Beyond the Numbers: What I Said and What Happened

A good, credible commentator continuously examines what he or she felt confident predicting in the past for both accuracy and learning.  It was the lack of this behavior on the part of right-wing commentators that I was screaming about yesterday.  Of course, introspection is made a little easier for me this time around, as my projections came through very solidly.  But, hey, what's wrong with a little victory lap?

Let's revisit the principle arguments made for a Romney victory and the counterpoints I made to those last Friday:

1) President Obama is still under 50% in virtually every national poll.  Undecideds will break late for the challenger and give Romney the narrow victory.

I wrote:

Recent history suggest no evidence of this rule of thumb.  Undecideds in 1980 surely did break for Ronald Reagan over Jimmy Carter late.  In 1984, they broke for Reagan again - this time as the incumbent.  In 1992, undecideds broke evenly.  In 1996, they broke for the challenger.  In 2004, they broke evenly.  There doesn't seem to be a pattern here to support the "rule of thumb" that an incumbent under 50% is in trouble - George W. Bush was under 50% in the polling and got 51% of the vote on election day. 

What happened:

Exit polling indicates that of those who decided in the final days of the election, 50% voted for Barack Obama, 44% for Mitt Romney.  This explains, to a certain extent, why my results had a slight Pro-Romney bias - I had assumed a 50/50 split (the difference is worth about a 0.5% shift in the popular vote.)  Certianly the notion that undecideds break late for the challenger is debunked.

(2) No incumbent President has ever been re-elected to a second term winning less states than he won the first time around and it is impossible to see a path to President Obama winning more states than in 1988.  It's win big or go home for incumbents and Obama cannot win big.

I wrote:

True, but irrelevant.  No one had ever won 49 states...until 1984 when Ronald Reagan did.  Candidates always win their home state - heck, even George McGovern and Walter Mondale did - until Al Gore lost Tennessee and the election with it.  The winner of Missouri always wins the election - until 2008 when Barack Obama won without it.  My point is that you can point to lots of things that are "always" true - until they aren't. 

What happened:

President Obama won re-election by a narrower margin than 4 years ago (approximately 2.5% in the popular vote versus 7.2% in 2008.)  Guess we can cross this one off the "no incumbent President has ever" list.

(3) The polls systemically overestimate Democratic turnout and the actual results will therefore differ from the polls by several percentage points.

I wrote (in a previous post):

Non-partisan pollsters only stock-in-trade, their only incentive is to get things right.  If you consistently get your polls wrong, you are out of the business.  Polls have been wrong before, but almost never because the pollster wanted to get it wrong.  The polls were very accurate in 2008.  Ditto in 2004.  In 2000, George W. Bush got less popular vote than the polls implied late, but that was principally because the release of his DWI conviction appeared to cause a late slide in his numbers that pollsters weren't able to capture in their final polls because it happened too late.

So forget the notion of a vast conspiracy.  The only reasonable way to believe the polls are systemically biased is if they are ACCIDENTALLY biased, that is, the majority of pollsters make an honest mistake in the turnout dynamics of the election.  Now clearly all the pollsters are reading and analyzing the claims on the right - and most are sticking by their guns.

What happened:

To the extent that there was any polling bias, it was Pro-Romney.  Obama outperformed 7 of the 10 polls in my final projection.  In the key swing states, Obama outperformed the projection in Florida, Virginia, Colorado, Pennsylvania, Nevada, Iowa, Michigan and Wisconsin.  Only in Ohio did the President underperform the projection and there only by 0.2%.

Clearly the polls did have a systemic bias - FOR Romney.  Pollsters generally estimated a turnout model between the 2004 and 2008 models when, in fact, turnout of demographics that favored Obama met or exceeded 2008 levels in 2012.

(4) The national polls show a tighter race than the state polls and the national polls are generally conducted by better-established, more reliable polling firms.  It is therefore reasonable to believe that swing states are actually in better shape for Romney than the state-level polling data would indicate.

I wrote:

Generally, the evidence doesn't support this theory.  On average, state-wide polls have been at least as accurate and often more so than national polls on election day...see 2000 for a great example of this.  Secondly, while there are some smaller firms polling in swing states, there are also a lot of large ones - Rasmussen, CNN/OR and Survey USA are all poling Ohio and their results are actually well in line with other polls from smaller firms.

What happened:

The polls largely converged by election day and both showed a slight pro-Romney bias, rendering the argument largely irrelevant.

If you like this site, tell your friends

On the Credibility of Polls, A Brief Hiatus

Polls, Polls, Polls
As you know, I watch poll releases pretty closely and the state-wide polling numbers released by Quinnipiac today were startling to me.  The race has clearly been trending towards President Obama since the DNC and he is a solid favorite, trending towards a highly probable favorite at this stage of the gain.  So that Quinnipiac would release polls showing him leading in Florida and Ohio was no shocker - virtually every poll since the DNC in those 2 states has shown the President in the lead.

What was shocking was the margins - 9 points in Florida and 10 points in Ohio.  Just for perspective, these are significantly larger margins than the President's margin of victory in 2008, and nothing in the national polling picture suggests that he will replicate his 2008 victory.

So what the heck is going on here and how credible are these polls?

Conservative commentator John Nolte notes that the sampling calibration in those two polls seems out of whack.  First, a brief explanation for those new to polling.  All pollsters calibrate their poll results based on a projection of the composition of the electorate.  This is because they are unable to truly randomly reach people as certain demographic groups may be more likely to answer the phone and speak to a pollsters than others.  So, for instance, if a pollster conducts a poll but finds that 70% of the respondents are men, but knows that in virtually every election, women comprise 51 to 55% of the actual vote, he will adjust the weighting of the responses to reflect that electoral reality.

In the case of the two Quinnipiac polls in question, Nolte notes that they show 9% more Democrats than Republicans in both Ohio and Florida, whereas the actual 2008 election results showed only 3% more in Florida and 8% more in Ohio.  If you were to normalize based on 2008 election results, it would shrink Obama's lead to 9% in Ohio and 3% in Florida.  If you were to normalize based on the mid-point between the 2004 and 2008 elections, Florida would be a dead heat and Obama would lead in Ohio by 1%.

Other polls released in the past 3 days show the President up by 3-5% in Florida and anywhere from 1%-8% in Ohio.

I suspect the reality is probably closer to a 3% lead for the President in Florida and a 5 or 6% edge in Ohio.  The Quinnipiac polls would appear to me to be outliers, just as the national Rasmussen poll, which Republicans like to cite, is an outlier for Romney, showing the national race a dead heat.

A Brief Hiatus
It is the worst time of the political season to be doing this sort of thing, but I will be taking a break for the next 10 days from blogging.  It is an intensely personal decision to support the faltering European economy by drinking large quantities of beer in Munich during Octoberfest.

I hope the first debate finds you well and I look forward to keeping you informed on all the twists and turns of the race down the home stretch upon my return.