Nate’s Numbers: the numbers converge
Posted: November 5, 2012 Filed under: 2012 elections, open thread, polling | Tags: Nate Silver, Number Krunching, open thread, Polling, polls, Punditry, Sam Wang, Statistics 60 Comments »
I’ve spent all my professional life drenched in numbers and statistics so Nate Silver’s numbers fascinate me. It’s probably the same reason they drive Republicans and pundits to distraction. Unraveling trend is easier with numbers than hateful, wishful thinking motivated by political piety. So, Karl Rove got on TV–probably trying to save what’s left of his credibility–saying that Romentum was stopped by Sandy. Romentum was a bit of canard and it turns out so is Sandy. Silver tries to discern the possible factors behind the recent numbers and looks at the Sandy Factor. That’s a relatively simple task for any one with a database and a background in trend analysis.
When the hurricane made landfall in New Jersey on Oct. 29, Mr. Obama’s chances of winning re-election were 73 percent in the FiveThirtyEight forecast. Since then, his chances have risen to 86 percent, close to his highs on the year.
But, while the storm and the response to it may account for some of Mr. Obama’s gains, it assuredly does not reflect the whole of the story.
Mr. Obama had already been rebounding in the polls, slowly but steadily, from his lows in early October — in contrast to a common narrative in the news media that contended, without much evidence, that Mr. Romney still had the momentum in the race.
Moreover, there are any number of alternatives to explain Mr. Obama’s gains before and after the storm hit.
- Mr. Obama was adjudicated the winner of the second and third presidential debates in surveys of voters who watched them.
- The past month has brought a series of encouraging economic news, including strong jobs reports in October and last Friday.
- The bounce in the polls that Mr. Romney received after the Denver debate may have been destined to fade in part, as polling bounces often do following political events like national conventions.
- Democrats have an edge in early voting based on states that provide hard data about which party’s voters have turned out to cast ballots. Some voters who were originally rejected by the likely voter models that surveys apply may now be included if they say that they have already voted.
- Both Mr. Obama and Mr. Romney have been running lots of advertisements, which could have some effect, especially in the swing states.
- Mr. Obama’s voter-targeting operation may in fact be stronger than Mr. Romney’s and may have begun to show up in the polls.
- Mr. Obama’s approval rating is at 49 or 50 percent in many surveys, a threshold that would ordinarily predict a narrow re-election for an incumbent.
- Some elections “break” toward one or another candidate at the end as undecided voters tune in and begin to evaluate their decision.
Each of these hypotheses could merit its own article. But the point is that the causes for Mr. Obama’s gain in the polls are overdetermined, meaning that there are lot of variables that might have contributed to the one result.
If I had told you in January that Mr. Obama’s approval rating would have risen close to 50 percent by November, and that the unemployment rate would have dropped below 8 percent, you likely would have inferred that Mr. Obama was a favorite for re-election, with or without a hurricane and what was judged to be a strong response to it.
Whatever the causal factors, Nate’s numbers look good for the President. Sam Wang–a Princeton number kruncher–says it not only looks like the President will hold his office but that the US Senate might see a Democratic Pick up of two. This is an important firewall for those of us that care about things like Supreme Court appointments and getting rid of the filibuster silliness that has allowed the Republicans to basically thwart governing. Dems may pick up Nebraska and Pennsylvania.
Rather than responding to the analysis, the Republicans continue to attack Nate Silver the man. You may recall this Krugman piece last week about The War on Objectivity.
Brad DeLong points me to this National Review attack on Nate Silver, which I think of as illustrating an important aspect of what’s really happening in America.
For those new to this, Nate is a sports statistician turned political statistician, who has been maintaining a model that takes lots and lots of polling data — most of it at the state level, which is where the presidency gets decided — and converts it into election odds. Like others doing similar exercises — Drew Linzer, Sam Wang, and Pollster — Nate’s model continued to show an Obama edge even after Denver, and has shown that edge widening over the past couple of weeks.
This could be wrong, obviously. And we’ll find out on Election Day. But the methodology has been very clear, and all the election modelers have been faithful to their models, letting the numbers fall where they may.
Yet the right — and we’re not talking about the fringe here, we’re talking about mainstream commentators and publications — has been screaming “bias”! They know, just know, that Nate must be cooking the books. How do they know this? Well, his results look good for Obama, so it must be a cheat. Never mind the fact that Nate tells us all exactly how he does it, and that he hasn’t changed the formula at all.
This is, of course, reminiscent of the attack on the Bureau of Labor Statistics — not to mention the attacks on climate science and much more. On the right, apparently, there is no such thing as an objective calculation. Everything must have a political motive.
This is really scary. It means that if these people triumph, science — or any kind of scholarship — will become impossible. Everything must pass a political test; if it isn’t what the right wants to hear, the messenger is subjected to a smear campaign.
