March 22, 2009 - March 28, 2009


NY-20: Murphy 47, Tedisco 43 (DCCC)

Dates Unkown, Sample Size Unknown
Mode: Live Telephone Interviews

New York CD-20

"The DCCC's poll was taken earlier this week, before the Siena College poll released Friday that showed Murphy leading Tedisco by four percentage points, 47 percent to 43 percent."

We will update our NY-20 chart if/when we have more information for this poll.


"Outliers" from Spring Break Week

Topics: Outliers Feature

DemFromCT has fun with Pollster.com charts.

Andrew Gellman uses pre-election poll data to map the white vote by income, Kos sticks up for exit polls, Gelman replies.

J Street releases a new poll of American Jews, generating commentary from Shmuel Rosner, Isaac Luria, Marc Stanley, Joe Klein, Dana Goldstein and more.

Stu Rothenberg weighs in on the NPR/POS/GQR survey (via TQIA).

Mark Mellman sees evidence of growing hope.

Ron Brownstein argues that liberals are not as important to the Democrats as conservatives are to Republicans.

Nicole McCleskey aggregates polling data from the Western U.S.

Gary Langer reviews U.S. and Afghani public opinion on the Afghanistan War.

CQ Politics maps 2008 election results by congressional district (via Lundry).

Dana Houle adds value to Nate Silver's map of CD's where Obama over or under performed versus Kerry.

Dan Merkle and Murray Edelman review a classic exit poll experiment demonstrating that higher response rates can make results less accurate.

Barbara O'Hare and Diana Buck find that midwesterners are less likely to hang up on survey interviewers (via Lundry).

Knowledge Networks announces a new approach to sampling that will facilitate inclusion of cell-phone-only households in their representative internet panel.

Tom Jensen mourns the Ann Arbor News. RIP.

P.S. (nearly overlooked):  Calbuzz shares a chart of Arnold Schwarzenegger's historic job approval ratings

About Those Conflicting PA Polls

The contradiction between two polls on next year's Pennsylvania Republican senate primary in (conducted by Quinnipiac University and Franklin and Marshall) is the sort of thing I usually write about. Fortunately, in the midst of a week of light blogging, The Washington Post's Jennifer Agiesta Jon Cohen provides a very helpful analysis:

The two surveys offer a similar read on Specter's standing in the hypothetical contest: about three in 10 registered Republicans said they would vote for him in both polls. Specter is the better known figure and, as the incumbent, the one on whom voters are passing judgment at this early stage, so it makes sense that his standing would hold steady across polls.

The variation is all on Toomey's side of the coin. Despite his prior run for Specter's seat, Toomey is largely an unknown quantity - nearly three-quarters of Republicans in the Quinnipiac poll said they hadn't heard enough about him to have an opinion - suggesting his support in the two polls is driven more by question wording than strong sentiment for or against his candidacy.

So why did Toomey get 41% on the Quinnipiac survey but only 18% on Franklin and Marshall's poll? The most likely reason, Agiesta Cohen argues, is that the latter included the option to say, "or aren't you sure how you would vote."

That final phrase makes all the difference. Quinnipiac's poll offers voters what we in polling call a forced choice, mimicking the one they would face in the voting booth (unlike Nevada, Pennsylvania does not allow voters to cast a ballot for "none of these candidates"), and as such is a great measure for predicting voter behavior. Franklin and Marshall's question makes it easier for voters to say they haven't made up their minds, a perfectly valid response more than a year before anyone has to cast a ballot.

Some have made much of the fact that the Franklin and Marshall poll had a relatively small sample of Republicans (n=211) than the Quinnipiac poll (n=423). Yes, a smaller sample allows for the potential for more random sampling error than a larger sample, but this is the one sort of potential survey error we can quantify. In this case, the so-called margin of error is +/- 4.8% on the Quinnipiac Republican sample and +/- 6.7% on the Franklin and Marshall Republican sample. A bigger potential for error, to be sure, but the notion that anything less than 600 (or some other arbitrary number) is unreliable is a myth.

Gallup: Economic Outlook

In today's USA Today, Susan Page reports on the improvement in the consumer confidence measures tracked by the Gallup Poll:

For the past two weeks, the percentage of respondents in The Gallup Poll who say the economy is getting better has been steadily ticking up. Monday through Wednesday, 29% took the optimistic view — the highest number since July 2007.

That doesn't mean everyone's outlook is rosy — 66% continue to say the economy is getting worse — but it does signal a significant improvement in public attitudes after nearly two years of downbeat forecasts. The percentage seeing better times ahead has nearly doubled since March 9, when 15% said the economy was improving and 78% said it was getting worse.

