carolina , poll

Public Policy Polling (D)
6/4-6/10; 601 likely voters, 3.9% margin of error
Mode: Automated phone
(PPP release)

North Carolina

2010 Senate
46% Burr (R), 35% Cunningham (D) (chart)
46% Burr (R), 39% Marshall (D) (chart)

Job Approval / Disapproval
Sen. Hagan: 34 / 39 (chart)
Sen. Burr: 35 / 37 (chart)

Favorable / Unfavorable
Cal Cunninham: 12 / 13
Elaine Marshall: 21 / 16


NC: 2010 Sen (Rasmussen 6/3)

Topics: North Carolina , poll

Rasmussen
6/3/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen release)

North Carolina

2010 Senate<
50% Burr (R), 36% Marshall (D) (chart)
47% Burr (R), 35% Cunninham (D) (chart)

Favroable / Unfavorable
Richard Burr: 54 34
Elaine Marshall: 41 / 39
Cal Cunningham: 35 / 38

Job Approval / Disapproval
Pres. Obama: 45 / 55 (chart)
Gov. Perdue: 46 / 53 (chart)


US: National Survey (Zogby 6/4-7)

Topics: National , poll

Zogby
6/4-7/20; 2,062 likely voters, 2.2% margin of error
Mode: internet
(Zogby release)

National

Obama Job Approval
47% Approve, 53% Disapprove (chart)

2010 Congress: Generic Ballot
41% Democrat, 41% Republican (chart)


CA: 2010 Sen, Gov Primaries (SurveyUSA 6/3-6)

Topics: California , poll

SurveyUSA
6/3-6/10; 569 likely Republican primary voters, 4.1% margin of error
617 likely Republican primary voters, 3.6% margin of error
Mode: Automated phone
(SurveyUSA release)

California

2010 Governor: Republican Primary
59% Whitman, 30% Poizner, 6% Others (chart)

2010 Senate: Republican Primary
48% Fiorina, 22% Campbell, 16% DeVore, 4% Others (chart)

2010 Governor: Democratic Primary
73% Brown, 4% Aguirre, 4% Pineda, 8% Others


US: National Survey (ABC/Post 6/3-6)

Topics: National , poll

ABC News / Washington POst
6/3-6/10; 1,004 adults, 3.5% margin of error
Mode: Live telephone interviews
(ABC: story, results; Post: story)

National

Obama Job Approval
52% Approve, 45% Disapprove (chart)
Oil Spill: 44% Approve, 49% Disapprove
Economy: 50% Approve, 49% Disapprove (chart)
Budget deficit: 39% Approve, 56% Disapprove

2010 House: Generic Ballot
47% Democrat, 44% Republican (among registered voters) (chart)

State of the Country
37% Right Direction, 60% Wrong Track (chart)

Congressional Job Approval
26% Approve, 71% Disapprove (chart)
Your own representative: 49% Approve, 44% Disapprove

Overall, which party, the Democrats or the Republicans, do you trust to do a better job in coping with the main problems the nation faces over the next few years?
44% Democrats, 32% Republicans

Right now, are you inclined to vote to re-elect your representative in Congress in the next election or are you inclined to look around for someone else to vote for?
29% Re-elect, 60% Look around


Census Kitteh 'Outliers'

Topics: Outliers Feature

Nate Silver debuts his new pollster rankings (methodology here) and gives his first scorecard to SurveyUSA; Matt Towery responds.

Tom Jensen sees Democrats still losing independents, but not as much as in 2009.

Christopher Beam asks what would happen if political scientists wrote the news; Andrew Gelman and John Sides respond; Conor Friedsdorf pens a Sociologist variant (via Chait).

Chris Bowers sees a "tectonic shift" in opinion on offshore drilling.

Alex Lundry presents at the PDF conference on the best political visualizations of the year.

NPR profiles Edward Tufte (via Lundry).

Junk Charts critiques a New York Times chart.

And census kitteh knows where to find you.

funny-pictures-cat-takes-census.jpg


CA: 2010 Gov, Sen Primaries (Magellan 6/3)

Topics: California , poll

Magellan Strategies (R)
6/3/10; 602 likely Republican primary voters, 4% margin of error
Mode: Automated phone
(Magellan release)

California

2010 Governor: Republican Primary
64% Whitman, 22% Poizner (chart)

2010 Senate: Republican Primary
54% Fiorina, 19% Campbell, 16% DeVore (chart)


US: Generic Ballot (Gallup, Rasmussen 5/31-6/6)

Topics: National , poll

National

Gallup
5/31-6/06/10; 1,600 registered voters, 3% margin of error
Mode: Live telephone interviews
(Gallup release)

2010 Congress: Generic Ballot
46% Democrat, 46% Republican (chart)


Rasmussen
5/31-6/06/10; 3,500 likely voters, 2% margin of error
Mode: Automated phone
(Rasmussen release)

