« Radio Interview: NatSec, Terrorism and Politics | Main | Barack Obama is a Socialist »

Using State Poll Performance Metrics to Verify National Support

Last week in the comment section to one of my articles, reader Andrew Byler made an important observation regarding the over/underperformance of state polls. I think it got lost by most readers, so I am posting today's article on that subject.

The more observant readers have noticed that the election depends more heavily on state results than the national tally, so they have repeatedly asked about what the state polls say. There is a range of opinion coming out of those polls, but one thing that should be observed, is that there is a clear relationship between the state and national performance. For example, in the state of Ohio, it has long been said that no Republican can win without it. That is the case, it turns out, because Ohio tends to track relatively close to national performance; if a republican does poorly in Ohio, he will likely do poorly across the nation. Over the course of election history, most states have demonstrated a tendency to favor the republican or democrat candidate, and by a certain range of support. This allows us to use the state polls to test the veracity of the national polls, and vice versa.

Let's have a look at a few states to see how this plays out:

Let's start with California. RCP's average shows Obama ahead by 14.5 points in California. RCP also says Obama is ahead 7.1 points nationally. Looking at California, we see that on average, California favors the democrat candidate by an average of 4.0 points more than the national average, based on past election results. Accordingly, California's poll numbers suggest that Obama's real lead nationally is 11.1 points;

The next state is Texas. RCP's average shows McCain ahead by 12.7 points in Texas. On average, Texas favors the republican by 7.0 points more than the national average, suggesting that McCain is leading the race, by 5.7 points.

Next up is New York. RCP's average shows Obama ahead by 18.0 points in New York. On average, New York favors the democrat by 8.8 points more than the national average, suggesting that Obama is leading the race nationally by 9.2 points.

Next up is Alabama. RCP's average shows McCain ahead by 23.8 points in Alabama. On average, Alabama favors the republican by 7.9 points more than the national average, suggesting that McCain has the national lead, by 15.9 points.

Next up is Florida. RCP's average shows Obama up by 3.8 points in Florida. On average, Florida favors the republican by 2.8 points more than the national average, suggesting that Obama is leading the race nationally by 6.6 points.

Next up is Tennessee. RCP's average shows McCain up by 15.7 points in Tennessee. On average, Tennessee favors the republican by 3.2 points more than the national average, suggesting that McCain is leading the race nationally by 12.5 points.

As you can see, there is no clear consensus from these results. Taken altogether, the 50 states project an Obama lead of 0.99 points right now. When the range of skewing is considered, the range could be anywhere nationally from Obama by 3.05 to McCain by 4.71 points.

Once again, the indications from the math are that the race is both close and fluid.


TrackBack URL for this entry:

Listed below are links to weblogs that reference Using State Poll Performance Metrics to Verify National Support:

» The Pink Flamingo linked with Barack & Michelle - Measuring for the New Drapes

Comments (29)

So how does that apply to t... (Below threshold)

So how does that apply to the Electoral College map?

LOL Eric, you anticipated t... (Below threshold)
DJ Drummond:

LOL Eric, you anticipated tomorrow's article.

This election is already ov... (Below threshold)
Tariq Hussein:

This election is already over. There is no way that McCain can come back.

Then the Obaaaaaaama suppor... (Below threshold)
DJ Drummond:

Then the Obaaaaaaama supporters can just take it easy, don't even go to the polls.

heh, Donnks be nervous.

This analysis is not lost o... (Below threshold)

This analysis is not lost on both campaigns. McCain needs to run as the under dog. Obama's campaign is crying racism when Obambi's past relationships are brought up because they know they are vulnerable. Obambi's not pulling away in the battle ground states like the MSM would like us to think. He wasn't able to close the deal on Hillary and he has to be worried about the bad feelings with her supporters.

This election is a... (Below threshold)
This election is already over. There is no way that McCain can come back.

Don't listen to what the media / polls are reporting. Look at what the campaigns are doing, not what they're saying.

If it's true that election is over and there's no way that McCain can come back as you've asserted, Obama need not campaign any more. Consider that after elections, candidates actually do stop campaigning - because the result won't change (as you're asserting that it is now). Given that Obama is still campaigning, Obama's actions indicate his campaign disagrees with your assertion.

This election is already... (Below threshold)

This election is already over. There is no way that McCain can come back.


"Don't listen to what the m... (Below threshold)

"Don't listen to what the media / polls are reporting. Look at what the campaigns are doing, not what they're saying."

Very good point. Do you really think the McCain campaign would waste precious time and money in Minnesota, Wisconsin and Pennsylvania, if they didn't know the race was close in these states?

Obama buying network airtime right before the election is also an indication he doesn't have it in the bag...or he would save his money.

