Friday, October 26, 2012

Last Meme Standing: Why Obama and Romney have Different Strategies


We’re just eleven days away from the Presidential Election, or more accurately, eleven days away from the end of voting.  The news says the race is tight, but you can still find a wide range of outcomes predicted by savants and would-be wizards.  While I have the same expectation for the outcome that I have published since August, I also recognize that a great many things can still happen to change that outcome and decide the margin.  What I find most interesting at this point, is the basic theory behind each candidate’s strategy.

First, the Obama campaign.  After winning the 2008 election fairly easily, the Obama Camp entered this year with understandable confidence.  With no primary competition in the Spring, and generally high likability all year long, President Obama did not appear to expect serious difficulty in earning a second term.  But as the Spring turned into Summer, the race began to tighten, and by October it was clear Obama would have to fight to win a second term.  What started as a relaxed attitude became tense as Obama aides and campaign directors found themselves looking up at Romney in national polls.  The narrative from Obama’s campaign now is simple – stay on message and protect the firewall.  That word, ‘firewall’, shows up a lot.  It’s the idea, also voiced in general over the past couple months, that Obama controls too many states for Romney to win in the Electoral College.  They say that if Obama simply holds what he has now, he wins.  No worry about the national polls, it’s all about the states. 

Next, the Romney campaign.  Romney understood going in that he’d have an uphill fight, but voter displeasure about the economy and Obama’s failed promise of bipartisanship gave him hope that he could win the election.  Romney’s team considered the election as an asymmetric campaign, where Romney first had to establish himself as a viable candidate in voters’ eyes, then prove he was a better choice than the incumbent.  The early summer looked daunting, but Romney remained disciplined and made a number of important decisions which were designed for long-term effect, rather than short-term splash.  This was why Romney enjoyed no bounce from his convention, yet exploded in support after the first debate.  Romney’s strategy worked to first consolidate his electoral base, then build a national appeal to open opportunities. 

With polls in disagreement and less than two weeks to go, these two concepts of the election now run head-on into each other.  If Obama is right, Romney will enjoy some good poll numbers but will lose in just enough swing states to give the incumbent four more years.  If Romney is right, then President Obama will appear to be closer than he really is, right up to Election Night, when the actual results will herald the end of the Obama Administration after this year.  The salient point, in my opinion, to this election, is the fact that no political firewall exists.

There is no shortage of punditry to promise this outcome or that, but in the end the election is numbers-driven  And it’s in the numbers where Mister Obama’s firewall proves illusory.

Let’s start with the national polls.  Rather than go through all of them, let’s look at the most prominent polls with polls in September and October.  To keep it simple, let’s look at Obama’s support last month and now:

Poll                        
Rasmussen:  Sept 16 at 45%, Oct 24 47%, gain of 2
Gallup:  Sept 27 at 49%, Oct 25 at 47%, loss of 2
ABC News/WaPo:  Sept 29 at 49%, Oct 23 at 48%, loss of 1
NBC News/WSJ:  Sept 30 at 49%, Oct 20 at 47%, loss of 2
FOX News:  Sept 26 at 48%, Oct 9 at 45%, loss of 3

Now let’s look at Romney’s support last month and now:

Poll
Rasmussen:  Sept 16 at 47%, Oct 24 50%, gain of 3 
Gallup:  Sept 27 at 45%, Oct 25 at 50%, gain of 5
ABC News/WaPo:  Sept 29 at 47%, Oct 23 at 49%, gain of 2
NBC News/WSJ:  Sept 29 at 46%, Oct 20 at 47%, gain of 1
FOX News: Sept 26 at 43%, Oct 9 at 46%, gain of 3

In every major poll, Romney has gained since last month. Even before the debate, Romney was doing well, and since the first week of October, Romney has taken a clear lead in national polls.   That’s momentum, folks.

So, OK, let’s look at some state polls.  After all, the Obama people tell us that’s where the ‘firewall’ is.

Obama/Virginia:
Rasmussen:  Sept 13 at 49%, Oct 24 at 48%, loss of 1
FOX:  Sept 18 at 50%, Oct 24 at 45%, loss of 5
ARG:  Sept 27 at 49%, Oct 14 at 47%, loss of 2

Romney/Virginia:
Rasmussen:  Sept 13 at 48%, Oct 24 at 50%, gain of 2
FOX:  Sept 18 at 43%, Oct 24 at 47%, gain of 4
ARG:  Sept 27 at 47%, Oct 14 at 48%, gain of 1

Looks like the ‘firewall’ failed, hmm?

