Florida: Gravis Marketing - Romney 48% Obama 47%

[MorningInAmerica]

http://www.pollheadlines.com/pdf/2012/gravis_florida_sept18.pdf

Obama: 47.1%
Romney: 47.7%

[Starbucks Union Thug HokeyPuck]

So... Obama +10 then?

Please stop posting their "polls" here.  They are showing no change in the race since their last poll at the very end of GOP convention, when the rest of the country has obviously shifted.  C'mon.   

[MorningInAmerica]

It's a poll. If it's good enough for Nate Silver (an actual poll aggregator), then it's good enough for an atlas forum that posts pretty much every poll that exists. Get over yourself, and stop telling people what to do.

[Starbucks Union Thug HokeyPuck]

It's a poll. If it's good enough for Nate Silver (an actual poll aggregator), then it's good enough for an atlas forum that posts pretty much every poll that exists. Get over yourself, and stop telling people what to do.

"please" would designate a request, I'm not telling you to do anything, but any objective person would look at how they have produced outliers across the country. 

[MorningInAmerica]

but any objective person would look at how they have produced outliers across the country.  

Sure. But every Gravis poll that has come out has been posted here by red and blue avatars alike. Where did I say anything about the objectivity of the poll? I didn't, and that's obvious from my very first post. But apparently, you enjoy projecting things on others, which is why I responded in kind to you telling me stop "stop posting these polls, here." Seriously, this is a political poll forum. Stop getting so worked up over polling you don't agree with.

And ps, it did not say "please" before you edited it. Nice try.

[Starbucks Union Thug HokeyPuck]

but any objective person would look at how they have produced outliers across the country.  

Sure. But every Gravis poll that has come out has been posted here by red and blue avatars alike. Where did I say anything about the objectivity of the poll? I didn't, and that's obvious from my very first post. But apparently, you enjoy projecting things on others, which is why I responded in kind to you telling me stop "stop posting these polls, here." Seriously, this is a political poll forum. Stop getting so worked up over polling you don't agree with.

And ps, it did not say "please" before you edited it. Nice try.

I'd edited the part about the lead it gave Romney.  I initially said they showed an improvement since their previous poll, which it didn't, and I corrected that. 

And you're right.  this is a a political poll forum.  Can we try to discuss things worth discussing, i.e.: polls and firms with credibility and not every poll no-name companies pull out their ass.  For this very reason.  YOU stop getting worked up about the fact that it's an reasonably irritating this when trying to analyze a race in a intelligent manner. 

[J. J.]

It's a poll.  It isn't one of the major ones, and should be weighed accordingly, but it should be posted.

[Likely Voter]

I agree that all polls should be posted.

Believed?  That's a different story

[krazen1211]

Great news!

[Umengus]

party id: D+5,6

yes it's biased, but not like you would like to think...

[ajb]

For reference, here's the Gravis poll of the PA senate race, where they have Tom Smith ahead of Bill Casey, 47-28:

http://www.scribd.com/doc/105306657/PA-Report-1

[SUSAN CRUSHBONE]

Great news!

It's amusing that krazen is desperate enough to latch onto this obvious garbage poll.

[Lief 🗽]

Tied in a poll that has a ten point Republican house effect? Sounds good to me.

[Craigo]

For reference, here's the Gravis poll of the PA senate race, where they have Tom Smith ahead of Bill Casey, 47-28:

http://www.scribd.com/doc/105306657/PA-Report-1

wtf

Also, whining about party ID is for people who don't understand polling.

[MorningInAmerica]

Tied in a poll that has a ten point Republican house effect? Sounds good to me.

Where are you getting the 10 point house effect from for Gravis? Nate Silver said their house effect was essentially 4 points, which is really no different than PPPs, which is just over 3 points. http://fivethirtyeight.blogs.nytimes.com/2012/08/30/aug-29-so-much-depends-upon-ohio/ So are we just all going to start making up facts about polls we don't like now?

[Craigo]

For reference, here's the Gravis poll of the PA senate race, where they have Tom Smith ahead of Bill Casey, 47-28:

http://www.scribd.com/doc/105306657/PA-Report-1

wtf

Also, whining about party ID is for people who don't understand polling.

And speaking as someone who's actually done this before, their numbers are still suspiciously high for a two-day survey. (not as bad as previous polls, which were simply unbelievable.) I'm getting a distinct Strategic Vision/Research 2000 vibe from this shop.

Edit: 500 likely voters from 12 to 4 pm on a Tuesday? Bull ing sh**t.

Edit 2: Lol, the idiot reversed the Senate numbers in the release. Otherwise, he was on track to making Zogby's 2006 results look like a crystal ball.

[Umengus]

For reference, here's the Gravis poll of the PA senate race, where they have Tom Smith ahead of Bill Casey, 47-28:

http://www.scribd.com/doc/105306657/PA-Report-1

wtf

Also, whining about party ID is for people who don't understand polling.

lol

[mondale84]

For reference, here's the Gravis poll of the PA senate race, where they have Tom Smith ahead of Bill Casey, 47-28:

http://www.scribd.com/doc/105306657/PA-Report-1

wtf

Also, whining about party ID is for people who don't understand polling.

lol

You don't understand polling, so stop commenting on polls. Thanks.