And in the battle ground st... (Below threshold)

And in the battle ground states Obambi is out spending McCain anywhere from 3 to 1 to 7 to 1 for TV adds.

DJ, you can't use RCP avera... (Below threshold)

DJ, you can't use RCP averages - they are garbage. RCP computes straight arithmetic averages, meaning a result of 41% in a sample of 250 is the same as a result of 51% in a sample of 3000, for an average of 46%. In reality, weighting for sample sizes, the average of the two is 50.2%

And let's not even get into their mixing of samples of LVs and RVs, other than to say, in a year like this when nobody knows what the turnout model is going to look like, RVs are probably the most useful for campaign strategists.

Great analysis, as always, ... (Below threshold)

Great analysis, as always, DJ. One thing, though, for other posters: The fact Obama is spending like crazy is not indicative of polling. Anybody in his position would not want to sit on his "lead." Pushing all the way to the finish line is expected from anybody who wants to win.

*Where* he campaigns is, however, indicative of what *his* polls are telling him. Wherever he goes tells everybody how close those states are.

Truedat, moqui. But there ... (Below threshold)
DJ Drummond:

Truedat, moqui. But there are not enough valid state polls for use, and the claim made by the Obambi acolytes, is that the state polls prove their lead nationally is solid. I am simply showing that this is not accurate.

You work with the material available, y'know?

Not sure what this means if... (Below threshold)

Not sure what this means if anything - just an observation.

We have early voting here in Iowa. My wife and I went Saturday and we had to stand in line for about 20 mins or so. The folks working there said they've been incredibly busy since it started.

We were in Michigan over th... (Below threshold)

We were in Michigan over the weekend (live in Oklahoma) and Obama was all over the TV up there all weekend long. He's running mostly ads slamming McCain's health care plan. I'm not sure what all of the implications of that expenditure are, but I was surprised to see so many ads in a state McCain pulled out of so publicly.

Let's remember John Kerry.<... (Below threshold)

Let's remember John Kerry.

The last time we had a presidential race, the exit polls on the day of the election said that John Kerry had won the presidency. Everyone was so sure that even John Kerry thought that he won. Kerry lost.

This election is not over. Don't let the polling discourage you from voting.

Obama cannot close the deal. Democrats are worried about "the Bradley effect" and they are worried about people not telling pollsters the truth for fear of being called racists.

The media and Democratic party talkers (one and the same) are trying to close the deal for Obama and discourage us McCain/Palin voters from voting. Don't fall for it!

No matter what the polls says, it is VITALLY IMPORTANT that all McCain voters vote. This is what really matters.

Democrats are worried ab... (Below threshold)

Democrats are worried about "the Bradley effect" and they are worried about people not telling pollsters the truth for fear of being called racists.

It's only one study, but the Bradley effect could really not help Republicans this year:

However, they found a reverse Bradley effect in 12 primary states. In these states they found actual support for Obama exceeded pre-election polls by totals of 7 percent or more, well beyond the polls' margins of error. These errors ranged up to 18 percent in Georgia.
Don't these comparisons mos... (Below threshold)

Don't these comparisons mostly hinge on the fact that this election is very much like past elections? I'm not really sure that is the case.

I also think moqui brought up some important points. While state polling is sparse, that does not stop anybody from weighting polls based on something really easy like sample size or past pollster performance (for example I put little stock in Zogby). More than anything else though it does not seem like the various pollsters know how to model this election. Too many altered demographics/voters, cellphones, potential Bradley effect (or reverse Bradley effect in some areas); overall it just feels like a really different game than in 2004.

Another thing, has anybody heard about McCain's evangelical get out the vote plan/organization? I think the strength of Bush's ground game in 2004 surprised most people. It was very under the radar but very effective and I wonder if anything like that is going on again this year. The result, Kerry got more votes than any presidential candidate ever: except for Bush.

I don't give a rat about th... (Below threshold)

I don't give a rat about the polls anymore.

The fix is in. It's working. No one will ever listen if McCain warns of a nuclear attack for tomorrow. The people is more likely to believe Obama's bread and circuses, and dreams of Utopian paradise.

This election is over. I will vote for McCain, but I don't trust to hope. It has abandoned this land.

I for one, will look forward to the day I will spend my days in jail for saying something negative about Obama, whatever it may be. Because that day is coming for us, guys. They have control over ever vital institution in this country. All they need is the Presidency, and their total dominance is complete.

Heaven help us. God might be the only thing we still have in the end.

Gloom and doom, the Donks h... (Below threshold)

Gloom and doom, the Donks have gotten under our skin again, making us mad, making us sad and depressed.

Truly look where the candidates are spending their time. At this point time is more precious than $$$.