2010 Congress: Generic Ballot
44% Republican, 35% Democrat (chart)


OH: 2010 Sen, Gov (Rasmussen 6/3)

Topics: Ohio , poll

Rasmussen
6/3/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen: Governor, Senate)

Ohio

2010 Senate
43% Portman (R), 43% Fisher (D) (chart)

2010 Governor
47% Kasich (R), 42% Strickland (D) (chart)

Favorable / Unfavorable
Rob Portman: 49 / 23
Lee Fisher: 46 / 33
Ted Strickland: 45 / 49 (chart)
John Kasich: 50 / 27

Job Approval / Disapproval
Pres. Obama: 49 / 50 (chart)
Gov. Strickland: 43 / 55 (chart)


Unsupported DNC claims on health care misinformation

Topics: health care , Health care , Health Care Reform , misperception

In an op-ed published in late March, I predicted that misinformation about health care reform would persist after its passage:

At the White House signing ceremony for health care legislation on Tuesday, President Obama declared, "In a few moments, when I sign this bill, all of the overheated rhetoric over reform will finally confront the reality of reform." For Democrats nervous about political fallout from the bill in the November midterm elections, it's reassuring to imagine that the myths about the legislation -- that it provides free coverage to illegal immigrants, uses taxpayer money to subsidize abortions and mandates end-of-life counseling for the elderly -- will be dispelled by its passage.

But public knowledge of the plan's contents may not improve as quickly as Democrats hope. While some of the more outlandish rumors may dissipate, it is likely that misperceptions will linger for years, hindering substantive debate over the merits of the country's new health care system. The reasons are rooted in human psychology...

Surprisingly, however, DNC pollster Joel Benenson suggests in a new memo (PDF) that "misinformation about President Obama's health care reforms" is "giv[ing] way to Americans' real-life experience with it" (via Mike Allen):

Jb

However, none of the poll results cited in the memo pertain to misinformation, and I haven't seen any surveys that show a decline in misperceptions about reform. While it appears to be true, as Benenson argues, that a narrow majority of Americans oppose repealing the law, it's not clear that this finding has anything to do with a decline in misinformation. Indeed, his proposed mechanism ("real-life experience" with reform) is implausible since most of the changes in the law have not yet taken effect. Absent further evidence, the claim appears to be pure partisan bluster.

[Cross-posted to brendan-nyhan.com]


US: Oil Spill (ABC/Post 6/3-6)

Topics: National , poll

ABC News / Washington POst
6/3-6/10; 1,004 adults, 3.5% margin of error
Mode: Live telephone interviews
(ABC: story, results; Post: blog post)

National

How would you rate ____'s overall response to the oil spill in the
Gulf of Mexico?

The federal government: 2% Excellent, 26% Good, 37% Not so good, 32% Poor
The oil company BP: 1% Excellent, 15% Good, 27% Not so good, 54% Poor

Do you think the federal government should or should not pursue criminal charges against BP and other companies involved in the oil spill?
64% Should, 28% Should not

From what you've seen and heard, do you think that the oil spill in the Gulf of Mexico is:
73% A major environmental disaster
25% A serious environmental problem but not a disaster
2% Not too serious an environmental problem


US: Oil Spill (CBS 6/1-3)

Topics: National , poll

CBS News
6/1-3/10; 960 adults, 3% margin of error
Mode: Live telephone interviews
(CBS: story, results)

National

Would you favor allowing increased drilling for oil and natural gas off the U.S. coast, or do you think the costs and risks are too great?
40% Favor, 51% Costs and risks too great

Do you think the recent oil platform collapse and oil spill in the Gulf of Mexico is most likely an isolated incident, or mostly an indication of a broader problem with offshore drilling?
45% Isolated incident, 45% Broader problem

Do you approve or disapprove of the way ______ is handling the oil spill in the Gulf of Mexico ?
The Obama administration: 38% Approve, 44% Disapprove
BP, the company that owned the oil rig: 21% Approve, 68% Disapprove


IA: 2010 Gov (DMR 6/1-3)

Topics: Iowa , poll

Des Moines Register Selzer & Co. Iowa POll
6/1-3/10; 501 likely Republican primary voters, 4.4% margin of error
Mode: Live telephone interviews
(Des Moines Register release)

Iowa

2010 Governor: Republican Primary
57% Branstad, 29% Vander Plaats, 8% Roberts


PA: Corbett 49 Onorato 33 (Rasmussen 6/2)

Topics: Pennsylvania , poll

Rasmussen
6/2/10; 500 likely voters, 4.5% margin of error
Mode: Automated phone
(Rasmussen release)

Pennsylvania

2010 Governor
49% Corbett (R), 33% Onorato (D) (chart)

Favorable / Unfavorable
Tom Corbett: 59 / 25
Dan Onorato: 45 / 35


On 'Modeling' and Surveys

Topics: Internet Polls , Likely Voters , Michael Traugott , Mick Couper , Probability samples , Robert Groves

My National Journal column for this week looks at the "modeling" that underlies both online panel surveys and all pre-election polling. Please click through and read the whole thing.