Obama/Florida:
Rasmussen:  Sept 12 at 48%, Oct 18 at 46%, loss of 2
Survey USA:  Sept 9 at 48%,  Oct 18 at 47%, loss of 1
AR:  Sept 22 at 50%, Oct 11 at 46%, loss of 4

Romney/Florida:
Rasmussen:  Sept 12 at 46%, Oct 18 at 51%, gain of 5
Survey USA:  Sept 9 at 44%. Oct 18 at 46%, gain of 2
ARG:  Sept 22 at 45%, Oct 11 at 49%, gain of 4

And again.


Obama/Ohio:
Rasmussen:  Sept 12 at 47%, Oct 23 at 48%, gain of 1
CBS/Quinn.:  Sept 24 at 53%, Oct 20 at 50%, loss of 3
PPP:  Sept 30 at 49%, Oct 20 at 49%, no change

Romney/Ohio:
Rasmussen:  Sept 12 at 46%, Oct 23 at 48%, gain of 2
CBS/Quinn:  Sept 24 at 43%, Oct 20 at 45%, gain of 2
PPP:  Sept 30 at 45%, Oct 20 at 48%, gain of 3

Again, Romney has momentum

(Real Clear Politics source for the poll numbers)

The fact is, Romney has been trending up in battleground states, even ones that Obama’s campaign figured they had locked up just a few weeks ago.

Well, there’s a problem with the ‘firewall’ theory.  A physical firewall is there to prevent fire from reaching you, while voters can change their mind … or just stay home and not vote.  For Obama’s firewall theory to work, he has to not only convince voters to stay with him, those voters cannot be impressed by the challenger.  Now, both Republicans and Democrats have a base of loyal voters that their candidates can depend on, but that’s the point – that’s the base, the bottom level that you get whether you work much or not.  If you look at past elections, you can see how much of that base incumbents can lose.  Carter, for example, was in dismal shape in 1980, and so was GHW Bush in 1992.  They stayed competitive in their races, but when it came crunch time, their base level was too low to protect them.  A successful incumbent has to build on their base and gain support, as we saw happen with Bush in 2004, Clinton in 1996, Reagan in 1984, Nixon in 1972, and Eisenhower in 1956.  Actually, that list is much longer, but you get the idea.  The only way to actually have a firewall to use is to build one on top of your base, not hope you can pump up support in a few targeted states. 

There just is no ‘firewall’ for Obama this year. 

But there’s more.  In 2004, John Kerry won twenty states plus DC.  In 2008, Barack Obama claimed 28 states plus DC, meaning he took 8 states that Bush won the previous election.  The thing about that is that there’s no real reason to say those same eight states could not flip back to the Republican.  Some states are certainly loyal to one party or the other, but there’s a reason some states are known as ‘battleground’ or ‘swing’ states – it’s frankly naïve to imagine that an incumbent has those states locked up, and only a little less silly to expect that personal appearances or spending on commercials will automatically win a contested state.   And the Obama camp is finding out that fact just a bit late in the campaign.

One fact that gets lost in all the talk, is that Obama has never run as an incumbent before.  In all of his previous campaigns, Obama was stepping up to the next level, from running for state senator to U.S. Senator to  President of the United States.  So Obama is only now learning that incumbents face a different landscape and conditions than do challengers.

It’s not hard to figure out that the national mood is different this year, from 2008.  That year, the disgust with conditions blamed Republicans as the incumbent (even though Democrats controlled Congress), and Mister Obama promised not only a fresh approach but cooperation with his political opponents.  Since then, the economy has become weaker and the job market absolutely dismal, and the tone of the Obama White House is at turns strident or arrogant.  Even as President Obama explains to voters what he wants to do with the next term, he has never properly explained why he did not accomplish the promised results in his first term. 
Obama could win, of course.  Romney’s recent surge has, at best, given him a narrow lead and the state polls remain very much in doubt.  But the trend is certainly on Romney’s side, as evidenced by the Obama camp’s attempt to denounce poll results and internals.

