Election Model: Independent and media pollsters agree: * is toast!

[TruthIsAll]

Kerry has pulled ahead of Bush in three models:

1- the nine independent national poll group
2- the 18 independent and corporate national poll group
3- the weighted-state poll popular vote.

Bush is at his 47% ceiling. He won't do much better.

Kerry is at his 47% floor. He will continue to rise from here.

I'm projecting Kerry at 51-52% - as of today. But that's conservative. Look for these numbers to rise from here to the election.

His win probabilties are over 90% in all three models.


http://www.geocities.com/electionmodel/

[endnote]

1. Well, people do what they've got to do to

manage their anxieties... Look, what are you talking about ? Things have changed dramatically over the last 3 weeks. They can change again... Just trying to be realistic here...

[Longhorn]

2. Love your updates, TIA!

By the way, did you see that the Votemaster at www.electoral-vote.com has decided to forego his regression model? He said there was just too much variance in the different polls so that the predictive value was low.

[TruthIsAll]

3. He's got a great site, but I have problems with his policy

of using the latest polls, regardless of how biased they are. Of coursse, he doesn't want to appear to be cherry-picking. The problem is: most are biased, so the Republicans fog the real picture.

That's why I stick with Zogby and ARG, etc. I've stopped blindly incoporating the latest poll that Votemaster puts up - unless t makes sense. Call me a cherry-picker. I throw away the bad ones. That's why my numbers seem so far out there for Kerry. He's doing a lot better than the Repub polls say he is.

As far as regression is concerned, I would never use it to predict based on polling results. A moving average trend is a better and simpler approach. But I don't even use that.

I prefer to keep it simple. I just included a description of the methodology in the site. Read it.

The models are in agreement: Kerry is closing the deal.

[kevin881]

4. you are awesome... can we give TIA a sticky?

i think you should have a "sticky" thread that you can update daily from here until nov 2nd. that way we can find your stats easily.

[featherman]

5. 52-47-1 probably takes MO, AR, maybe AZ, WV

in addition to locking up NV, OH, FL AND makes a run at a few others.
It would be a very good spread but not sure it will happen. Maybe 51-48-1.

[TruthIsAll]

6. Zogby has it tied 45-45 today, will update the model this evening

Oct. Surprise

[ellie]

7. Kicking this

[ArkDem]

8. Wow, you can do things with statistics that are absolutely

unbelievable!Please, keep up the good work!!