Any kind of scholarship has become challenging under Republican fanaticism as witnessed by the attacks on evolution, climate change, and the economic analysis that shows there is no such thing as an economic benefit created by low marginal tax rates for the rich. Just ask scientists trying to get grants to study things like stem cell research. Fox gets people to believe anything. Science causes them to retreat to their medieval churches and scream about intervention by celestial beings. (So, if gawd caused Sandy to take out NJ and NY because of Gay Rights, does this mean gawd caused Sandy to give Obama momentum? Ask Grand Inquisitor Pat Robertson about that one.)
Yes, Nate’s numbers took another upward tick this morning. He also believes that Obama will take the popular vote which should be dismaying to all those journalists that keep wanting to turn this into a white knuckle election.
Silver also added to Obama’s likely number of electoral votes on Monday. He now sees the president winning 307.2 to 230.8 for Mitt Romney, a tiny tick higher than he saw the race on Sunday.
He also sees Obama capturing the popular vote, taking 50.6 percent to Romney’s 48.5.
Rachel Maddow insists the Republicans see the numbers and actually believe that their man Mittster is a goner. The blame game has already begun. Haley Barbor blames Sandy. Lindsey Graham is actually looking at numbers and notices that that demographics are not in their favor.
QUOTE OF THE DAY: ”If I hear anybody say it was because Romney wasn’t conservative enough I’m going to go nuts. We’re not losing 95% of African-Americans and two-thirds of Hispanics and voters under 30 because we’re not being hard-ass enough.”
– Politico quotes Sen. Lindsey Graham (R-SC), saying that demographics would be the only reason for a hypothetical Mitt Romney loss Tuesday.
Yeah, the blame game has begun and the election isn’t even over. Funny he should bring up Hispanic and black voters. Latino Decisions found that Hispanics support President Obama in historic numbers — 73 percent. They believe that’s enough to carry President Obama to victory in four swing states and ultimately to win re-election. Those four swing states are Nevada, Colorado, Virginia, and Florida.
This is closer to the truth. Republican policy statements as expressed by “severely conservative” Mitt have driven off the young, hispanics, blacks, and women. I had MSNBC on mute most of the weekend when they were following the candidates around. All you have to do is look at the people used as back drops for candidates’ speeches to realize who really is on the losing side of US demographics. This is part of the numbers game. You can’t build momentum or fantasize a trend based on capturing an ever decreasing slice of the American Pie.
Which brings me to the post election deconstruction that should occur in the Republican party. When will the actually give up on the Southern Strategy? We’ve seen
more race baiting in this election that I’ve frequently wondered if the ghost of George Wallace is running the Romney campaign. We’ve seen attacks on women’s rights that make me wonder if Republicans know that women got the right to vote. We’ve seen support of policies that are based on show us your papers that remind me of old NAZI movies. You can’t attack and demonize the majority of the electorate and expect the numbers to come in for you. You also can’t build policy on attacking scientific models and theories. The Republican party has definitely shown that its plan for America is to try to recreate the past no matter what the cost.
All I can say is go Nate go! Win one for Ada Lovelace and the country. There are easy ways to figure out which events contribute to trend and what’s just random. People should pay more attention to Nate Silver and a lot less attention to the likes of Karl Rove and Haley Barbour. Nate Silver bet Joe Scarborough $2000 that his analysis was right saying “Occam’s Razor: Pundits are useless”. That’s something I completely grok.
“I think I get a lot of grief because I frustrate narratives that are told by pundits and journalists that don’t have a lot of grounding in objective reality,”
Remain Calm …
Posted: October 29, 2012 Filed under: 2012 elections, 2012 presidential campaign | Tags: polls 32 Comments »The latest republican trick is one again to attack the polls, lie about the polls, and make up shit. Here’s some great pollsplaining from one of the great
nerds of statistics and polls Sam Wang.
First, thing up … there is no Ro-mentum and Obama’s lead is static.
In either case, the overall picture is the same: a narrow Obama lead that is static – or perhaps widening. There is no evidence for Ro-mentum.
I’ve been pulling my hair out over the total lack of understanding by a lot of media punditry over white noise or random variation. I think it’s ignorance and not deliberate. Any series of numbers reported over time will go up or down randomly because that’s just the behavior of a variable reported over time. That’s when you have to apply the idea of what’s the top and bottom border of are representing random. This is measured by Standard Deviation and it’s what underlies the idea of being within the margin of error. You have to see fairly clear and sustained patterns in order to call it not random. That’s why you can’t hang on every up and down. Basically, it takes 7 ups or 7 downs to bust out of the three standard deviation realm of what’s normal. Take a look at the graph over there. It goes up and it goes down. The deal to figure out is what is ‘statistically’ significant. You can’t hang on every blip of every poll.
