Non-Gallup/Rasmussen tracking polls thread

[muon2]

Subsamples have to abide by the same laws of statistics as the overall sample.  Subsamples are not immune from criticism.

If this just a pole of the 18-24 year olds, I'd probably agree.  Newsflash, it isn't.

If you've paid attention, newsflash, I'm the only guy that defends you somewhat when it comes to this issue.  Polls with dozens and dozens of samples make outliers d
ozens and dozens of times more likely.

it *IS UNFAIR* to pick through a poll and find things that seem a little off to validate pre-conceived beliefs about the poll.  Every poll with have something a little off.  No poll with a statistically sound methodology will have McCain leading the 18-24 year olds like this poll has, given the 100 person sample size.  Well, maybe one poll every thousand years.

I'm not a fan at looking at subsamples either.  But if they show something that is basically impossible for them to show, it reveals a methodological weakness.  If McCain was winning 5 of the 8 black people (63%) in an Iowa poll or whatever, that'd be no big deal.  But we can look at sample size and account for the normal error that is involved with looking at subsamples and adjust our criticism to account for the reasons why we shouldn't critique subsamples under most situations.  

I agree with you that, in general, criticizing subsamples is bad.  Of course they average out in any good poll and some in every poll with appear off.

But this poll is one in a gazillion or it has flawed methodology.  You can't dismiss this fact under the above rule-of-thumb.  Subsamples are generally useless, but rarely they are incredibly revealing, and this is one of those cases.  This is partly why polls publish their subsamples, so we can understand the inner workings of the poll a little bit better.

I think this should go a step further. What I haven't seen in this discussion is the recognition that the poll is weighted. When a poll weights raw values or preselects samples to fill, the intent is to create a more accurate poll. Those adjustments are made at the subsample level and as a result can skew those or other subsamples.

For example, lets assume that there is weighting of the sample by age. That does not imply that there is any mechanism to weight within that subsample. Quoting results for the age subsamples, is now equivalent to posting a raw, unadjusted poll. Since the pollster has reason to believe that the raw numbers would be skewed and therefore performs some weighting, there is every reason to believe that the subsample would show a higher likelihood of skewing based on the reduced statistical size in the subsample.

As another example, suppose that the weighting is by party ID and not by age. Now if the age subsample is broken out, it could carry the same party ID weight as the larger sample. If so, there would be clear methodological bias. This could be corrected by applying different party ID weights to different age samples, but I'd want to know that from a pollster before concluding that a subsample was free from this type of bias.

To conclude, I tend to give less import to subsamples than the statistical weight might suggest, unless I know how any weighting or sample preselection works at the level of the reported subsamples.

[Alcon]

muon,

Fair point.  If it's an unweighted sample, would we have the right idea?  My math education doesn't go much beyond Algebra II so I figured I'd check.

[muon2]

muon,

Fair point.  If it's an unweighted sample, would we have the right idea?  My math education doesn't go much beyond Algebra II so I figured I'd check.

If an unweighted sample is randomly selected from the total population, and the subsample is also a random sample, then the statistical conclusions on the subsample are a valid as on the whole sample. However, most polls don't trust that they can get a truly random sample, so they make adjustments to compensate for the systematic errors that they believe they would introduce. There's nothing wrong with correctly compensating for measured systematic bias in a statistical sample, but those corrections will not in general behave the same for all subsamples. I only wish that polls would quote both their systematic as well as statistical errors.

[Rowan]

IBD/TIPP
Obama 45.8%(nc)
McCain 41.9%(-0.4)

[Sam Spade]

Daily Tracker Table - October 25, 2008

Poll Name	Obama	McCain	Margin	Change	Observation
Zogby	51.1%	41.6%	O+9.5%	M+0.8%	Who knows - it's Zogby!
Rasmussen	52.32%	44.43%	O+7.89%	O+0.89%	The last three samples looks about the same to me.  I think today's and Wednesday's are a tad more pro-McCain than Thursday's, but whatever, not important...
Battleground	49%	46%	O+3%	NC	No polling done today.
Hotline	50%	43%	O+7%	NC	It is fairly likely that today's sample was more pro-McCain than yesterday, but maybe not.  Tough to tell.
R2000/DKos	52%	40%	O+12%	NC	Down from yesterday's bumper Obama sample.
Gallup
Expanded	51%	43%	O+8%	O+1%	The sample that moved on today probably wasn't as pro-Obama as yesterday, but moreso in terms of likelies.
Traditional	51%	44%	O+7%	O+2%
IBD/TIPP	45.8%	41.9%	O+3.9%	O+0.4%	Hard to tell.
ABC/WP	53%	44%	O+9%	NC	Hard to tell how the samples work here.
POLLS AVERAGE	50.53%	43.05%	O+7.48%	O+0.25%	Note: I do include Battleground in this average, even though it didn't poll yesterday.  If you wish not to, just remove and re-round.

