political polls

by

Why did Mitt Romney think he was a winner?

We all know that Mitt Romney was stunned when he lost.  It is said that he didn’t even have a concession speech written thus accounting for the delay between everyone including Fox calling the election and his speech.  And Logan Airport in Boston was crowded with private jets belonging to donors who were there to celebrate at Mitt’s cash bar.  But the party was spoiled because his internal polls were not only wrong, they were garbage.

Last night on Hardball, John Brabender, the Republican campaign official, did not answer Chris Matthew’s direct question as to how the Romney polls could have been so wrong.  This morning, Nate Silver, the man the Republicans trashed but who turned out to be correct, explains what happened.

In this morning’s FiveThirtyEight, Silver writes

Pollsters can expect to take their share of blame when their campaigns lose, and this year has been no exception. Not long after Barack Obama and Democrats had a strong night on Nov. 6, Republicans began to complain publicly that the polls conducted by their campaigns and by affiliated groups implied considerably more optimistic outcomes for them than actually occurred.

Perhaps these Republicans shouldn’t have been so surprised. When public polls conducted by independent organizations clash with the internal polls released by campaigns, the public polls usually prove more reliable.

Take, for example, the gubernatorial recall election in Wisconsin earlier this year. Independent polls had the Republican incumbent, Scott Walker, favored to retain his office by about six percentage points. A series of polls conducted for Democratic groups showed a roughly tied race instead.

Mr. Walker in fact won by seven points: the independent polls called the outcome almost exactly, while the internal polls were far from the mark.

Take note any Republicans reading this:  This is a Democratic error.  And, generally speaking, internal polls are not worth much as predictors of the outcome.

But when campaigns release internal polls to the public, their goal is usually not to provide the most accurate information. Instead, they are most likely trying to create a favorable news narrative – and they may fiddle with these assumptions until they get the desired result.

The Democratic pollster Harrison Hickman, who testified under oath in the federal case against John Edwards, put this bluntly, describing the release of internal polls to the news media as a form of “propaganda”:

Hickman testified that when circulating the polls, he didn’t much care if they were accurate. “I didn’t necessarily take any of these as for — as you would say, for the truth of the matter. I took them more as something that could be used as propaganda for the campaign,” the veteran pollster said.

Some reporters make the mistake of assuming that information is valuable simply because it is private or proprietary. But the information that makes it to the reporter’s ears, or into his in-box, may be something that the campaign wants him to hear or see.

During the campaign Republican polling data was released to the New Republic and subsequently to Silver.

Silver explains

In fact, Mr. Obama won all seven states, and by an average margin of 5.7 percentage points based on the ballots counted so far. (Several of the states have yet to certify their results.) Therefore, the polls were biased in Mr. Romney’s direction by nearly five percentage points, on average.

It should be mentioned that most of the independent polls this year were also slightly biased (in a statistical sense) toward Mr. Romney. In the same seven states, the final Real Clear Politics averages overrated Mr. Romney’s standing by 2.5 percentage points. The final FiveThirtyEight forecasts were less biased statistically, in part because our forecast model was designed to respond aggressively to movement in the polls in the closing days of the campaign, which favored Mr. Obama after Hurricane Sandy. Still, our forecasts in these seven states had a one-point bias toward Mr. Romney, on average, compared against the actual results.

The curious, but little known, thing about the Romney internal polls is that it appears they never projected him to win the Electoral College.

Further, the Romney campaign’s polls did not have him winning the Electoral College, as they had Mr. Romney behind in Ohio, Minnesota, Pennsylvania and Wisconsin, according to Mr. Scheiber. Assuming that the campaign also had Mr. Romney trailing in Nevada and Michigan, but leading in Virginia, Florida and North Carolina, then Mr. Romney would have been leading in states containing 261 electoral votes, but trailing Mr. Obama in states containing 271. Mr. Romney’s internal polls implied better chances for him than the public polls did – but if Mr. Scheiber’s reporting is right, they still had him as the underdog.

My husband points out that Mitt the self-described data guy seems to have only looked at his internal polling data.  Did he look at Real Clear Politics?  Or the daily reporting of poll results from the Daily Kos?  Or even FiveThirtyEight?  These were sources readily available to him.  He could just have had staff compile all the public polling these sources used each day in a special report just for him.