The uptick over the last few months is also evident in the consumer confidence tracking conducted by ABC News and RasmussenReports. You can also see these trends as measured by multiple pollsters in our charts on how Americans rate the state of the economy and whether they think it is getting better or worse.

And speaking of the Gallup Poll, here are some Gallup releases from this week that we may have overlooked:

[Note: I changed this item's headline to better reflect the content of the USA Today article].

CT: U.S. Senate (Res2000/DailyKos 3/23-29)

Research2000 conducted on behalf of DailyKos.com (D)
3/23-29/2009; 600 likely voters, margin of sampling error +/- 4%
(post, results & crosstabs)


2010 U.S. Senate
Sen. Chris Dodd (D) 45%, Rob Simmons (R) 40%
Sen. Chris Dodd (D) 51%, Sam Caligiuri (R) 30%
Sen. Chris Dodd (D) 53%, Larry Kudlow (R) 31%

2012 U.S. Senate
Jodi Rell (R) 42%, Ned Lamont (D) 30%, Sen. Joe Lieberman (I) 25%
Jodi Rell (R) 43%, Dick Blumenthal (D) 28%, Sen. Joe Lieberman (I) 25%

MO: 2010 Senate (Wilson Res-R, 3/7-9)

Wilson Research Strategies (R), conducted on behalf of Sarah Steelman
3/7-9/2009; surveyed 600 likely voters, margin of sampling error +/- 4%
(via coverage and political notebook on KY3.com)


2010 U.S. Senate
Robin Carnahan (D) 47%, Roy Blunt (R) 44%
Robin Carnahan (D) 47%, Sarah Steelman (R) 39%

About the Murphy Trend in NY-20

Topics: NY-20 , Siena Institute

The final poll (release, crosstabs) by the non-partisan Siena Institute certainly gives Democrats reasons to be optimistic: The trend is all Murphy, with the Democrat improving his performance on each successive poll and now holding a slight (though not yet statistically significant) four-point lead (47% to 43%). The trend is consistent with earlier internal polls conducted by the two campaigns. If we focus only on the trend, it is hard not to consider Murphy a slight favorite, especially since the final Siena poll came out of the field with four days left until voting begins on Tuesday.


However, we also see three reasons for caution about these results:

  • The margin on the final Siena survey is still within the margin of error, which is to say we cannot be at least 95% confident that Murphy is leading. That does NOT mean the survey amounts to a "statistical tie." If this final snapshot were a perfect random sample of truly likely voters (a very big and essentially impossible "if" for any pre-election poll), we could be roughly 80% confident that Murphy really leads.
  • Predicting turnout in this sort of special election-- and thus selecting "likely voters -- is far more difficult than in a November general election. So there is more room than usual for the possibility that all of these surveys are measuring the wrong likely electorate.
  • Finally, as of this final Siena poll, Murphy has closed virtually all of Tedisco's early advantage in name recognition. Eight-six (86%) can now rate Murphy compared to 89% that can rate Tedisco, the the Democrat may have little room to grow over the last few days of the campaign.
Update: The Hill gets pushback on the poll from the Tedisco campaign and misinterprets the poll's 3.2 % margin of error (via Chris Good).  Remember, the margin of error applies to each percentage separately (i.e. 47% +/- 3% and 43% +/- 3%), not to the difference between the percentages.  

NY-20: Murphy 47, Tedisco 43 (Siena-3/25-26)

Sienna Research Institute, Siena College
3/25-26/09; 917 likely voters, +/- 3.2 margin of error
Mode: Live Telephone Interviews

New York CD-20

'09 Special General Election
Murphy (D) 47, Tedisco (R) 43, Sundwall (L) 2 (table-all polls)

From release:

As the special election in the 20th C.D. enters the final weekend, Democrat Scott Murphy has reversed a four-point deficit and turned it into a four-point lead over Republican Assembly Minority Leader James Tedisco.  Murphy leads 47-43 percent, having trailed two weeks ago by a 45-41 percent margin, according to a new Siena (College) Research Institute poll of likely voters.


"While the percentage of likely voters supporting Murphy has risen about three points per week for the last four weeks, the percentage supporting Tedisco has dropped three points.  In the last four weeks, Murphy turned a 12-point deficit into a four-point lead," said Steven Greenberg, spokesman for the Siena New York Poll.