The Democrats are correct to some degree, in that the states will determine the electors, who in their turn will decide the Presidential election.  At this point, we can consider the states safely locked up for Obama or Romney, where the candidate has 54% or more support in the polls (state polls have about a 4% MOE):

Obama:  9 states (including DC), 122 Electoral Votes
Romney:  11 states, 93 Electoral Votes

That means that 31 states and 323 Electoral Votes are statistically in play.  Let’s next look at additional states where the candidate has a lead greater than the 4-point margin of error plus the undecideds:

Obama: 4 states, 43 Electoral Votes (total now up to 13 states, 165 Electoral Votes)
Romney: 7 states, 59 Electoral Votes (total now up to 17 states, 152 Electoral Votes)

165 to 152 is a lot closer than you hear about in the news, isn’t it?  It means that 21 states remain in play, even this close to the election.  So what about those states?  Without getting into arguments about party weighting on the polls, one fairly undeniable point is how these states come down to how the undecideds break.  That is, Obama’s camp believes they will break to the incumbent while Romney’s team expects them to break for the challenger. 

So, both campaign teams are chasing the undecideds.  Romney has been gradually winning them over, and will continue until he reaches either his ceiling or the election finishes.  But Mister Obama has a different condition.  Here’s why:

Incumbents deal with three kinds of voters.  There are the people who voted for him, whom he keeps as long as he does the job as he promised, voters who dislike him and won’t vote for him no matter what, and voters who did not vote for him but will consider voting for him if they believe he did a good job.  That’s basically why Presidents who win re-election do so with a better percent of the vote than the first time.  Obviously, you can’t add people to your side who are already on your side, so incumbents win the re-election by keeping their base energized, by making their opponents feel they are not able to win, and by convincing the open-minded that they have done a good job.  So, it comes down to the record, not the marketing.

Challengers, on the other hand, start empty and have to win over folks.  It’s true that the challenger in the Presidential general election gets to claim the support of his party once he wins the nomination, but as anyone who ever ran in a primary can tell you, winning that nomination is grueling.  That’s why even a poor candidate is able to stay somewhat close; you don’t get to the general election unless you know how to campaign.  Once he has the nomination of his party, the challenger starts a new race, where he has to win over the nation.  He gets the voters who rejected the incumbent, provided they are mad enough to be sure to vote, but remember, if the incumbent has done a good job, the incumbent already has some of the voters who did not vote for him the first time, so the challenger is at a disadvantage.  This, basically, is why the Obama camp believed that it was too late for Romney to win. 

But the problem is where the new voters come from.  That is, when polls show the incumbent President is enjoying good Job Approval polls, he’s got voters behind him and all he has to do, is not blow it.  But if he falls below 50% in Job Approval polls, history shows he is in trouble, because once voters walk away from an incumbent, they either vote for the challenger or they stay home.  When the challenger knows this, he can target those voters.  This, in short, explains Romney’s debate strategy, and why the polls rewarded him so well in October.

The short version is that the remaining undecided voters will either vote for Romney, or they will stay home. 
  
There just is no ‘firewall’ for Obama this year.  

Wednesday, October 24, 2012

Polling Fudge


I don’t work for any polling group.  On the one hand, this means I don’t have first-hand knowledge of how a poll determines its methodology, weighting, or resolves conflicts, but on the other it also means I am free from any pressure to excuse or cover-up mistakes or false claims.  One of the boldest of those claims is not stated explicitly, but is allowed to fly unchallenged – that the polls are accurate measures of voter opinion and are reflected by results close to their prediction.  That’s just not so, when you check it out.

Here are some interesting final poll results from Presidential elections:

Gallup 1992:  Clinton 49, Bush 37 (off by 6.4 points)
Gallup 1980:  Reagan 47, Carter 44 (off by 6.8 points)
Harris 1992:  Clinton 49, Bush 37 (off by 6.4 points)  
Harris 1984:  Reagan 56, Mondale 44 (off by 6.4 points)
CBS/NYT 2008:  Obama 51, McCain 42 (off by 6.0 points)
CBS/NYT 2000:  Bush 44, Gore 45 (off by 7.3 points)
CBS/NYT 1996:  Clinton 53, Dole 35 (off by 9.5 points)
CBS 1980: Reagan 44, Carter 43 (off by 8.8 points)
CBS 1976:  Carter 45, Ford 41 (off by 12.2 points)
USA Today 2008:  Obama 50, McCain 42 (off by 7.0 points)
USA Today 1992:  Clinton 49, Bush 37 (off by 6.4 points)
USA Today 1988:  Bush 52, Dukakis 42 (off by 5.1 points)
USA Today 1984:  Reagan 61, Mondale 34 (off by 8.6 points)
NBC/WSJ 2008:  Obama 51, McCain 43 (off by 5.0 points)
NBC 2000:  Bush 47, Gore 44 (off by 5.3 points)
NBC 1980:  Reagan 42, Carter 36 (off by 13.8 points)
Fox 2000:  Bush 43, Gore 43 (off by 10.3 points)
Ipsos 2004:  Bush 46, Kerry 49 (off by 5.4 points)
IBD 2004:  Bush 46.9, Kerry 44.3 (off by 7.8 points)
Rasmussen 2000:  Bush 40, Gore 49 (off by 8.5 points)
Pew 1996:  Clinton 52, Dole 38 (off by 5.5 points)
Marist 2000:  Bush 49, Gore 44 (off by 5.5 points)
Newsweek 2000:  Bush 45, Gore 43 (off by 8.3 points)
LA Times 2008:  Obama 50, McCain 41 (off by 8.0 points)