Internal polls are used for a lot a purposes other than showing a candidates standing in the race.  They can be used to measure effectiveness of message or standing among a specific demographic.  But they should be taken with caution by the candidate and certainly their public release can be dangerous.  In this case, the campaign also sold all the folks on Fox. Silver concludes

But most important, campaigns would be wise not to have their pollsters serve as public spokesmen or spin doctors for the campaign. Campaigns have other personnel who specialize in those tasks.

The role of the pollster should be just the opposite of this, in fact: to provide a reality check such that the campaign does not begin to believe its own spin.

Mitt didn’t write a concession speech because he believed his own spin.  And there will likely be only one picture of him in the Oval Office.

White House Photo

Photograph from the White House.

by

Why voting for Obama is important in blue states

If you are like me and live in a state that has already an insurmountable lead for President Obama’s re-election you might be tempted to vote third party, but it is still important for you to vote for Obama.  Why?  The popular vote total.  The pundits and headlines will continue to say the race is tied.  Forget the electoral college which in most estimates have Obama now over the 279 mark with some headed to 300.  No it is the popular vote where there is potential trouble.

Willard Mitt is too close for comfort. This morning Nate Silver puts it at 50.6 to 48.3 or a 2.3% margin for the President.  The margin of error is 2.1.  Much of the Romney vote comes from Red States and that is what is making it look close.  Unless Obama wins both the popular vote and the electoral college, the Republicans can complain about the results.  You know they will.  They are already beginning to blame Hurricane Sandy for the loss.

Of course, we won’t know until the votes are counted how things will turn out.  Polls can be wrong and folks like Nate depend on aggregating polls, but as an Obama supporter, I do feel hopeful.

Also it looks as if Elizabeth Warren will beat Senator Scott Brown.  Let’s hope that’s the last time I have to call him that!  And better yet, it is beginning to look like my old friend, Tim Kaine, will win in Virginia.

This shows President Clinton, President Obama and Tim Kaine.  This is an important sign:  The Democratic Senate candidate is not running from the President.  In a purple state.

So if you live in a blue state, don’t be thinking your vote for Obama doesn’t matter because it does.

by

About that Gallup poll

The most recent Gallup Daily Tracking polls have Mitt Romney up by 6 or points.  When I saw that I almost had a heart attack!  I mean how can that be when President Obama has a lead in all those individual state polls.  Then last night I read Nate Silver’s FiveThirtyEight blog post Gallup vs. the World and I calmed down.  I know that Romney supports are probably convinced that Nate manipulates everything so that Obama comes out ahead, but somehow I doubt that and you might want to actually read the post.  Silver begins

The Gallup national tracking poll now shows a very strong lead for Mitt Romney. As of Wednesday, he was ahead by six points among likely voters. Mr. Romney’s advantage grew further, to seven points, when Gallup updated its numbers on Thursday afternoon.

The Gallup poll is accounted for in the forecast model, along with all other state and national surveys.

However, its results are deeply inconsistent with the results that other polling firms are showing in the presidential race, and the Gallup poll has a history of performing very poorly when that is the case.

Other national polls show a race that is roughly tied on average, while state polls continue to indicate a narrow advantage of about two points for President Obama in tipping-point states like Ohio. The forecast has Mr. Obama as a narrow favorite in the election largely on the basis of the state polls. (You can read my thoughts here on the challenge of reconciling state and national poll data.)

Our database contains records from 136 distinct pollsters that have released at least one state or national survey at some point in this election cycle. Of those, 53 are active enough to have issued at least one survey since Oct. 1.

With so much data to sort through, it will usually be a counterproductive use of one’s time to get overly attached to the results of any one particular poll. Whether you look at the relatively simple averaging methods used by Web sites like Real Clear Politics, or the more involved techniques in the FiveThirtyEight forecast, the Gallup national tracking poll constitutes a relatively small part of the polling landscape.

After a lengthy explanation of how the data is used (I have to say it is long, but readable) Silver says

Over all, the Gallup daily tracking poll accounts for only about 3 percent of the weight [for the FiveThirtyEight calculation] in this stage of the calculation. The national tracking polls collectively, including Gallup, account for only about 10 percent of it. Most of the weight, instead, is given to the state polls.

Silver also recounts the history of the Gallup tracking polls (they have often missed the mark) and concludes

It’s not clear what causes such large swings, although Gallup’s likely voter model may have something to do with it.

Even its registered voter numbers can be volatile, however. In early September of this year, after the Democratic convention, Gallup had Mr. Obama’s lead among registered voters going from seven points to zero points over the course of a week — and then reverting to six points just as quickly. Most other polling firms showed a roughly steady race during this time period.

