Thursday, August 7, 2008

What Would Happen If...

...FHQ dropped some of the older state polls that may not be as reflective of the current (or if not current, recent) situation in the presidential race?

I've been asked several times by folks commenting here at FHQ and colleagues here at UGA if I had any plans to phase out any of the Super Tuesday period polls. My standard answer has been no, but once we hit the conventions and get past Labor Day, the traditional general election campaign will get underway and the dynamics of the race will likely change as well. I would expect increased polling and greater total attention from the public/electorate. Whether the latter means "better" responses from survey respondents is up for debate, but in any event we will likely have more representative polling emerging in September, vis a vis the vote in November, than we would with the polls that came out in February or March. Am I permanently dropping those polls from these analyses? No, this is simply a speculative look at how the landscape would appear in their absence.

Fine, what are you dropping then? This, as it turns out, was not an easy decision, though, it may look that way once I've explained. Some electoral college projections use just the most recent poll or the most recent several polls (two or three). In the case of FiveThirtyEight.com, they have used a decay function (a half life equation) to gradually phase out older polls. This is perhaps a good middle ground approach, but I don't want to be accused of aping what is being done over there. Despite that, I looked into where that cut off was on average. In most states, the oldest poll used ranges from mid-April to early May. I considered doing a similar cut off, but opted instead to cut things off at the beginning of the general election campaign, which I placed at the beginning of June. Yeah, Clinton wasn't officially out until June 3-7, but the Rules and Bylaws Committee's decision all but sealed her fate on the final day of May with their Florida/Michigan ruling.

The point here is to accomplish a couple of things. For starters, removing past and potentially inaccurate (at least outdated) polling may prove beneficial. Secondly, this removes the Clinton factor from the equation by focusing on polls conducted just during the general election race. The main criticism I'll get for this is that it is going to skew things in the favor of Obama because the polling cut off point sets the beginning at a point that encompasses his "bounce" during June.

Well, we've set the rules, so how does the map look? I should note now that this is not an official FHQ update of its electoral college analysis (Actually, the color scheme of the map is different so as to serve as a preventative measure on that front. Democratic blues will now be shades of purple and Republican reds will be altered to shades of orange.). This is merely speculative, but at the same time is something of a trial balloon. As I said, the dynamics of the race will change following the conventions, and I plan on officially revisiting our methodology at that time to see if there need to be any changes made. The method used here may be that change, if there is one, or it may not. With that said, to the map!
[Click Map to Enlarge]

If we compare this map to the most recent electoral college map I posted just yesterday, you'll see that there are twelve states that change categories (ie: from McCain lean to strong McCain) and a third of those change sides from Republican to Democratic or vice versa. The result is that Obama has a net gain of 22 electoral votes. Indiana, Montana and Virginia (27 electoral votes) move into Obama's column while Nevada (5 electoral votes) switches to favoring McCain. When each candidate's prospective electoral votes are broken down into categories, the distribution isn't all that different from before. The strong Obama category still holds -- by a large margin -- the most electoral votes, but lean (74D - 81R) and toss up (56D - 64R) electoral vote tallies are largely the same across the two parties.

Looking at the individual states, we see that Michigan, New Hampshire and Pennsylvania move out of the toss up distinction and become more solid for Obama. The movement of those 42 electoral votes is as important as the movement of those formerly Republican toss ups to the Democratic side. Aside from the states that switch from one partisan side to the other, these three states moving further into Obama's side are among the most important shifts. This is a good point to look at this in terms of the rankings we started doing here a few electoral college posts ago. The first thing to note is that Ohio is the new (and this is the last time this will be in quotation marks) "victory line." The Buckeye state is state where each candidate passes (or would pass) the 270 electoral vote threshold to claim victory in the election. The partisan line -- where the states shift from being Democratic to being Republican -- has now, with just the state polls from June on, been pushed further away from the victory line. That is indicative of the gains Obama makes when the cut off point for the polls is shifted. One additional thing to note about the victory line is that Ohio is the first toss up state for Obama. In other words, Obama is nearly to 270 electoral votes with just his lean and strong states. He needs just one of those toss up states to surpass that barrier (with the exception of Montana which would put him just three votes short). Colorado, Indiana or Virginia could be substituted for Ohio if the Buckeye state and the other three toss ups slipped into McCain territory.

The Electoral College State Rankings
HI-4
WA-11
NH-4
ND-3
TN-11
VT-3
MN-10
OH-20*
SD-3
KY-8
RI-4
NJ-15
CO-9
AK-3
WY-3
MD-10
WI-10
VA-13
GA-15
LA-9
NY-31
DE-3
MT-3
TX-34
AL-9
MA-12
OR-7
IN-11
WV-5
ID-4
CT-7
PA-21
NV-5
SC-8
KS-6
CA-55
NM-5
FL-27
AR-6
NE-5
ME-4
IA-7
MO-11
AZ-10
OK-7
IL-21
MI-17
NC-15
MS-6
UT-5
*Ohio is the state where Obama crosses (or McCain would cross) the 270 electoral vote threshold to win the presidential election.

As I've said, this is, for the time being, simply a glimpse into what things would look like if I decided to drop some of these "older" polls. The shift has been overwhelmingly toward Obama, but as we head into August this alternate version of reality will be something to keep tabs on. Does a shift toward McCain or away from Obama move the needle any more in this than it would in the normal version? The polling between now and the Democratic convention will help us to answer that question not to mention give us an idea of whether a change in methodology is even prudent. I will be keeping up with this now that I have the infrastructure in place, so that it will be an easier transition should we opt to go in that direction following the conventions (and their bounces).


Recent Posts:
The Electoral College Map (8/6/08)

Did Obama or McCain Win July?

About Those Rules: What Obama's New Florida/Michigan Stance Means for 2012 and Beyond

4 comments:

Jack said...

Of course you should switch your methodology! This map is 22 votes better than the other one!

Okay, now to put aside my bias and speak objectively:

Perhaps you could keep your methodology but at some point after the two conventions are over (say, early October), you could do something similar, comparing the actual map with your current methodology to the polls after the two conventions?

Anonymous said...

I will be keeping both lines of analysis going, so the option you mention is certainly on the table, Jack. If were my course of action, I would likely have a comparison post on a monthly basis (one similar to the one I put out on Monday).

We'll see. I don't want any of this to appear as if I'm doing any of this based on whim. This option may be the most pragmatic one though.

Robert said...

Looks good. I am glad you adopted the victory line terminology. The incorporation of June polls is a definite boost to Obama. If you were to drop those polls and go with July polls only, the results would look more favorable to McCain.

A tip of the hat to Allen. No VP announcements before the Olympics or Obama's Hawaiian vacation. Expect the McCain folks to make a big deal of that in a forthcoming ad at the risk of hurting his chances in HI!

Anonymous said...

Rob,
I'd imagine, given the state of things in the July wrap-up post that you are correct. McCain would hold some sort of advantage. If I have time later today I'll calculate that and post it (though not in as detailed a manner). And that's the problem with picking a point to cut off early polling.

If you think about it, McCain was deprived of a similar bounce in the polls because of the competition in the Democratic race. It would be hard to say that McCain's "gains" in that March 5 to April 21 period were due to his winning the GOP nomination or because of Wright or bitter-gate putting a drag on Obama's numbers.

I'll actually have a post up shortly concerning you other two points.