Posted on 11/02/2012 5:57:13 AM PDT by Perdogg
There have been some fantastic pieces the last couple of days analyzing the divergent polls and how partisans seem to be choosing whichever data supports their candidate and arguing for its veracity over the contrary. Today, a great many Republicans look at Mitt Romney’s lead in national polls and point to that as the reason for his expected election victory. Democrats look at the state polling (since that is where the actual electoral votes come from) and say Obama still has the electoral college advantage regardless of any deficit in national polls. Sean Trende at Real Clear Politics had a great non-partisan column on national polls versus state polls and how looking at each can lead to opposite conclusions:
The RCP Average currently has Mitt Romney up by 0.8 points nationally. He has held this lead fairly consistently ever since the first presidential debate. Given what we know about how individual states typically lean with respect to the popular vote, a Republican enjoying a one-point lead nationally should expect a three-to-four-point lead in Florida, a two-to-three-point lead in Ohio, and a tie in Iowa. Instead we see Romney ahead by roughly one point in Florida, and down by two in Ohio and Iowa.
That would give the Presidency to Mitt Romney. But if you reverse engineer the state polls to a national turnout you arrive at a different conclusion:
Since the national vote is a collection of state votes, polls of all states should collectively approximate the national vote (since errors should be randomly distributed, they should cancel out). This is done by a simple weighted average…[T]here are several good arguments for favoring the state polling: (1) you have more polls — a much larger collective “n”; (2) you compartmentalize sampling issues — pollsters focused exclusively on Colorado, for example, seem less likely to overlook downscale Latinos than pollsters with a national focus; and (3) the state pollsters were better in 1996 and 2000, two years that the national pollsters missed (although the truly final national pollsters in 2000 got it right, suggesting that perhaps there was a late shift in the race)…After adding the totals up, the results were plain: If the state polls are right, even assuming Romney performs as well as Bush 2004 did in the states without polling, Obama should lead by 1.18 points in the national vote. Given the high collective samples in both the state and national polling, this is almost certainly a statistically significant difference. It’s also a larger margin than all but one of the polls in the national RCP Average presently show.
But national versus state polls isn’t the only debate. Actual poll results versus the data within those same polls may even be the more contentious (and valuable) debate this cycle. Enter Baseball Crank with a fantastic look at modeling election outcomes based on polls versus looking at the actual data that makes up the polls to forecast election winners:
Mathematical models are all the rage these days, but you need to start with the most basic of facts: a model is only as good as the underlying data, and that data comes in two varieties: (1) actual raw data about the current and recent past, and (2) historical evidence from which the future is projected from the raw data, on the assumption that the future will behave like the past.
[A]n argument Michael Lewis makes in his book The Big Short: nearly everybody involved in the mortgage-backed securities market (buy-side, sell-side, ratings agencies, regulators) bought into mathematical models valuing MBS as low-risk based on models whose historical data didn’t go back far enough to capture a collapse in housing prices. And it was precisely such a collapse that destroyed all the assumptions on which the models rested. But the people who saw the collapse coming weren’t people who built better models; they were people who questioned the assumptions in the existing models and figured out how dependent they were on those unquestioned assumptions. Something similar is what I believe is going on today with poll averages and the polling models on which they are based. The 2008 electorate that put Barack Obama in the White House is the 2005 housing market, the Dow 36,000 of politics. And any model that directly or indirectly assumes its continuation in 2012 is – no matter how diligently applied – combining bad raw data with a flawed reading of the historical evidence.
Nate Silver’s much-celebrated model is, like other poll averages, based simply on analyzing the toplines of public polls…My thesis, and that of a good many conservative skeptics of the 538 model, is that these internals are telling an entirely different story than some of the toplines: that Obama is getting clobbered with independent voters, traditionally the largest variable in any election and especially in a presidential election, where both sides will usually have sophisticated, well-funded turnout operations in the field. He’s on track to lose independents by double digits nationally, and the last three candidates to do that were Dukakis, Mondale and Carter in 1980. And he’s not balancing that with any particular crossover advantage (i.e., drawing more crossover Republican voters than Romney is drawing crossover Democratic voters). Similar trends are apparent throughout the state-by-state polls, not in every single poll but in enough of them to show a clear trend all over the battleground states.
If you averaged Obama’s standing in all the internals, you’d capture a profile of a candidate that looks an awful lot like a whole lot of people who have gone down to defeat in the past, and nearly nobody who has won. Under such circumstances, Obama can only win if the electorate features a historically decisive turnout advantage for Democrats – an advantage that none of the historically predictive turnout metrics are seeing, with the sole exception of the poll samples used by some (but not all) pollsters. Thus, Obama’s position in the toplines depends entirely on whether those pollsters are correctly sampling the partisan turnout.