Poll correctness has a lot to do with the way the sample is treated. That’s the basis of the guess of how many republicans you should sample or democrats in the overall sample. You have to estimate–base on historical patterns or something else–what the patterns of voter turn out will be. That’s what most of the complaints about polls tend to reflect. These assumptions lead to weighting the samples differently. That’s why a lot of folks do meta-analysis or look at a poll of polls. This has to do with the law of large numbers which tells us that averages of averages tend to reflect reality. But, the core reality is that pollsters make money by producing accurate pictures and not by telling people what the want to hear. One legitimate concern is if you should look at all voters or likely voters. A lot of the rest of the so-called sampling biases that pundits scream about tend to be based more on wishful thinking than anything. There are some differences in terms of how statistics are used. Both Gallup an Rasmussen are median-based polls and this can make a difference when comparing to a poll that’s not based on the same metrics.
Wang points to the echo chamber and the Romney minions that are focusing on single polls and screaming or clapping.
Paul Krugman is calling out National Review Online for their attempted takedown of Nate Silver for biased methods and somehow cooking the books. Krugman writes:
This is, of course, reminiscent of the attack on the Bureau of Labor Statistics — not to mention the attacks on climate science and much more. On the right, apparently, there is no such thing as an objective calculation. Everything must have a political motive.
Now more commentators on the right, including Jay Cost (The Weekly Standard) and Jennifer Rubin (Washington Post), are getting in on the act. Wow, dogpile on the rabbit!
A popular approach to undermining technical knowledge is to throw mud, assert expertise, make picky points, and sow doubts among the less savvy. In this case, what’s the argument? The NRO writer, Josh Jordan, makes this core criticism:
When you weight a poll based on what you think of the pollster and the results and not based on what is actually inside the poll (party sampling, changes in favorability, job approval, etc), it can make for forecasts that mirror what you hope will happen rather than what’s most likely to happen.
Jordan sounds like many partisan polling enthusiasts – on both sides. However, his style of poll-dissection can very easily lead a person astray. The human mind has a large capacity for finding reasons to reject a piece of disagreeable evidence. I’ve written about this in the context of how people form false beliefs in politics (“Your Brain Lies To You,” NYT, June 27, 2008). Polling internals lend themselves very well to such “motivated reasoning.” It is always possible to find something not to like in a poll. This is why I discourage all of you from chewing over single polls.
Part of the reason that conservatives are hating on Nate Silver is that they aren’t getting the results they want. It’s the idea that if you scream loud enough, you can get things to change. Check out Silver’s latest. Romney’s chance at getting the electoral college is less than 30% which is basically where it’s been for a very long time . A few up blips do not change a long term trend unless they occur over a period of time.
Any way, calm down and let the metrics be with you. Here’s some interesting snapshots of trends on a state by state basis.
More Endorsements
Posted: October 25, 2012 Filed under: 2012 elections, 2012 presidential campaign | Tags: endorsements, polls 80 Comments »The last legs of presidential campaigns are filled with major endorsements and last minute polls. The WAPO editorial board and former Bush SOS
General Colin Powell have both endorsed the president.
Powell criticized Romney’s foreign policy as inconsistent and questioned the former Massachusetts governor’s ability to address the deficit and looming defense cuts.
“I’m not quite sure which Governor Romney we’d be getting with respect to foreign policy,” Powell said, calling Romney’s foreign policy “a moving target.”
As for the U.S. budget, he added: “It’s essentially, let’s cut taxes and compensate for that with other things, but that compensation does not cover all the cuts intended or the expenses associated with defense.”
Powell has been critical of Romney’s foreign policy advisers and has taken issue with the former business executive’s stance on countries such asRussia.
A moderate Republican, Powell served under President George W. Bush. Some of Romney’s advisers are more conservative veterans of the Bush administration.
“There’s some very, very strong neo-conservative views that are presented by the governor that I have some trouble with,” Powell said on CBS.
WAPO’s endorsement and the Powell endorsement were really no surprise.
We come to that judgment with eyes open to the disappointments of Mr. Obama’s first term. He did not end, as he promised he would, “our chronic avoidance of tough decisions” on fiscal matters. But Mr. Obama is committed to the only approach that can succeed: a balance of entitlement reform and revenue increases. Mr. Romney, by contrast, has embraced his party’s reality-defying ideology that taxes can always go down but may never go up. Along that road lies a future in which interest payments crowd out everything else a government should do, from defending the nation to caring for its poor and sick to investing in its children. Mr. Romney’s future also is one in which an ever-greater share of the nation’s wealth resides with the nation’s wealthy, at a time when inequality already is growing.
