Surge of voter rolls in New Mexico

Zogby and Mason-Dixon agree that New Mexico is tilting to Bush, yet ARG today released a poll showing Kerry leading by a 48-47 percent margin in the state. Whenever I get these conflicting results, I head to the local in-state online newspapers to find out what's up.

I don't know who in the heck Zogby & M-D are polling, because the news looks good for Kerry, as New Mexico's voter rolls have surged by 12% since 2000-- an increase of over 119,000 newly registered voters, mostly among 18-34 year-olds. Here's the facts I culled:

Party ID of NM:

Democrats     51% 
Republicans   32%
Independents  14%

119,000 newly registered:

Democrats     43%
Independents  31%
Republicans   26%

Percent of those newly registered:  (D - I - R) 

18 to 24 year-olds         36%      39  38  23
25 to 34 year-olds         19%	  
With Spanish surnames      31%
The 527 organizations like ACT, Moving America Forward (Richardson's group), New Voters Project, & ACORN have been working like crazy, Richardson is a popular Democratic Governor, the issue of the War in Iraq is driving young people to register & vote like never before, the demographics that lean Democratic are those registering to vote, and Republicans are trailing Independents in those newly registered!

I think we'll just have to chalk this up to the pollsters not being able to reach the actual voters for their polls; because the facts on the ground point toward a Kerry victory in New Mexico.

A 50,000-100,000 Hispanic Vote Switch in Florida?

Zogby just did a poll in Florida, taking into account the Hispanic community.  I want to focus on Dade County, the largest county in Florida and a predominantly Democratic district.

In 2000 - Gore 53  Bush 46
Recent Zogby - Kerry 55  Bush 41

What does this mean, and where is the shift?

First of all, this is a move from a Democratic seven point lead to a Democratic fourteen point lead.  Assuming 750,000 Miami-Dade voters on 11/2 - this translates into an extra NET 50,000 votes for the Democrats, not including new voters (and there are a lot of them).  There is record early voting, with lines of three or four hours on sunny weekend days (people aren't doing this because they think the country is heading in the right direction).

There's more...

The Greatest Turnout

This 'turnout' article in the WaPost points out all types of things that I find agreeable.

First, we'll have the turnout of a lifetime in 2004. I'll get more into this a little further below.

Second, Karl Rove main desire (and seemingly Gallup & SRBI's calling) is to narrow or eliminate the historic Democratic advantage in party identification on Election Day. In the past three presidential elections, 35 percent of voters identified themselves as Republicans, while 38 percent to 39 percent said they were Democrats.

Third, the Republicans have become engaged early and with full effort, but that enthusiastic fundamentalist base is spread out across the nation, not concentrated in battleground states.

Fourth, that increase of wingers, from Rove's lost 4M in 2000, is more than swamped by anti-Bush votes among Democrats.

And fifth, withing the battleground states, voters view Bush more negatively than the overall electorate across the nation, giving Kerry an important advantage among those independents.

Both sides are energized, but much of those voters are not in the battlegrounds. They will increase the total, but not effect the outcome.

Steve Soto Puts the Final Nail in Gallup's Coffin

In their most recent survey of candidate preference in the Presidential election, the highly respected Harris poll, which has nailed the final percentage for each candidate within one percent for three consecutive elections, described their methodology as follows:The Harris Poll® was conducted online within the United States between September 20 and 26, 2004 among a nationwide cross section of 2,301 adults (aged 18 and over), 1,777 of whom are likely voters. Figures for age, sex, race, education, region and household income were weighted where necessary to bring them into line with their actual proportions in the population. Propensity score weighting was also used to adjust for respondents' propensity to be online. Harris does not weight by Party self-identification, but does weight according to many other widely available demographics, such as age, income and race. Similarly, in their recent press release arguing against weighting by Party ID, the Pew Research Center for People and the Press wrote the following:Given that it [Party self-identification] is an attitude and not a personal characteristic, it is not at all comparable to race, ethnicity, gender, age, education, or other demographic markers that are routinely used to check on the representativeness of surveys. The debate over whether or not pollsters should weight by Party self-identification continues, but one thing that polling firms do not debate is that characteristics such as age, region, race, education, income, and gender are demographics and not attitudes. Further, considering that they are demographics, in order for a survey of candidate preference to be accurate, that survey must have representative samples of age, education, gender, income, race and region in order to be representative of the electorate. No one would disagree with this.