SC: 2010 Gov Primary (PPP 6/5-6)

Topics: Governor , Primary , South Carolina

Public Policy Polling (D)
6/5-6/10; 998 likely Republican primary voters, 3.1% margin of error
Mode: Automated phone
(PPP release)

South Carolina

2010 Governor: Republican Primary
43% Haley, 23% Barrett, 16% McMaster, 12% Bauer


CA: 2010 Sen Primary (Field 5/27-6/2)

Topics: California , poll

Field Poll
5/27-6/2/10; 511 likely Republican primary voters, 4.5% margin of error
Mode: Live telephone interviews
(Field release)

California

2010 Senate: Republican Primary
37% Fiorina, 22% Campbell, 19% DeVore (chart)


NV: 2010 Sen, Gov (Mason-Dixon 6/1-3)

Topics: Nevada , poll

Mason-Dixon for the Las Vegas Review Journal
6/1-3/10; 625 likely voters, 4% margin of error
500 likely Republican primary voters, 4.5% margin of error
Mode: Live telephone interviews
(Senate, Governor)

Nevada

2010 Senate: Republican Primary
32% Angle, 24% Tarkanian, 23% Lowden (chart)

2010 Senate: General Election
44% Angle (R), 41% H. Reid (D) (chart)
42% H. Reid (D), 41% Lowden (R) (chart)
46% Tarkanian (R), 39% H. Reid (D) (chart)

2010 Governor: Republican Primary
47% Sandoval, 33% Gibbons, 6% Montandon (chart)

2010 Governor: General Election
44% R. Reid (D), 38% Gibbons (R) (chart)
51% Sandoval (R), 37% Reid (D) (chart)


Department of Irony: Markos Allows Himself to be Influenced by Rasmussen

Topics: Approval Ratings , House Effects , Obama

Recently, Markos Moulitas of DailyKos questioned if Rasmussen's polling was designed more to set a narrative than to accurately predict election outcomes.

I was thus highly amused by his appearance as a guest on ABC's This Week on June 6. Commenting on Obama's reactions to BP's oil spill, Markos stated: "I mean I don't think there's any doubt that the polling is slipping for Obama."

Really? Let's suppose that Markos is using Pollster's trend line averages as the evidence for this statement. The most current trend line as I write this on Sunday, June 6 does indeed show an apparent recent tick down in Obama's approval rating.
Obama_approval_6_6_10.pngHowever, as I have pointed out previously, movements in Obama's approval rating can be sensitive to the ubiquitous polling of Gallup, YouGov/Polimetrix and - you guessed it - Rasmussen. For whatever reasons - and there are potentially many - these pollsters tend to be the least favorable to Obama. I do not want to argue about the accuracy of these polls, I'll leave that to others. It is sufficient to note that these pollsters poll often and tend to be the least favorable to Obama and Democratic candidates.

The other national pollsters often run their polls on a regular monthly or so schedule, absent any major event to stimulate them to run an additional survey. At times, this causes lulls in the polling among these national pollsters. When a lull occurs, the Pollster trend line becomes dominated by the frequent pollsters and tends to move in a negative direction.

We are in one of these lulls right now. And as a consequence, the Obama trend line has moved in a negative direction. You can see this by using the "Tools" to remove Gallup, YouGov/Polimetrix and Rasmussen from Pollster's Obama job approval plot.

Obama_approval_6_6_10_modified.png

In fact, if you look closely at the recent polling, Obama's approval rating from all three of these polls has recently trended higher.

Obama Approval
Rasmussen: 5/23-25/10 (43%), 6/1-3/10 (48%)
Gallup: 5/25-27/10 (45%), 6/1-3/10 (48%)
YouGov/Polimetrix: 5/22-25/10 (44%), 5/29-6/1/10 (45%)

If these pollsters didn't consistently have a lower job approval rating for Obama compared to the other national pollsters, Obama's job approval trend line would actually be increasing!

The punch line is that Markos allowed himself to be influenced by what he claims to be a Rasmussen narrative. And the moral is that care should be taken in interpreting the Pollster trend lines.


 

MAP - US, AL, AK, AZ, AR, CA, CO, CT, DE, FL, GA, HI, ID, IL, IN, IA, KS, KY, LA, ME, MD, MA, MI, MN, MS, MO, MT, NE, NV, NH, NJ, NM, NY, NC, ND, OH, OK, OR, PA, RI, SC, SD, TN, TX, UT, VT, VA, WA, WV, WI, WY, PR