 What should be noticed in these polls, is not only how far off they ended up, but the fact that polls often over- or under-estimated one candidate’s support .  That, by the way, is also why my review of their errors is different than you will hear from some polls.  Some will simply compare the margin in their final poll to the election margin, while others will take the total variance between their poll and the election result and cut it in half to call it an “average”, but neither is statistically correct.  Polls measure specific levels of support for each candidate, and so their margin of error is actually the total distance between their call and the result for each candidate.  As an example, let’s say PollCo releases a poll saying candidate A will beat candidate B 53% to 45%, but in fact candidate A wins 51% to 48%.  The poll might claim that their margin was +2 for A and -3 for B, so the average margin is 0.5 points off, but in fact the actual margin of error would be 5 points off.  This is often trivial in itself, but let’s say PollCo is usually off between 4 and 5 points, understating one candidate while overstating another.  Shouldn’t you know that history when, say, in another year PollCo says candidate G is leading candidate H 49% to 48%?  In a close race, a poll with a history of missing the mark by a sizable chunk is not really reliable, is it?

Ah, but there’s more.  Only polling nerds like myself would recognize the name Walter Mitofsky, but this gentlemen was a legend in opinion polling.  Having worked for the Census Bureau then CBS News, Mitofsky for all practical purposes created the Exit Poll as we know it.  Mitofsky knew how polls worked, and significantly observed that there is a chronic bias in favor of Democrat candidates in opinion polling, not just once in a while, but all the time. 


There are exceptions, but in general polls tend to undervalue support for both Republican candidates and challengers.  The implications for this election are rather obvious.

I have said before that polls try to get the results right, but we should be very careful to test their headline claims, which are often driven by the narrative of the moment.  This week it’s amusing to hear the excuses being thrown out by Democrats, that the state polls are correct while the national polls, somehow, are not.  Republicans, in some cases, say the opposite, that the state polls are wrong while the national polls are right.  What I think is something else entirely – a lot of people do not realize what the polls are really telling us, and so assumptions drive emotion to error.

Let’s start with three obvious facts:

1.  In general, poll groups try very hard to publish accurate representations of voter intent.  This point often gets lost in all the emotion, but looking for conspiracies or attempts to mislead voters.  Errors happen but are honest mistakes due to faulty (sometimes common) false assumptions.

2.   All polls have errors and unknowns.  Expecting a poll to be perfect means you expect voters to have no doubts, to never change their mind, and to respond to poll queries in the exact proportions that they will vote, demographically.  To understand a poll, you do not count it as part of an average of polls, you do not assume that the margin held at any date a week or more out will hold through the end, and you do not ignore the internal data.  To understand a poll, you note shifts in trends, momentum, you observe weak and strong demographic groups for each candidate, and you make sure the poll has not changed its methodology or demographic weights since the last poll release.

3.  The state and national polls are inextricably linked.  If there is disagreement in the topline conclusion between state and national polls, either the national polls will correct to be in line with the correct state polls, or state polls will correct to be in line with the national polls.  This does not happen because someone wants to avoid embarrassment, but because math requires it.  Four quarts always make a gallon, sixteen ounces always make up a pound, and the fifty states plus D.C. have to make up the national total.  Resolution is inevitable.