Because Gallup’s polls usually take large sample sizes, statistical variance alone probably cannot account these sorts of shifts. It seems to be an endemic issue with their methodology.

To be clear, I would not recommend that you literally just disregard the Gallup poll. You should consider it — but consider it in context.

The context is that its most recent results differ substantially from the dozens of other state and national polls about the campaign. It’s much more likely that Gallup is wrong and everyone else is right than the other way around.

Then this afternoon my other favorite wonk, Ezra Klein, also weighed in.

According to Real Clear Politics, Mitt Romney is, on average, up by one point in the polls. According to both Nate Silver and InTrade, President Obama has a better-than-60-percent chance of winning the election. I think it’s fair to say that the election is, for the moment, close.

But not according to Gallup. Their seven-day tracking poll shows Romney up by seven points — yes, seven — with likely voters. But he’s only up by one point with registered voters.

It gets weirder: Dig into the poll, and you’ll find that in the most recent internals they’ve put on their Web site  — which track from 10/9-10/15  — Obama is winning the West (+6), the East (+4), and the Midwest (+4). The only region he’s losing is the South. But he’s losing the South, among likely voters, by 22 points. That’s enough, in Gallup’s poll, for him to be behind in the national vote. But it’s hard to see how that puts him behind in the electoral college.

If Gallup is right, then that looks to me like we’re headed for an electoral college/popular vote split. Last night, I spoke with Frank Newport, editor-in-chief of Gallup, to ask him if I was missing something. He said I wasn’t. “That’s certainly what it looks like,” he says.

But Newport was cautious in interpreting his numbers. Gallup’s poll cheered Romney supporters because it showed Romney gaining ground even after the second debate. But Newport didn’t see it like that. Remember, he warned, it’s a seven-day poll. “I think we’re still seeing leftover positive support for Romney and I don’t think we’re seeing impact yet from the second debate,” he says.

It turns out the Gallup’s likely voter model includes a measure of enthusiasm which might explain why the large swings and the differences from the other polls.  Nate Silver is right:  it is the likely voter model.  He is probably also right when he said on the Daily Show that we tend to follow polls much too obsessively.  But I can’t help myself.

And if you support Obama you can take comfort in the figures posted late last night on FiveThirtyEight:  Obama 291.6 electoral votes with a 70.6 chance of winning.

by

Slick Willard

Mitt Romney shook his etch-a-sketch again last night.  My husband says we should call him Slick Willard.

Right after the debate ended last night I predicted that as badly as the President did last night that the fact checkers would find that Mitt made more misstatements of fact than the President.  That at least is happening.

The Daily Kos posted this list

The results of Wednesday night’s first presidential debate are in and it’s official: Mitt Romney won round one. He was aggressive, he was decisive, he delivered. Of course he also lied through his teeth for most of the debate.

Romney lied:

  • When he claimed that “pre-existing conditions are covered under my plan.” They’re not.
  • When he said that President Obama had “cut Medicare by $716 billion to pay for Obamacare.” Obama didn’t.
  • When he denied proposing a $5 trillion tax cut. He did.
  • When he said President Obama had “added almost as much to the federal debt as all the prior presidents combined.” Not even close.
  • When he resurrected “death panels.” That was called “one of the biggest whoppers of the night.”
  • When he stated that half the green energy companies given stimulus funds had failed. Only if three out of nearly three dozen is half.

Stay tuned. These just scratch the surface.

And Jackie Calmes wrote this in the New York Times

To viewers of the first presidential debate who knew Mitt Romney only from the Republican primary season or Democratic advertising, the man on the stage on Wednesday night must have sounded surprisingly moderate.

Tax cuts under a President Romney? On the whole, really wouldn’t be any. Government regulation? Good for business. President Obama’s education policies? Lots to like there. Mr. Obama’s health care plan? Would keep some of its key provisions.

Republicans are reveling in the instant analysis that Mr. Romney outscored Mr. Obama on Wednesday night, largely on style points for aggressiveness.

Yet many conservatives, who have long viewed Mr. Romney’s ideological commitment with some skepticism, might have been less than thrilled with his tone. Mr. Romney, in front of a national television audience, took the opportunity to present himself as a reasonable pragmatist who was willing to work across the aisle as governor of Massachusetts — risking criticism that this was another “Etch-A-Sketch” moment for him, potentially reviving accusations that he is a flip-flopper.

…

Questions from the moderator, Jim Lehrer, about whether there is too much government regulation seemed the softest of softballs to a conservative. Yet Mr. Romney’s answer was not exactly out of the Tea Party playbook.