Interesting analysis, DJ, b... (Below threshold)

Interesting analysis, DJ, but I think you're off the mark on this; it assumes that the electoral dynamics between the states have remained and will remain constant. While they did indeed remain remarkably constant between 2000 and 2004, that is the exception, not the rule. 1992 and 1996 had a very strong third party candidate which muddied things up, and averaging things out completely negates any trends. How do you account for Al Gore's presence on the ballot between 1992 and 2000, which clearly halted Tennessee's Republican trend? And what about West Virginia, which went for Dukakis in 1988?

Furthermore, elections such as 1988 and 1984 that break very strongly for one candidate often inaccurately portray states' partisanship, as the swing states go much more strongly for the winning candidate than usual, but the states already aligned with the winner don't go as strongly because they don't have any further to go. For example, in 1984, Reagan won MA 51-48, MI 59-40 and WY 71-24. In 2004, Bush lost MA 37-62 and MI 48-51, but won WY 69-27. By that logic, you could suggest that WY is trending strongly Republican, which it's obviously not.

A personal attitude to the polls is to look at them like a weather report. I listen to them, but with a grain of salt. If I see polls that look suspect, I treat them as such until I see a handful more that confirm them. I don't believe for a second, for example, that Obama is really ahead in WV or ND, but if he continues to do well there in the polls, I might start. Where polls do fail is to pick the late breakers, which will often determine a close election, or in the case of elections like 1994 or 1980, turn a close election into a blowout.

Amusing Brian. The author ... (Below threshold)
DJ Drummond:

Amusing Brian. The author of that 'science' article is a writer for the Huffington Post and an Obama fund-raiser. You should have scrolled down to the comments first.


There is no way th... (Below threshold)
There is no way that McCain can come back.

He didn't go anywhere, socky.

In the greater L.A. area, t... (Below threshold)

In the greater L.A. area, there are more conservatives than many people may think, but the vast majority live in California's Central Valley (Fresno, Merced, Bakersfield, etc.). I'm curious as to whether pollsters include the Central Valley in the mix.

As a Vonage user, I haven't... (Below threshold)

As a Vonage user, I haven't gotten a telemarketer or pollster call in years. That said - I feel no obligation to tell anyone who calls accurate information about what my plans are regarding who I'm going to vote for - or even if I'm going to vote.

And I wonder what procedures are in place to take account of the respondent who willingly gives misleading information? Is there a certain percentage adjusted for that, or does that fall into the 'uncertainty' area?

This election is different ... (Below threshold)

This election is different in that the main stream media is not just biased, but blatantly supporting a candidate. It's not over yet.

PCC, I was very surprised t... (Below threshold)

PCC, I was very surprised to learn that Gov. Palin made a campaign stop in the other end of LA County from us (I also live in the San Gabriel Valley) the other weekend. And I gather that she was also in Orange County and up in the Silicon Valley. I would be kind of surprised if McCain won California, but why would the campaign spend such a precious asset out here to no purpose?

it does depend on how man... (Below threshold)

it does depend on how many people actually vote what the outcome is. So it isnt over until it's all counted and confirmed.

I am surprised by the fact that several acquaintances
told me that they mailed in their ballots and didnt vote for any President. They skipped the President choices and just did their local election items.
I asked them why. The reasons were the same. They didnt like their party's candidate but refused to cross party lines. So they made a choice.

Were I not a Flyers fan, I ... (Below threshold)

Were I not a Flyers fan, I would not know that Palin was just in Philadelphia.

Didnt we reject the metric ... (Below threshold)
Spurwing Plover:

Didnt we reject the metric system becuase we didnt want to have anything to do with the euroweenie union?






Follow Wizbang

Follow Wizbang on FacebookFollow Wizbang on TwitterSubscribe to Wizbang feedWizbang Mobile


Send e-mail tips to us:

[email protected]

Fresh Links


Section Editor: Maggie Whitton

Editors: Jay Tea, Lorie Byrd, Kim Priestap, DJ Drummond, Michael Laprarie, Baron Von Ottomatic, Shawn Mallow, Rick, Dan Karipides, Michael Avitablile, Charlie Quidnunc, Steve Schippert

Emeritus: Paul, Mary Katherine Ham, Jim Addison, Alexander K. McClure, Cassy Fiano, Bill Jempty, John Stansbury, Rob Port

In Memorium: HughS

All original content copyright © 2003-2010 by Wizbang®, LLC. All rights reserved. Wizbang® is a registered service mark.

Powered by Movable Type Pro 4.361

Hosting by ServInt

Ratings on this site are powered by the Ajax Ratings Pro plugin for Movable Type.

Search on this site is powered by the FastSearch plugin for Movable Type.

Blogrolls on this site are powered by the MT-Blogroll.

Temporary site design is based on Cutline and Cutline for MT. Graphics by Apothegm Designs.

Author Login

Terms Of Service

DCMA Compliance Notice

Privacy Policy