(release, crosstabs)

14 States: Obama Approval (SurveyUSA-3/20-22)

3/20-22/09, 600 adults, 4% margin of error in each state
Mode: IVR

Obama Job Approval / Disapproval (1/20 - 1/21 results)

Alabama: 47 / 47 (48 / 45)
California: 67 / 28 (63 / 33)
Iowa: 57 / 40 (63 / 32)
Kansas: 55 / 40 (54 / 37)
Kentucky: 56 / 36 (57 / 37)
Massachusetts: 68 / 26 (66 / 29)
Minnesota: 61 / 29 (62 / 32)
Missouri: 57 / 39 (51 / 43)
New Mexico 61 / 35 (59 / 34)
New York: 72 / 23 (70 / 25)
Oregon: 62 / 31 (61 / 32)
Virginia: 55 / 35 (54 / 42)
Washington: 62 / 34 (64 / 32)
Wisconsin: 53 / 42 (60 / 37)

MA: 2010 Governor (7News/Suffolk Univ-3/17-20)

7NEWS/Suffolk University Poll
3/17-20/2009; 400 registered voters, margin of sampling error +/- 4.9%
(Press release, marginals, crosstabs, Boston Herald article)


Deval Patrick Favorable Rating
44% favorable, 43% unfavorable

Deval Patrick Reelect
34% deserves reelection, 47% time to elect someone else

Deval Patrick Job Rating
40% approve, 49% disapprove

2010 Governor Matchup
Deval Patrick 30%, Tim Cahill 35%
(Editor's note: text identified Cahill as State Treasurer but did not identify Patrick as a Democrat or Cahill as a Republican)

CA: State Propositions (PPIC - 3/10-17)

Public Policy Institute of California (PPIC)
3/10-17/2009; 2,004 adults, sampling error +/-2%; 987 likely voters, sampling error +/-3%
Mode: Telephone, live interviewers
(press release, full report)


From press release:

California's likely voters are divided on five of six propositions related to the state's budget crisis that will appear on the May special election ballot . . . Levels of support for Propositions 1A through 1E vary widely, but none has the approval of a majority of likely voters. However, in a signal of the mood of the electorate this year, an overwhelming 81 percent favor Proposition 1F, which would limit salary increases for state elected officials when the state faces a budget deficit.

Gov. Schwarzenegger Job Rating
32% approve, 56% disapprove
(Feb: 33% approve, 56% disapprove)

Pres. Obama Job Rating
71% approve, 20% disapprove
(Feb: 70% approve, 16% disapprove)

AR: 2010 Senate (PPP-3/20-22)

Public Policy Polling (D)
3/20-22/09; 600 registered voters, +/-4% margin of error
Mode: Automated-IVR
(summary, results)


Sen. Blanche Lincoln Approval Rating
45% approve, 40% disapprove

2010 Senate Matchups
Sen. Blanche Lincoln (D) 48%, Gilbert Baker (R) 37%
Sen. Blanche Lincoln (D) 46%, Tim Griffin (R) 37%

PA: 2010 Senate (Franklin & Marshall- 3/17-22)

Franklin & Marshall College Poll
3/17-22/2009, 662 adults, margin of sampling error +/- 4%
Mode: Telephone, live interviewers
Produced in conjunction with Philadelphia Daily News, WGAL-TV, Pittsburgh Tribune Review, WTAE-TV, WPVI-TV6/ABC, and Times-Shamrock Newspapers
(summary of findings)


Republican Primary (among n=211 registered Republicans)
33% Arlen Specter, 18% Pat Toomey, 2% Peg Luksik, 5% Other, 42% "arent sure how you'd vote"

Specter Job Approval
52% excellent or good, 37% only fair or poor
(2/2009: 43% excellent or good, 49% only fair or poor)

Specter Re-elect
40% deserves reelection, 46% time for a change

Obama Job Approval
60% excellent or good, 36% only fair or poor
(2/2009: 55% excellent or good, 36% only fair or poor)

Obama's Pollster

Topics: Barack Obama , Joel Benenson

Ben Smith caught a another small glimpse into the Obama polling operation buried a longer story in yesterday's Wall Street Journal on the administration's efforts to build support among bankers and financiers for the bank bailout plan:

Mr. Obama and his aides regularly and publicly criticized financial firms for buying private planes and redecorating offices and hosting lavish parties. The talk was fueled in part by the results of surveys by New York pollster Joel Benensen, commissioned by the Democratic Party, which Mr. Axelrod regularly reviews. The polls consistently showed that the public blames big financial firms for the current mess, and is hesitant to offer aid.

