Arkansas - Tie - Rasmussen Reports

[The Vorlon]

If it's 45-45 it's not unwinnable. However, it would be interesting to hear Vorlon's view on this one.

First, the usual standard methodological rants on a Rasmussen State poll...

<< insert standard rant....>>

One Day Robot State poll...+/- 4.5% 19/20 - could be a blip...
One day polls - bad - robots - no call backs.....Sunday - Bad day to poll.

<< rant over >>

Rasmussen is fairly tight lipped about the internal guts of how he does his one day state snapshots.  My educated guess is that they are far less tightly "constrained" than his daily tracking poll.

He almost certainly is (or at least should) be building in some fairly aggressive weights to take into account the probabilities of reaching various demographic groups in a one day poll. (especially on a sunday)

These standard caveats being said however, there is enough data out there for some broader conclusions.

Arkansas has a lot of "PMCs" (precarious middle class)  people who are doing "ok" economically, not poor, but lack deep financial reserves to let them feel comfortable about their lives and their futures.  Their employers are often smaller, they may or may not have reliable, portable health care.  Their jobs may or may not be secure.  In short, they are vulnerable.  They are not the captain of their own ship, their are along for the ride on somebody elses ship..

It is these people, many who vote GOP on social issues like abortion, general religious feelings, patriotism, etc, which are eroding on Bush, and Arkansas has a ton of them.

As I believe I have posted before (??) , Bush is really starting to especially feel a hit among married women in his popularity.  This is a group he just has to hold Kerry to at least a tie on or he is in real difficulty.

I have swung Pennsylvania, Ohio, and Wisconsin back over to Kerry based on this errosion among women.  

The Bush folks have picked up on this breakdown among married women and I expect you will see Bush launch a "jobs/kids/soft & fuzzy" offensive quite soon.

I think this torture thing in Iraq will have a far larger political effect than the commentators seem to think.

The torture thing is hard to impossible to poll in the sense that you can't really draw a straight logical line between geneva convention violations in Iraq and how this makes you vote,

This cannot however make anybody feel better about what is going on in Iraq, and to the degree that "angst" builds about Iraq it hurts Bush. (Think PMKs - they Support Bush and the war because it is the "right" thing to do... after the torture photos is it still the right thing to do?)

I think a lot of this is showing up in Married women who usually are the "softest" GOP supporters when they do vote GOP.

A good indicator to watch is if the Kerry folks throw some extra ads into Arkansas this flight of ads.  

Little Rock is pretty cheap to buy and if they sense an opening I expect that Arkansas will get a real good dose of the new Kerry ads (which are pretty decent BTW IMHO, not gamebreakers by any means, but pretty decent)

Don't quite have enough data to have anything super hard in terms of Arkansas conclusions, but botton line to me is that this poll is not crazy or a fluke.

[The Vorlon]

Anyone have any input on why Rasmussen nationally keeps showing the race a tie.. kerry will go up by 3 or 4, then bush come even, then the same thing will happen the other way.. but Kerry seems to be polling really well in all the state polls. Arkansas- a tie, Wisconsin- up 8, Ohio up 4, Iowa up 10, and so on... From the polling rasmussen is putting out it seems he is saying this will be a national dead heat but the electoral college will go to Kerry by a lot. Any input on why the disconnect between the state and national polls of rasmussen?

An interesting and observant question....

Rasmusssen is doing a hard weight in his daily tracking poll to a predetermined distribution of DEms/GOP/Ind which will tends to give you both a very stable result, and one which will not drift too far from dead even...

re one day polls...

One day polls have some inherest challenges built into them.  One of  the obvious of these is that you can't talk to people who are not home.

Normally when you do a poll, you select your sample of XXX phone numbers, and then if you do not reach a certain phone number, you try back tomorrow, or the day after till you have reached as much as you can of the original sample, and then only after you have failed to reach a phone number many times, do you substitute in a replicate number. (You usually try a number about 10 to 12 times before you give up and replace the number)

This compensates for the fact that different demographic groups have diferent social, travel and holiday patterns.

The elderly, for example, go out partying far less on Friday night than to 21 year olds, Republicans tend to leave the area more on weekend vacations, etc...

To use a simple example, imagine you did a poll in Green Bay Wisconsin on the day of a Packers game about building the Packers a new stadium.

 A very meaningful chunk of Green Bay Foorball Fans (whom we presume may disproportionately favor a new statium) are at the football game, and hence a Sunday afternoon poll would not reach them - hence your sample would not be a valid snapshot of the town...

If you called back all the numbers where you got no answer on Sunday afternoon by doing "call backs" on Monday, Tuesday, etc till you reached all your original sample, you could get around this problem.  Obviously a one day snapshot poll makes this impossible.

(This is the same reason why the "snapshot" polls some networks try on the night of the Presidential debates are deeply problematic as well...)

I am assuming Rasmussen is building in some systemic counter weights to this "one day" problem by weighting his sample upwards in terms of the number of boomers, Rebpublicans, etc...

How and to what degree he is doing this I do not know.  Perhaps his new "premium" service will shed some light on this..?

[The Vorlon]

How and to what degree he is doing this I do not know.  Perhaps his new "premium" service will shed some light on this..?

Are you going to sign up for that?

I am undecided on that actually...

Rasmussen is a "decent" pollster (B+ or so) - certainly not an idiot by any means.  I am just not sure there is enough "meat" in his data to tell me anything I don't already know.

[The Vorlon]

How and to what degree he is doing this I do not know.  Perhaps his new "premium" service will shed some light on this..?