So why is there argument?  For one thing, a lot of otherwise intelligent people do not seem to understand that 2012 is not 2008.  The economy, world condition, social and legal issues, are all different from four years ago.  The candidates are different from four years ago, including Barack Obama.  Mister Obama cannot run as the fresh young challenger this year, he has to run on his record and accept Mister Romney will be on offense this time.  What that means in the polls is that many assumptions have to change to match the new paradigm, especially in demographic terms.  A rather large number of polls were set up on assumptions which are clearly in dispute now.  As a result, state and national polls are sometimes in sharp disagreement about the party participation by Democrats, Republicans, and Independents in this election.  Also, Pew reported earlier this year that the response rate by voters to polling groups has plummeted below ten percent, indicating  large portion of voters do not respond to poll queries, which calls poll results into question, especially when sample sizes are low, as is generally the case with state polling.  Also, state polls are performed far less frequently than national polls, and even then by a variety of agencies rather than by the same groups on a regular schedule.  Consequently, if something shifts within the dynamics of a state, the state polls tend to lag behind national polls in observing and reporting the new trend.     

Polling Is a Messy Business


I became interested in polls back when the first George Bush ran for President.  I had noticed how Reagan thumped Carter in 1980 after the polls said he was behind, and noticed how odd the polls looked at various times in subsequent elections.  So I started paying attention to polling agencies and tried to understand how they work.

There’s a certain mystic quality to polls, you know.  While they carefully state that polls are not predictive, polling groups well understand the influence they carry in shaping opinion as well as reporting it.  Human behavior is especially sensitive to Heisenberg’s warning that the act of observation itself changes behavior of the observed.  The idea that you can ask a few people about something and get a detailed report on what everyone is thinking, seems a bit far-fetched.  Which brings us to Statistics and the importance of getting details right.

Statistics is all about numbers, but it’s also about providing information on large amounts of information, kind of like the handle on a suitcase, it gives you a way to get a grip to handle something large.  Opinion polling is based on the very real science of extrapolating large group behavior on known demographics and, well, a certain herd mentality.  Statistics is the reason advertising works, for example.  A company finds out that people pay attention to certain sensory triggers, and they tie their product in to those things.  Credit ratings work the same way, on the empirical record that people behave in ways which are generally predictable.    

Polls enjoy a certain protection from suspicion, as well.  They publish only summaries of their results, on the claim that their details are proprietary.  This is true, except that it also means no one checks the process or integrity of most polls’ methodology.  As a result, a poll could theoretically publish whatever results it wished, manipulating numbers in reverse.   In the case of election opinion polling, the only way to know how well a poll performed is to compare its last release before an election to the actual result, which says nothing about polls released earlier in the campaign.  And boy howdy, sometimes polls earlier in a campaign are very odd. 

Having said this, I pretty much reject it.  Polls are in business to attract clients, and you don’t succeed by publishing results that could blow up on you if your employees revealed sloppy methods.  But it’s also true that sometimes polls change methods and get worse instead of better.  The problem comes down to your business model.  There are well-known polls like Gallup and Rasmussen and Harris, which have been in the business for literally decades, there are some universities and colleges which put out polls somewhat irregularly, and there are a great many small, frankly unknown polling agencies whose purpose in publishing election opinion polls seems to be in hopes of attracting future clients.  There are also the private polling firms the public never hears about, companies who perform polls for the specific and confidential use of their clients.  Both Romney and Obama use private polling firms, which not only focus on selected demographics and battleground states, but also track effectiveness of strategies and tactics.  The candidates do not disclose their internal poll results (although you may hear rumors from time to time from aides), but you can get a sense of their poll results by how confident and ambitious the candidate appears and where they go to make appearances.  This late in the race, candidates will only make appearances in states where they believe their personal appearance will be most effective.

Part of the problem of polling, aside from the small start-ups with no history which pop up every election and pretend to be just as reliable as the established polls, is laziness.  Very few of us are willing to print out and study all of the polls and their internal data to weigh the election race in context.  Most people just want to know who’s winning, so they want a nice easy-to-read scoreboard.  And that has led us to aggregation.  What’s worse, people who really should know better also buy in to aggregated summaries and sell them not only as accurate displays of the election condition, but also in some cases as valid predictors of future behavior.  Frankly, this kind of behavior is dishonest.

Statistics is a science, but since it studies human behavior certain cautions are necessary.  Aggregation bias is a well-known problem in statistical analysis, as you can see in studies by:

The National Institute of Health, regarding aggregation of group level statistics

The Federal Reserve Bank, regarding aggregation errors in economic behavior

The American Statistical Association, regarding covariance analysis and aggregation distortion


The problem comes from forgetting that polls use very small portions of the voter poll to ascertain opinion and trends.  Aggregation amplifies whatever bias exists in any given poll, and exacerbates error if a common assumption proves faulty.  This is why aggregation is considered an invalid practice in statistical analysis.  As much as I appreciate Real Clear Politics for presenting a one-stop place to compare and consider polling, their RCP Average is invalid as a true indicator of the election condition.

