Non-Gallup/Rasmussen tracking polls thread

[Tender Branson]

Diageo/Hotline - Wednesday, Oct. 29:

Obama 49 (-1)
McCain 42 (nc)

[Sam Spade]

Daily Tracker Table - October 29, 2008

Poll Name	Obama	McCain	Margin	Change	Observation
Zogby	49.1%	44.4%	O+4.7%	O+0.4%	It's Zogby!
Rasmussen	50.24%	47.07%	O+3.17%	M+1.71%	Today's sample reflects the aggregate result pretty well.
Battleground	49%	46%	O+3%	NC	There should be a favorable Obama sample bumping off tomorrow.  Let's see where we are then.
Hotline	49%	42%	O+7%	M+1%	Considering the lack of movement over the past few days, the sample was probably better for McCain than the one which bumped off.
R2000/DKos	50%	44%	O+6%	M+1%	Still trending upward for McCain here.
Gallup
Expanded	51%	44%	O+7%	UC	Good Obama sample bumped on, I guess.
Traditional	49%	46%	O+3%	O+1%
IBD/TIPP	46.9%	43.9%	O+3.0%	M+1.0%	As mentioned last evening, a good Obama sample bumped off today.
NOT UPDATED
ABC/WP	52%	44%	O+8%	O+1%	A good McCain sample fell off today.
POLLS AVERAGE	49.53%	44.55%	O+4.98%	M+0.35%	Slow trend continues.

[Sam Spade]

IBD/TIPP - October 29, 2008
Obama 46.9% (-0.8 )
McCain 43.9% (+0.2)
Undecided 9.2% (+0.6)

[TheGlobalizer]

IBD/TIPP - October 29, 2008
Obama 46.9% (-0.8 )
McCain 43.9% (+0.2)
Undecided 9.2% (+0.6)

Wow, Obama under 47?  9.2% undecided?

[Swing low, sweet chariot. Comin' for to carry me home.]

IBD/TIPP - October 29, 2008
Obama 46.9% (-0.8 )
McCain 43.9% (+0.2)
Undecided 9.2% (+0.6)

*IF* this poll is accurate, McCain is well within striking distance: if it gets to be a 1-2 point race with Obama around 47%, McCain can win this.

[© tweed]

IBD/TIPP - October 29, 2008
Obama 46.9% (-0.8 )
McCain 43.9% (+0.2)
Undecided 9.2% (+0.6)

*IF* this poll is accurate, McCain is well within striking distance: if it gets to be a 1-2 point race with Obama around 47%, McCain can win this.

I still think McCain wins the PV before he gets to 270, and you're looking at one poll, and I disagree with your statement, and etc

[Sam Spade]

Tracker fully updated.

[Tender Branson]

Uh-oh, McSurge is over !

Zogby/Reuters/C-Span - October 30:

Obama 50 (+1)
McCain 43 (-1)

[cinyc]

Uh-oh, McSurge is over !

Zogby/Reuters/C-Span - October 30:

Obama 50 (+1)
McCain 43 (-1)

It's Zogby.

Actual numbers to the super-duper Zogby tenth:
Obama 50.2% (+1.1)
McCain 43.3% (-1.1)

[Rococo4]

i just dont know what will happen until his 5 pm election day polls are released

[Wall St. Wiz]

I expect Zogby to say that the informercial brought undecideds, soft Dems, and a few republicans back to Obama.  He will show Obama up 10 at minimum, maybe 12, by Saturday.  By Monday night it will be a statistical dead heat again with Obama up 2 or 3.  Tuesday at 5pm he'll show Obama back at 5 for his final prediction.  The man is slime.

[Tender Branson]

R2000/DailyKos - Thursday Oct. 30:

Obama 50 (nc)
McCain 45 (+1)

[Tender Branson]

The last days of Zogby's 2004 tracking:

6 days before the election it was

Bush 48%
Kerry 46%

http://www.zogby.com/news/ReadNews.dbm?ID=922

[Tender Branson]

Diageo/Hotline - Thursday, October 30:

Obama 48 (-1)
McCain 42 (nc)

[Tender Branson]

Battleground is frozen for a few days now ...

Thursday, October 30:

Obama 49 (nc)
McCain 46 (nc)

[Sam Spade]

I expect Zogby to say that the informercial brought undecideds, soft Dems, and a few republicans back to Obama.  He will show Obama up 10 at minimum, maybe 12, by Saturday.  By Monday night it will be a statistical dead heat again with Obama up 2 or 3.  Tuesday at 5pm he'll show Obama back at 5 for his final prediction.  The man is slime.

With the exception of the last sentence, I agree with this man.