[Rowan]

ZOGBY SUNDAY: 'In single day of polling, it was 49% to 46% in favor of Obama'... Developing...

[Lunar]

ZOGBY SUNDAY: 'In single day of polling, it was 49% to 46% in favor of Obama'... Developing...

He doesn't usually do single days, does he?

What a buffoon.  But his margins are about the RCP average, which isn't coincidental in my book.  He won't have an awful year in his final prediction.

[Rowan]

ZOGBY SUNDAY: 'In single day of polling, it was 49% to 46% in favor of Obama'... Developing...

He doesn't usually do single days, does he?

What a buffoon.  But his margins are about the RCP average, which isn't coincidental in my book.  He won't have an awful year in his final prediction.

I think he means tonights daily sample was 49-46. Which, if my math is correct, should bring the tracker down to Obama +4 or 5.

[ChrisFromNJ]

You righties.... er, I mean indies... are really getting desperate when you are flaunting a one day average in a Zogby poll.

[Rowan]

Zogby last three individual nights:
Thursday Obama 49%- McCain 42%
Friday Obama 50%- McCain 45%
Saturday Obama 49%- McCain 46%

[Sam Spade]

After the ten point movement the last four days, I am willing to bet even money that Zogby shows McCain within a couple of points or even ahead sometime before the election.

[J. J.]

Zogby last three individual nights:
Thursday Obama 49%- McCain 42%
Friday Obama 50%- McCain 45%
Saturday Obama 49%- McCain 46%

A.  It could be a bad sample.

B.  It's Zogby!

[Sam Spade]

On his website...

"I have alluded before to this strange, magnetic pull that brings Obama down to 48% or 49%, a danger zone for him. McCain's gains are among white voters, where he now leads by 12 points, and with men, where he again has a healthy lead. There is still a lot of campaign to go. A lot of campaign to go." - John Zogby
lol...  such an attention whore.

[cinyc]

I see Zogby's still generating polls headlines.  Is there a bigger media whore pollster out there?

[TheGlobalizer]

Zogby last three individual nights:
Thursday Obama 49%- McCain 42%
Friday Obama 50%- McCain 45%
Saturday Obama 49%- McCain 46%

ELECTION SHOCKER: MCCAIN SURGING

If trends continue, McCain projected to win by 15%+.

[Rowan]

Zogster
Obama 49.4%(-1.7)
McCain 44.1%(+2.5)

[Sam Spade]

Zogster
Obama 49.4%(-1.7)
McCain 44.1%(+2.5)

Clearly, McCain is going to win by a landslide.

[Tender Branson]

Zogster
Obama 49.4%(-1.7)
McCain 44.1%(+2.5)

You must be logged in to read this quote.

LOL Zogby, you want to be in the news, right ?!

[Sam Spade]

Zogster
Obama 49.4%(-1.7)
McCain 44.1%(+2.5)

You must be logged in to read this quote.

LOL Zogby, you want to be in the news, right ?!

With his weighting, that type of Independent margin would be consistent with a five-point lead.

[Eraserhead]

wow this is almost as awesome as that time Obama won the California primary by 14 points... oh wait...

[Sam Spade]

wow this is almost as awesome as that time Obama won the California primary by 14 points... oh wait...

That's the Zogby election day surge (also saw it in New Hampshire 2008 Dem primary and Florida 2000 (from Gore +10 to Gore +1, lol))  This is something different.

[Eraserhead]

wow this is almost as awesome as that time Obama won the California primary by 14 points... oh wait...

That's the Zogby election day surge (also saw it in New Hampshire 2008 Dem primary and Florida 2000 (from Gore +10 to Gore +1, lol))  This is something different.

Various garbage from the same awful source.

This guy should be selling his body to the night somewhere.

[minionofmidas]

wow this is almost as awesome as that time Obama won the California primary by 14 points... oh wait...

That's the Zogby election day surge (also saw it in New Hampshire 2008 Dem primary and Florida 2000 (from Gore +10 to Gore +1, lol))  This is something different.

Various garbage from the same awful source.

This guy should be selling his body to the night somewhere.

Night is a far more discerning buyer than the American punditocracy (or the German punditocracy for that matter). Not a chance.

[freedomburns]

Zogby shmogby.  they suck.

[Tender Branson]

Zogby's 8 telephone battleground polls will be out tomorrow.