No one, that is, except for Gallup:

Gallup has been very forthcoming in responding to my requests for information, and they obviously stand behind their methodology and assumptions. But take a look at the demographic breakdown of this week's sample, and ask yourself how likely is this to replicate itself on Election Day, given the increases in registration this year?

Total Weighted Sample: 557 Likely Voters
(2000 exit poll actual results in parentheses)

By Political Ideology:
Conservative: 41% (29%)
Moderate: 41% (50%)
Liberal: 18% (20%)

Party ID:
GOP: 39% (35%)
Dem: 35% (39%)
Ind: 25% (27%)

Income:
Over $75,000: 32% (28%)
$50-75,000: 16% (25%)
$30-50,000: 26% (24%)
$20-30,000: 11%
Under $20K: 9%

And if this wasn't bad enough,

Race:
White: 85% (81%)
NonWhite: 15% (19%)
Black: (a subset of NonWhite) 8% (10%)
Not only does Gallup not weight by Party self-identification, a characteristic that is debatably a demographic, they do not weight by age, race and income either, characteristics that are unquestionably demographics.

Even without the Party ID debate, Gallup is clearly using an unrepresentative sample. To use such shoddy methodology, have such a tight connection to major media outlets, and simultaneously show Bush ahead by more than any other poll, is nothing short of an irresponsible in-kind contribution to the Bush campaign. Shame on you Gallup. Shame on any news outlet that still uses their polls.

Heavy and Light Polls

Mystery Pollster has two new posts that go into great detail about how different polling firms weight their polls. In fact, he has an entire category on his blog about weighting polls by party. If this is a topic that interests you, the entire category is worth a read. Here is a quick summary of what he has found out about the methodology of various polling firms:
  • ABC News, in addition to the usual demographic weighting in their registered voter sample, partially weights by Party ID in their likely voter sample (but not their registered voter sample). That is, the likely voter sample averages the Party ID in the random sample with Party ID in exit polls from previous Presidential elections. This is done as a nod to the validity of both the weighting and non-weighting arguments.

  • IDB / CSM, conducted by TIPP, uses "dynamic" Party ID weighting. That is, they weight by Party, but not based on 2000 exit polls. Instead, their Party ID weighting is determined by the combined Party ID of all IDB / CSM surveys taken over the course of this campaign. This strikes me as a very good idea, and possibly the best solution I have seen so far.

  • NBC / Wall Street Journal, conducted by Hart / McIntruff, weights by Party ID on a "discretionary" basis. If they find something out of whack with Party ID numbers, they check to see other other demographics are out of whack. If they are, then they weight by Party ID in order to correct the balance. This is heavy on the "artistic" side of polling.

  • Democracy Corps and Fox News both use a complicated and detailed regional weighting model based on historical turnout. This model incorporates neither Party ID nor the potential new voters have to alter past turnout, but it does prevent wild swings. I cannot do justice to this model with a quick summary, but you can click here for more.
Overall, I think what this does show is that most of the differences between polls really are based on methodology--that is not just an old saying. Further, my personal preference leans toward "heavy" polls that do more rather than less weighting. Included in this group are Zogby, Rasmussen, IBD / CSM / TIPP, Democracy Corps and, yes, Fox News / Opinion Dynamics. From my perspective, these polls do a good job of flattening out the "swings" in an electorate that, these days, I do not believe swings very much at all. By contrast, and this my be somewhat cynical of me, the closer a poll is connected to a high circulation news periodical (USA Today, Newsweek, Time), the "lighter" and less weighted that poll becomes. The less weighted a poll is, the more likely it is to swing significantly in one direction or the other. I believe this is very much connected toward the use of "light" polls to sell copies, since nothing helps a poll catch your eye better than a wild swing that breaks your expectations and / or busts up the narrative.

Diaries

Advertise Blogads