[Sam Spade]

Daily Tracker Table - October 30, 2008

Poll Name	Obama	McCain	Margin	Change	Observation
Zogby	50.2%	43.3%	O+6.9%	O+2.2%	It's Zogby!
Rasmussen	50.88%	46.21%	O+4.67%	O+1.50%	Today's sample mirrors yesterday.
Battleground	49%	46%	O+3%	NC	No change for five days.
Hotline	48%	42%	O+6%	M+1%	Considering the lack of movement over the past few days, the sample was probably better for McCain than the one which bumped off.
R2000/DKos	50%	45%	O+5%	M+1%	Still trending upward for McCain here.
Gallup
Expanded	51%	44%	O+7%	NC	Kind of odd sample bumped on.
Traditional	50%	45%	O+5%	O+2%
IBD/TIPP	47.7%	43.6%	O+4.1%	O+1.1%	Looks like a good Obama sample bumped on.
ABC/WP	52%	44%	O+8%	O+1%	Nothing much going on here.
POLLS AVERAGE	49.79%	44.33%	O+5.46%	O+0.48%	Slight bump back for Obama today.

[Alcon]

IBP/TIPP has, um, 'corrected' their process:

You must be logged in to read this quote.

Clicky

I personally think he's making some amateur pollster mistakes in 'correcting' his poll.  It's a little Zogbyian, but make your own decisions.

[TheGlobalizer]

IBP/TIPP has, um, 'corrected' their process:

You must be logged in to read this quote.

Clicky

I personally think he's making some amateur pollster mistakes in 'correcting' his poll.  It's a little Zogbyian, but make your own decisions.

Certainly explains that bizarro "McCain winning huge among young voters" number.

[Alcon]

Nah.  That was their attempt to correct it.  Basically, they'd been getting a weirdly low number of youth voters in their polls.  They ignored it, until the sample shifted to being ridiculously McCain.  To fix this, they started applying a non-random sample to meet quotas.  Basically, he ignored a methodological flaw until it started showing up, and then applied a non-random solution.  It's shoddy pollster behavior.

[Sam Spade]

Table updated with TIPP/Gallup.

[TheGlobalizer]

Nah.  That was their attempt to correct it.  Basically, they'd been getting a weirdly low number of youth voters in their polls.  They ignored it, until the sample shifted to being ridiculously McCain.  To fix this, they started applying a non-random sample to meet quotas.  Basically, he ignored a methodological flaw until it started showing up, and then applied a non-random solution.  It's shoddy pollster behavior.

What I meant was that what you quoted indicated why the numbers were screwy (in that much-highlighted chart last week) in the first place -- extremely low sample sizes.

I'm not enough of a stats guy to get into the fix side of things.

[Lunar]

IBP/TIPP has, um, 'corrected' their process:

You must be logged in to read this quote.

Clicky

I personally think he's making some amateur pollster mistakes in 'correcting' his poll.  It's a little Zogbyian, but make your own decisions.

So J.J. can stop hiding from lightning and admit he was wrong and we were right?

[Verily]

Nah.  That was their attempt to correct it.  Basically, they'd been getting a weirdly low number of youth voters in their polls.  They ignored it, until the sample shifted to being ridiculously McCain.  To fix this, they started applying a non-random sample to meet quotas.  Basically, he ignored a methodological flaw until it started showing up, and then applied a non-random solution.  It's shoddy pollster behavior.

What I meant was that what you quoted indicated why the numbers were screwy (in that much-highlighted chart last week) in the first place -- extremely low sample sizes.

I'm not enough of a stats guy to get into the fix side of things.

True; we were assuming that young voters were a reasonable 9-10% of the sample in our calculations when they were actually about 3%. That would increase the MoE substantially, to the point where the results within the subsample were outside the margin of error, but not radically so. But the undersampling clearly was a major problem.

[Alcon]

What I meant was that what you quoted indicated why the numbers were screwy (in that much-highlighted chart last week) in the first place -- extremely low sample sizes.

I'm not enough of a stats guy to get into the fix side of things.

What happened is they took a screwy sample size and weighted it higher.  That makes it less likely to be indicative of bad methodology, because the raw sample was smaller.  On the other hand, the pollster literally just proved their methodology is bad when they tried to "fix" it.  The problem is, the initial tiny sample size is indicative of a methodological problem.  They essentially outright admitted they had one, and then they de-randomized their sample to fix it.  Bad juju.

It was indicative of some problem in methodology -- that problem was undersampling, which cannot be fixed by drastically overweighting a tiny sample, especially when that sample was wrong.  I was right, J. J. wasn't.  I am King of the Mountain, bring me your women.