A New York Times profile of Axelrod a few weeks ago had a similar reference. Smith adds that Benenson "was was Obama's key pollster in the general election" and is "close to Axelrod," though points out that we cannot tell yet from FEC filings how much polling the DNC political operation is doing on behalf of the White House).

When the new reports appear, do not be surprised to see the Democratic Party conducting considerable polling and research on behalf of the White House, following the pattern of previous administrations. As I wrote back in January, such polling has become standard operating procedure for presidents going back to Kennedy. That activity has been chronicled in a series of articles in the journal, Public Opinion Quarterly. The most recent study, by Kathryn Dunn Tenpas and James A. McCann (abstract, full text) found that presidents since Carter "do not vary significantly in the average amount spent per month on polls" and that such spending on internal polling increases throughout the term and especially "during the most intense months of a presidential reelection campaign."

Spring Break Housekeeping

Topics: Housekeeping

A quick update and apology for the slow pace of analysis posts over the last few days. This week is spring break for my children, and I have been trying to combine light blogging with a family visit (and rediscovering the challenge of finding uninterrupted time in the company of precocious 4 and 6-year-olds). I'll be back to full speed next week.

PA: 2010 Senate (Quinnipiac 3/19-23)

The Quinnipiac University Poll
3/19-3/23/2009; 1,056 registered voters, +/- 3% margin of error; 423 registered Republicans, +/- 4.8% margin of error
Mode: Live Telephone Interviews

Pennsylvania 2010 Senate

Republican Primary
Specter (R-i) 27%, Toomey (R) 41%

Specter Favorable Rating
All voters: 45% favorable, 31% unfavorable
Among Republicans: 29% favorable, 47% unfavorable

Specter Job Rating
All voters: 50% approve, 38% disapprove
Among Republicans: 36% approve, 52% disapprove

Specter Reelect
All voters: 38% deserves to be reelected, 41% does not
Among Republicans: 30% deserves to be reelected, 53% does not

Barack Obama Job Rating
All voters: 61% approve, 30% disapprove
(Feb 2009: 63% approve, 22% disapprove)

Job Approval, Outliers and Perspective

An absurd amount of attention has been given today to a new Zogby internet poll. In a very well managed PR campaign, Zogby leaked the results last night before releasing them a bit after noon today, while also debuting a Zogby presence on Twitter. A little Googling will turn up many hits citing the not-yet-released-at-the-time results. Nate Silver at fivethirtyeight.com helped the poll get attention by attacking it before it was even released. The right is delighted-- "Obama approval drops below 50%!!" The left (with Silver's help) denounces the poll. Twitter is abuzz on both sides. And media, both old and new, couldn't contain their chatter over the results. (My favorite, the Boston Herald's Joe Dwinell's lede "The honeymoon is over, a national poll will signal today as President Obama's job approval stumbles to about 50 percent over the lack of improvement with the crippled economy." The fourth paragraph notes that "Some polls show Obama coasting with a 65 percent job approval, but not in Zogby's tally.") 

It takes five seconds to put the new poll in perspective. Take that long to look at the chart above. The Zogby poll stands out pretty clearly in the chart, no? 

To make a lot of the Zogby poll is to deliberately ignore the context in which it appears. Yes, the left is correct that it is an outlier. A huge one. The right looks desperate or ignorant by embracing this result as meaningful. 

But rather than suppress the poll or ban it from polling analysis, let's just put it in the chart and let the data speak! No stats needed to get the point. 

Poll results are far more meaningful when we look at them with a bit of perspective. The chart also makes clear how the Gallup and Rasmussen daily tracking polls differ from one another as well. Gallup's daily tracker consistently results in higher approval ratings than do non-daily national polls. Rasmussen consistently results in lower approval ratings than do non-daily national polls. But put them all together and we get a trend estimate based on all the polls that matches the trend for conventional non-daily polls quite well. If we pick only Gallup or only Rasmussen, we bias our understanding of the state of public opinion. Not by a huge amount, but by a persistent two-or-three points up or down compared to the overall trend or to the non-daily polls. This is no surprise. House effects, the tendency of polling organizations to produce modest differences from one another, are well known and much written about. By putting all the data in the chart for everyone to see we let these house effects stand out in an obvious way. 

If someone still wants to cherry pick a result to suit their partisan preferences, then fine. That's called politics, duh! I'm not against it. But let's not confuse willful distortion for partisan purposes with analysis of what the data actually show. 

The Zogby internet polls have a considerable history that I won't repeat here. The point is not to condemn them but to put them in perspective. That done, I don't think much more comment in required.