Aggregation is easy to read, though, and a lot of folks like the idea that they understand what’s going on by just reading one website’s release.  Some of these bloggers have enjoyed undeserved praise for piggy-backing off other people’s work, like Nate Silver.  Mister Silver developed a formula which basically takes published poll results, weights them according to his personal preference, aggregates the results and produces an average.  He then assumes the formula is good for a prediction of the election, which he publishes like a weather report.  Silver recently announced that despite setbacks since the start of October, President Obama still has, in his opinion, a seventy percent chance of winning.  Stop and consider that for a moment, in its emotional impact.  If the guy doing the weather on TV said there was a seventy percent chance of rain tomorrow, you’d expect rain, naturally, and possibly a heavy rain.  At the very least, you’d expect to see heavy clouds and some wind.  No one would expect bright sunshine and blue skies.  So Mister Silver’s statement is a clear warning that things are going poorly for the Romney campaign, dire and bleak.  Never mind that most of the well-established national polls (Gallup, Rasmussen, ABC News/Washington Post) not only give Romney a good chance, they actually show him winning right now.  The problem, you see, is that Mister Silver is an Obama partisan, and he allows that to flavor his reports. 

In a way, I think I should like Nate Silver more than I do.  I’m something of a numbers guy in my work, I love polls and politics, and I enjoy reading up on opinion polling in particular and can appreciate the work that goes into an analysis, especially an on-going one through a campaign lasting more than a year.  But I learned in 2008 the hard way about assumptions; after a bit of success in analyzing polls in 2004 for the Bush-Kerry race as a writer for Polipundit, I made the mistake of trusting a similar model in 2008.  I realized after the election that conditions are different for every election, and if you do not adjust for the new conditions you will make mistakes, possibly serious errors.  Silver is doing the same thing now, I think, his formula turned out great in 2008 and he thinks, why change what’s working?  The problem is, the election this year is fundamentally different than the 2008 election, to which I will return in a later post. 

The reader might counter that most polls turn out to be generally accurate (and that aggregators are therefore reliable), but that statement does not hold up to close inspection.  First, consider that the only polls measured for accuracy are the final polls, which generally come out in the last week of the campaign.  Predicting the outcome that late is like predicting the score of a football game in the last minute of the fourth quarter; it’s not really something to brag about.

And polls don’t do all that well, actually, in terms of precision.  If you take the time to go back and look at the polls’ historical error from actual results, the following average comes out:


Gallup (last 10):  3.41 points average error
Harris (Last 10):  3.63 points average error
ABC/WaPo (9 elections):  3.05 points average error
CBS/NYT (9 elections):  6.37 points average error
USA Today (7 elections):  3.86 points average error
NBC/WSJ (6 elections):  5.73 points average error
Zogby (4 elections):  2.70 points average error
Pew (4 elections):  2.40 points average error
Battleground/GWU (4 elections):  5.75 points average error
Rasmussen (3 elections):  3.40 points average error
CNN (3 elections):  2.15 points average error
Newsweek (3 elections):  5.63 points average error
Fox (3 elections):  7.10 points average error
Marist (3 elections):  4.30 points average error
IBD (3 elections):  4.43 points average error
Ipsos (2  elections):  2.70 points average error    
ARG (2 elections):   2.20 points average error
TIME (2 elections):  3.80 points average error
LA Times (2 elections):  5.00 points average error

(final election poll variance from each candidate actual Presidential election result, last ten such elections if available, data collected from online site for each poll, corroborated where possible from RCP and PollingReport.com for election year)

Given that most polls advertise a margin-of-error of about 3.5%, this data shows that of twenty national polls which published final releases before elections, eleven average actual error rates beyond their published margin of error, and two-thirds of all polls which have published final releases in six or more of the last ten Presidential elections had average error rates greater than their published margin of error.   While some polls seem to do much better in accuracy, keep in mind these are the polls with less experience in election polling, and so their perceived accuracy is possibly just a fluke.  And, as I said, these results are how the final poll performs; some of the earlier releases are more than little bit suspect in their claims.

The technical term used for the discovery of this fact, is “oops”.  But you don’t see the polls bring that up in their releases, even when the election is close enough that these actual error margins eclipse the presented results from the poll.