Battlegroundwatch clearly falls into the Baseball Crank category of looking at the internals and taking the conclusions wherever they lead us. Following this methodology Baseball Crank concludes thusly with which we have no disagreement:
I stand by my view that Obama is losing independent voters decisively, because the national and state polls both support that thesis. I stand by my view that Republican turnout will be up significantly from recent-historic lows in 2008 in the key swing states (Ohio, Wisconsin, Colorado) and nationally, because the post-2008 elections, the party registration data, the early-voting and absentee-ballot numbers, and the Rasmussen and Gallup national party-ID surveys (both of which have solid track records) all point to this conclusion. I stand by my view that no countervailing evidence outside of poll samples shows a similar surge above 2008 levels in Democratic voter turnout, as would be needed to offset Romney’s advantage with independents and increased GOP voter turnout. And I stand by the view that a mechanical reading of polling averages is an inadequate basis to project an event unprecedented in American history: the re-election of a sitting president without a clear-cut victory in the national popular vote. Perhaps, despite the paucity of evidence to the contrary, these assumptions are wrong. But if they are correct, no mathematical model can provide a convincing explanation of how Obama is going to win re-election. He remains toast.
We always view our loved ones through rose-colored glasses, don’t we? No one is better looking than our husband or wife. This is at the root of conservative denial. We continue to believe that, in the words of Medved, this is the “greatest country on God’s green earth.” How can such a great country have elected Obama? It doesn’t compute, so we deny, deny, deny.
This is no longer the country it was in 1985. Anyone who thinks that the results on Tuesday will result in some sort of Reaganesque outcome is just deluding themselves. This is a bitterly divided country in decline. Romney may pull it off by a hair, if the turnout is just right, but let’s get real. America isn’t what it was and all the fancy rationalizations won’t change that.
This Baseball Crank article is epic everyone should read this article:
http://baseballcrank.com/archives2/2012/10/post.php
more from this post:
Nate Silver’s much-celebrated model is, like other poll averages, based simply on analyzing the toplines of public polls. This, more than any other factor, is where he and I part company.
If you read only the toplines of polls - the single number that says something like “Romney 48, Obama 47” - you would get the impression from a great many polls that this is a very tight race nationally, in which Obama has a steady lead in key swing states. In an ordinary year, the toplines of the polls eventually converge around the final result - but this year, there seems to be some stubborn splits among the poll toplines that reflect the pollsters’ struggles to come to agreement on who is going to vote.
Poll toplines are simply the sum of their internals: that is, different subgroups within the sample. The one poll-watchers track most closely is the partisan breakdowns: how each candidate is doing with Republican voters, Democratic voters and independent voters, two of whom (the Rs & Ds) have relatively predictable voting patterns. Bridging the gap from those internals to the topline is the percentage of each group included in the poll, which of course derives from the likely-voter modeling and other sampling issues described above. And therein lies the controversy.
My thesis, and that of a good many conservative skeptics of the 538 model, is that these internals are telling an entirely different story than some of the toplines: that Obama is getting clobbered with independent voters, traditionally the largest variable in any election and especially in a presidential election, where both sides will usually have sophisticated, well-funded turnout operations in the field. He’s on track to lose independents by double digits nationally, and the last three candidates to do that were Dukakis, Mondale and Carter in 1980. And he’s not balancing that with any particular crossover advantage (i.e., drawing more crossover Republican voters than Romney is drawing crossover Democratic voters). Similar trends are apparent throughout the state-by-state polls, not in every single poll but in enough of them to show a clear trend all over the battleground states.
If you averaged Obama’s standing in all the internals, you’d capture a profile of a candidate that looks an awful lot like a whole lot of people who have gone down to defeat in the past, and nearly nobody who has won. Under such circumstances, Obama can only win if the electorate features a historically decisive turnout advantage for Democrats - an advantage that none of the historically predictive turnout metrics are seeing, with the sole exception of the poll samples used by some (but not all) pollsters. Thus, Obama’s position in the toplines depends entirely on whether those pollsters are correctly sampling the partisan turnout.
That’s where the importance of knowing and understanding electoral history comes in. Because if your model is relying entirely on toplines that don’t make any sense when you look at the internals with a knowledge of the past history of what winning campaigns look like, you need to start playing Socrates.
BTW looking at an aggregate of 6 MSM polls, SurveyUSA, PPP, CBS/Quinnipiac, Gravis, Ras, ARG and FoxNews Romney is +10% among indies in Ohio. Obama is not winning Ohio.
http://polls2012.blogspot.com/
Statistical sampling is not a useful tool for predicting the outcome of a close election. No matter how hard you stare into a dark, rainy night, you cannot see farther than your headlights can illuminate.
Anyone who has taken a basic course in statistics understands that the “48-48%” result actually means (with a margin of error of +/-3%), is that all that can be accurately said is that the real result lies somewhere between 45-51%. Nothing more. The midpoint is no more likely than the endpoints of the range. The mechanics of the analysis impose these limits - even where the technique is used on inanimate objects that lack the complexities of humans expressing political preferences.
Combining polls is much worse and looking for trends across multiple polls is a waste of time. And none of this even begins to account for the mathematical fact that there is a one out of 20 chance that any single poll will not be representative of the actual result.
It has long been established that you can interpolate between the gradations on a ruler, scale, etc. But that process has a limit - normally you can go 1/2 gradation smaller than the marked increments. But you can’t measure to thousandths of an inch with a yardstick - no matter how hard you try or what imaginative techniques you develop.
No matter how bad you want it to be sunny on Saturday, weather forecasting also has a margin of error. You accept it and do the best you can.
My son’s girlfriend broke her jaw in two places on Saturday. She has had to have it wired shut for at least five weeks. She is in great pain, hungry, and feels like crap. She insisted that we take her to vote with us yesterday and she voted straight R.
She will make a very good daughter-in-law.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.