US: AIG, et al (Gallup-3/21-22)

USA Today / Gallup
3/21-22/09; 1,004 adults, 3.1%
Mode: Live Telephone Interviews


Are you satisfied or dissatisfied with the way each of the following has handled this matter?

    54% Satisfied, 39% Dissatisfied

    28% Satisfied, 54% Dissatisfied

    26% Satisfied, 65% Dissatisfied

    AIG Management
    12% Satisfied, 80% Dissatisfied

In your view, which of the following would be the best way to recover the bonus money - [ROTATED: have Congress pass a new law imposing heavy taxes on bonuses paid to executives at companies that receive bailout money, ask the AIG executives to voluntarily return the money, not pass a new law but try to recover the money through legal actions or as a condition of payment of additional bailout money]?

    25% New law to tax bonuses
    27% Ask to return voluntarily
    26% Try to recover through legal action
    12% Should not return any


NYC: 2009 Mayor (Quinnipiac-3/17-22)

Quinnipiac University
3/17-22/09; 1,142 registered voters, 2.9% margin of error
766 registered Democrats, 3.5% margin of error
Mode: Live Telephone Interviews

New York City

Favorable / Unfavorable
Mayor Bloomberg (i): 62 / 31 (chart)
William Thompson (D): 25 / 5
Anthony Weiner (D): 31 / 13

Bloomberg Job Approval
64% Approve, 28% Disapprove (chart)

'09 Mayor - Democratic Primary
Weiner 30%, Thompson 23% (chart)

'09 Mayor - General Election
Mayor Bloomberg 46%, Weiner 36% (chart)
Mayor Bloomberg 49%, Thompson 35% (chart)


US: AIG, et al (CBS-3/20-22)

CBS News
3/20-22/09; 949 adults, 3% margin of error
Mode: Live Telephone Interviews


Obama Job Approval
64% Approve, 20% Disapprove (chart)
Dems: 87 / 2 (chart)
inds: 60 / 23 (chart)
Reps: 35 / 50 (chart)

Economy: 61% Approve, 29% Disapprove (chart)
Situation with AIG: 41% Approve, 42% Disapprove

Congressional Job Approval
30% Approve, 56% Disapprove (chart)

How much confidence do you have in Treasury Secretary Tim Geithner's ability to handle the nation's financial crisis -- a lot, some, not much, or none at all?

    54% A Lot / Some
    35% Not Much / None At All

Should the Obama Administration have prevented AIG from paying the bonuses, or would this have been too much government involvement in how the company is run?

    56% Yes, should
    34% No, too much involvement

(story, results)

US: Youth Politics (DemCorps-2/25-3/11)

Democracy Corps (D) /
Greenberg Quinlan Rosner (D)
2/25 - 3/11/09; 606 adults
weighted: 255 cell phone interviews, 242 internet interviews, 109 landline interviews
Mode: Live Telephone Interviews, Internet


"Democracy Corps and Greenberg Quinlan Rosner's first post-election survey of youth shows the Republican Party growing more and more irrelevant to America's young people. In marked contrast, young people's support for the President has expanded beyond the 66 percent support they gave him last November. However, progressives have work to do among these voters--and would be voters--as well, as this survey signals insufficient enthusiasm for participating in the 2010 elections."


US: 2010 Gov, Sen (Siena-3/16-18)

Siena College
3/16-18/09; 626 registered voters, 3.9% margin of error
Mode: Live Telephone Interviews

New York State

Favorable / Unfavorable
Pres. Obama: 70 / 23 (chart)
Gov. Paterson: 29 / 58 (chart)
Sen. Gillibrand: 26 / 20 (chart)
Andrew Cuomo: 68% / 17%
Rudy Giuliani: 58 / 36
George Pataki: 49 / 41

Job Approval / Disapproval
Gov/ Paterson: 19 / 78 (chart)

'10 Governor - Democratic Primary
Cuomo 67%, Paterson 17% (chart)

'10 Governor - General Election
Giuliani 56%, Paterson 33% (chart)
Cuomo 51%, Giuliani 41% (chart)

'10 Senate - General Election
Gillibrand 47%, King 23% (chart)
Gillibrand 41%, Pataki 41%

(release, crosstabs)

US: Obama Job Approval (Harris-3/9-16)

Harris Interactive
3/9-16/09; 2,355 adults
Mode: Online


Obama Job Approval
55% Excellent/Pretty Good, 45% Only Fair/Poor (chart)

Dems: 87 / 13 (chart)
inds: 51 / 49 (chart)
Reps: 18 / 82 (chart)