“Regulation is essential,” he said emphatically. “You can’t have a free market work if you don’t have regulation. As a businessperson, I had to have — I needed to know — the regulations. I needed them there. You couldn’t have people opening banks in their garage and making loans. I mean you have to have regulations so that you can have an economy work. Every free economy has good regulation.”

He also said

Much like George W. Bush in 2000, Mr. Romney seized on the issue of education to signal — especially to women, who lopsidedly support Mr. Obama — that he supports a muscular role for the federal government. In Republican primary debates, the popular answer, and one Mr. Romney has floated in the past, is to call for abolishing the Department of Education.

Mr. Romney did say the primary role in education should be at the state and local level.

“But the federal government also can play a very important role,” he said, adding, “The federal government can get local and state schools to do a better job.”

As for federal spending, “I’m not going to cut education funding,” Mr. Romney said. “I’m planning on continuing to grow.”

One of his big tax cutting examples was to cut funding for Public Broadcasting by saying he is going to fire Big Bird.  James Lipton was on Hardball tonight pointed out that Romney once said that he liked to fire people – and he was a having a good time being the Bain executive and firing not only Big Bird, but Jim Lehrer the moderator.

So did Slick Willard’s act work?  Here are the first poll numbers from Ipsos/Reuters as posted on the Daily Kos.

The top-lines are encouraging for everyone—Mitt Romney improved his lot, while President Barack Obamadidn’t lose any ground. What does that look like? Like this:

Obama 48 (48) Romney 43 (39)

That four-point jump for Romney was real and significant and takes him from “getting blown out of the water” to merely “lagging quite a bit behind.”

…

First thing to note is that the post-debate sample has more independents and fewer Democrats than the pre-debate one. No, that’s not some major conspiracy. Please leave that shit for the other side. It just means that poll samples will float from poll to poll. Nothing nefarious about that.

So check it—Obama’s favorables are unchanged from before and after the debate, 56-44. But looking at the crosstabs, Obama stayed solid with Democrats, gained a tiny bit with Republicans, and … kicked ass among independents. Seriously, flipping his faves among independents from 46-54 to 54-46, a 16-point shift, is a pretty big deal.

Now look at Romney’s favorables. He definitely improved, from 46-54 to 51-49. He desperately needs those numbers to improve (and improve further) if he wants to be competitive. So, good news, right?

Well, Romney improved marginally with Democrats and stayed even with independents. So where did he improve? Among Republicans, where his “very favorable” jumped a solid 10 points, from 36 to 46 percent.

So is this what Romney set out to do? Solidify his GOP base and trick some Democrats into thinking that he wasn’t as horrible as they thought?

There is a very nice chart so click on the link.

Maybe Slick Willard won’t play after all.

by

More on Polls and other election stuff

After posting “reading the tea leaves”, I was checking out AlterNet and ran across several interesting posts.  First was an interesting piece by Joshua Holland about why polls drive us crazy. http://www.alternet.org/election08/99586/why_the_polls_drive_us_crazy_%28and_shouldn%27t%29/?page=1

Holland points out that the daily tracking polls and other national polls, while interesting, don’t mirror how the election will be won or lost.  He argues that one has to look at the individual states – particularly the swing states.

Remember that we don’t vote for president in the United States – we vote state by state for electors who vote for the president.  As I write, [September 20] new polls who Obama up by 9 points in Michigan, 5 points in Pennsylvania and a couple of points in Ohio – all crucial swing states.

He also points out a lot of experts are looking at who can get the voters to the polls on November 4 rather than who is leading in the polls.  So you combine all the new registered voters including new citizens and the new registrants under 35 and get them to the polls and that may be the election.  A lot of the under 35’s don’t have landlines and aren’t polled. 

And what is an election with out some fun?  This link has some great stuff. http://www.alternet.org/mediaculture/99057/the_10_most_talked-about_election_%2708_viral_videos_/?page=1  I think my favorites are the Obama/Lion King one by Jon Stewart and the McCain debating McCain one.  Several of the videos are very serious, however, including the one by doctors about the possible state of John McCain’s health.

A few other random thoughts for the day:  When will we get to see Sarah Palin’s  (and Todd Palin’s) tax returns?  Will anyone mention the Keating Five to John McCain?  And since when does thinking about an issue before making a decision as Obama is doing about the Bush-Paulson-Bernanke bail-out proposal a bad thing?  Finally, can the Red Sox clinch a playoff spot tonight?