Are you going to sign up for that?

I am undecided on that actually...

Rasmussen is a "decent" pollster (B+ or so) - certainly not an idiot by any means.  I am just not sure there is enough "meat" in his data to tell me anything I don't already know.

Have you ever e-mailed them?

Oh ya.. Scott and I have emailed back and forth maybe 10 times or so.  He "kinda" answers my questions

Pollsters hold on to their "secrets" like Col. Sanders does his 13 secret herbs & spices...

[The Vorlon]

As I believe I have posted before (??) , Bush is really starting to especially feel a hit among married women in his popularity.  This is a group he just has to hold Kerry to at least a tie on or he is in real difficulty.

I have swung Pennsylvania, Ohio, and Wisconsin back over to Kerry based on this errosion among women.  

The Bush folks have picked up on this breakdown among married women and I expect you will see Bush launch a "jobs/kids/soft & fuzzy" offensive quite soon.

You'll notice the new Kerry ads have quotes from his daughter and wife.  Hmmmm...

That is NOT a co-incidence...  

[The Vorlon]

You must be logged in to read this quote.

The "horserace" question, (who is ahead, behind, etc ) I agree is pretty worthless right now...

A "likely" voter in May.... if I actually knew what that meant in any meaningful way, I might then know what being ahead or behind among likely voters actually meant then too...

I disagree however about the fundementals behind the data.  Base voter attitudes, issues, etc are very pollable right now.  

Indeed, I might argue since a lot of the "undecided" have not really tuned in yet, their answers to many many questiosn are more rather than less honest this far out than they might be after they lock in on a candidate.

just my 2 cents worth...

[The Vorlon]

hmm.  excluding favorite son bill clinton, arkansas last voted democratic in 1976.

the virginia trending democratic argument is vastly overstated.

I agree. Arkansas and Virginia remain strong GOP.

Seems to me that Rasmussen's polling is all over the place. Thats what you get from small, one day samples. I think he likes it that way because it gets his polling noticed. Particularly this early in the race when there is no way to confirm if he is right or wrong. If I recall correctly the same thing occurred in 2000.

They can't remain strong GOP, since they weren't in 2000...

Point to Gustaf.

[The Vorlon]

Oh ya.. Scott and I have emailed back and forth maybe 10 times or so.  He "kinda" answers my questions

Pollsters hold on to their "secrets" like Col. Sanders does his 13 secret herbs & spices...

I just e-mailed him...I asked him your question about the packers game.

cool...!

Let me know what he sends back.  What exactly did you ask him if I may ask..? (Scott usually answers his email on Saturday mornings BTW)

[The Vorlon]

cool...!

Let me know what he sends back.  What exactly did you ask him if I may ask..? (Scott usually answers his email on Saturday mornings BTW)

Transcript of mt e-mail: (keep in mind I already know the answer to the first question and I just asked it to lead off)

"Hi.  I love your site.  A few questions:
 
1. What Party ID weights do you use?  (ie D, R, I)
 
2. How do you weight state polls, which can sometimes be inaccurate?  For example, teens are out more on friday than seniors, etc.?
 
Thanks,
Dave"

Let me know if you get a "straight" answer... I have mainly gotten general answers that I had to "read between the lines" on....

chop chop!

[The Vorlon]

Let me know if you get a "straight" answer... I have mainly gotten general answers that I had to "read between the lines" on....

chop chop!

I will the post his response right here at this board.  

I hope he gives you an EXACT answer on the Party ID, he gave me about 2 parargraphs worth that I "think" said a +3 dem weight... I am eager to see if I under stood him corectly...

[The Vorlon]

hmm.  excluding favorite son bill clinton, arkansas last voted democratic in 1976.

the virginia trending democratic argument is vastly overstated.

I agree. Arkansas and Virginia remain strong GOP.

Seems to me that Rasmussen's polling is all over the place. Thats what you get from small, one day samples. I think he likes it that way because it gets his polling noticed. Particularly this early in the race when there is no way to confirm if he is right or wrong. If I recall correctly the same thing occurred in 2000.

They can't remain strong GOP, since they weren't in 2000...

Point to Gustaf.

The newbie twists in the wind as Gustaf cuts him down to size and Vorlon tallies the score.

For the record, Virginia was +8% and Arkansas was +5% in 2000, and there is no reason to believe they will be any stronger or weaker relative to the national average result in 2004.

Strong is such a relative term . . .
What ever the term, these states will trend GOP just as much in 2004 as in 2000.

Perhaps the word strong was too strong?

Watch out for Gustaf.. he's a killer..

[The Vorlon]

Vorlon please answer my question as to where you get the information that "married women" are leaving support for Bush behind?

A couple indicators

The "gender gap" has risen substantially poll to poll (ie a Gallup from 6 weeks ago versus a Gallup from 2 weeks ago)  In ths case of Gallup the rise was 4%, in Tipp it was 3%, in Zogby it was also 4%.

Single women already break hugely from the Dems, so the change has to be in married women.

In the March Quinipiac from Penn Bush lost women 42/41, in the April Quinipiac (even though Bush lead went from +4 to +6 overall) he lost women 48/39 ) a negative change among women of 8%)

If you want to be picky, you could limit my comment to "all women" as opposed to "married" women, but in reality single women are reliably democratic, it's the married ones that are swing voters.

There are tons of examples.  I know it's true cause I look for gender gap changes in every poll I look at - it's just about the best indicator of a direction change there is in an election - women are fickle after all