Even granting the importance of the fiscal issue, a case might still be made for Mr. Romney if Mr. Obama’s first term had been a failure; if Mr. Romney were more likely to promote American security and leadership abroad; or if the challenger had shown himself superior in temperament, capacity and character. In fact, not one of these is true.
The Poll Front still shows the President is likely to win the electoral college and thus, the election. A Time poll shows Obama up 5 points in the important state of Ohio which will probably determine the election result.
Buoyed by early voting in his favor, Barack Obama leads Mitt Romney by five points in the pivotal state of Ohio, according to a new TIME poll.
Counting both Ohioans who say they will head to the polls on November 6, and those who have already cast a ballot, Obama holds a 49% to 44% lead over Romney in a survey taken Monday and Tuesday night.
The poll’s margin of error is plus or minus three percentage points.
The poll makes clear that there are really two races underway in Ohio. On one hand, the two candidates are locked in a dead heat among Ohioans who have not yet voted but who say they intend to, with 45% of respondents supporting the President and 45% preferring his Republican challenger.
Even weird ol’ Joe Scarborough says: Two new polls scream ‘advantage Obama’.
Two polls released yesterday show President Obama stubbornly clinging to his electoral advantage. TIME Magazine released a new Ohio poll that has Mitt Romney trailing in the Buckeye State by 5 points. Last week’s NBC News/Wall Street Journal/Marist survey also had Romney behind by 5.
TIME’s poll should rattle the nerves of Romney supporters because the results run contrary to Team Romney’s ongoing claim that their internal polls show a dead heat in the Buckeye State. Maybe that’s the case among voters planning to go to the polls on election day but it looks like early voters are tilting dramatically in the president’s direction. If the TIME poll is accurate, it means Mitt Romney will have to grab most of Ohio’s remaining undecided voters if he wants to win this critical battleground state.
PPP released a Nevada survey yesterday that also shows President Obama holding a lead in this key swing state that remains outside the margin of error. Like Ohio, Nevada remains stubbornly in the Obama column. While Mitt Romney has made up ground in the three Southern swing states of Florida, North Carolina and Virginia, voters in Ohio, Nevada and Wisconsin seem do not seem inclined to be easily swept into Romney’s camp.
Obama appears to lead in Virginia also.
A new Public Policy Polling survey in Virginia, conducted on behalf of Health Care for America Now, finds Barack Obama expanding his lead in the aftermath of his debate victory Monday night. He now has 51% to 46% for Mitt Romney, up from a 49/47 advantage last weekend.
Key findings from the survey include:
-Obama’s seen a 7 point net improvement in his favorability rating among Virginia voters from a -3 spread last week (48/51) to now +4 at 51/47. Romney’s numbers have headed in the other direction. He’s dropped 7 points from a +2 spread on our last poll (49/47) to now -5 at 46/51.
-Voters trust Obama more than Romney on several major issues in the election. Those include who voters think will stand up for the middle class (52/44) and who they think will do more to protect Medicare (50/46).
-Obama leads 57/41 with women, 88/8 with African Americans, and 53/42 with young voters. Romney has a 50/45 advantage with men, a 57/41 one with whites, and a 57/41 edge with seniors. Obama’s moved from being slightly behind with independents last week at 45/44 to now slightly ahead at 47/45.
One of the weirdest observations that I’ve seen in awhile is how the US election maps seem to reflect the same kind of boundary lines we saw when we were fighting over the issue of slavery. Even actual Confederate hold outs see this. Steve Pinker has some interesting thoughts on the redness and blueness of some states. I can tell you, it’s not pleasant to live in a red state if you’re a woman, a child, or a minority. There’s an emphasis on a plantation style economy, education goals that are out of step with modernity, and ensuring the primacy of white, christian, men. Abortion and birth control restrictions, ensuring the taxes don’t impact the rich, and enacting radical religious views on all kinds of things have been their priorities. Your only hope is to stay in a red state’s biggest city or move.
Broadly speaking, the Southern and Western desert and mountain states will vote for the candidate who endorses an aggressive military, a role for religion in public life, laissez-faire economic policies, private ownership of guns and relaxed conditions for using them, less regulation and taxation, and a valorization of the traditional family. Northeastern and most coastal states will vote for the candidate who is more closely aligned with international cooperation and engagement, secularism and science, gun control, individual freedom in culture and sexuality, and a greater role for the government in protecting the environment and ensuring economic equality.
So, this election is important. We can’t afford to have these extremist religious agendas dictating our national policy. I say that as I listen to many of my friends who are rape survivors being traumatized all over again by troglodyte white, extremist christian, men who identify more with a fertilized eggs than women and children. We need to send the entire Republican agenda and its goosestepping arm of religious freaks into oblivion. PERIOD.














Recent Comments