[Umengus]

For reference, here's the Gravis poll of the PA senate race, where they have Tom Smith ahead of Bill Casey, 47-28:

http://www.scribd.com/doc/105306657/PA-Report-1

wtf

Also, whining about party ID is for people who don't understand polling.

lol

You don't understand polling, so stop commenting on polls. Thanks.

[Craigo]

For reference, here's the Gravis poll of the PA senate race, where they have Tom Smith ahead of Bill Casey, 47-28:

http://www.scribd.com/doc/105306657/PA-Report-1

wtf

Also, whining about party ID is for people who don't understand polling.

lol

Ever work as a professional pollster?

Thought not.

Self-professed party ID is very volatile, and a dependent variable of voter intention. In other words, if you think that topline results are due to party ID, you've got it backwards.

This is why virtually all real pollsters don't weight by party ID. (It's why John Zogby, who believed very strongly in weighting by party ID, crashed and burned so terribly.) Even Rasmussen, the only pollster I know of who weights by party ID at all, uses a three-month rolling average derived from his raw samples.

This is why people who know what they're talking about discuss demographics, not party ID. Race, age, and income are relatively stable - they vary little from cycle to cycle, and even then in predictable ways.

Ever hear the saying regarding the military "Professionals discuss logistics, and amateurs talk tactics?" Same situation.

(Other signs you don't know what the hell you're talking about:

1. You say "PPP/Rasmussen, add/subtract four points"
2. You interpret a single number's movement within a single poll's margin of error as "movement"
3. You use the phrase "statistical tie" for any result that doesn't have the candidates exactly tied.)

[Craigo]

One more point: I don't have it on me, but in grad school I did a short paper on party ID and two-party vote share. It's lost to history, my old college email server, and a fried laptop, but the basic results: (and you can run the numbers yourself using Roper's exit poll data, which dates back to 1976)

There is virtually no relationship between party ID and that party's presidential vote share. In fact, for the elections 1976-2004 there is actually a very slight negative correlation for both parties. A hell of a lot more people claimed to be Democratic than actually voted for Carter in both 1976 and 1980. If you remove those two elections and run only 1984-2004 (the post Solid South era), you get a positive correlation, but one that's so weak (below .25) that it's basically equivocal.

The correlation for the differences between party IDs and presidential vote shares is a little better - but still weak. (And it gets demolished if you add 1980 and 1976, of course).

None of this includes 2008, because that election hadn't occurred when I ran the numbers. But the bottom line is that the relationship basically doesn't exist - the 1984, 1988, and 1992 electorates were all 38D-35R, for example.

[Badger]

One more point: I don't have it on me, but in grad school I did a short paper on party ID and two-party vote share. It's lost to history, my old college email server, and a fried laptop, but the basic results: (and you can run the numbers yourself using Roper's exit poll data, which dates back to 1976)

There is virtually no relationship between party ID and that party's presidential vote share. In fact, for the elections 1976-2004 there is actually a very slight negative correlation for both parties. A hell of a lot more people claimed to be Democratic than actually voted for Carter in both 1976 and 1980. If you remove those two elections and run only 1984-2004 (the post Solid South era), you get a positive correlation, but one that's so weak (below .25) that it's basically equivocal.

The correlation for the differences between party IDs and presidential vote shares is a little better - but still weak. (And it gets demolished if you add 1980 and 1976, of course).

None of this includes 2008, because that election hadn't occurred when I ran the numbers. But the bottom line is that the relationship basically doesn't exist - the 1984, 1988, and 1992 electorates were all 38D-35R, for example.

You should post here much, much more often.

[Umengus]

One more point: I don't have it on me, but in grad school I did a short paper on party ID and two-party vote share. It's lost to history, my old college email server, and a fried laptop, but the basic results: (and you can run the numbers yourself using Roper's exit poll data, which dates back to 1976)

There is virtually no relationship between party ID and that party's presidential vote share. In fact, for the elections 1976-2004 there is actually a very slight negative correlation for both parties. A hell of a lot more people claimed to be Democratic than actually voted for Carter in both 1976 and 1980. If you remove those two elections and run only 1984-2004 (the post Solid South era), you get a positive correlation, but one that's so weak (below .25) that it's basically equivocal.

The correlation for the differences between party IDs and presidential vote shares is a little better - but still weak. (And it gets demolished if you add 1980 and 1976, of course).

None of this includes 2008, because that election hadn't occurred when I ran the numbers. But the bottom line is that the relationship basically doesn't exist - the 1984, 1988, and 1992 electorates were all 38D-35R, for example.

"Self-professed party ID is very volatile, and a dependent variable of voter intention."

lol no and certainly not today.
 
"In other words, if you think that topline results are due to party ID, you've got it backwards."

Yes I think and polls for now confirm that.

Guy, I'm on this forum since 2003 and I can say to you that the party id is the base of the polling. Each day it's confirmed. Look at the last washington post poll with a D +9 sample, look at the ppp polls each week: there is a very strong correlation between the result of obama and the difference between democrats and republicans: greater the gap is, greater the obama result is.

And if Ras gives better results to Romney, it's due to the fact that the numbers of republicans is more important than in others polls.

And I can continue again and again... it's quite logical: Obama will do better in a sample with 40 % of democrats than 30 %...

[The world will shine with light in our nightmare]

I'm surprised no one has pointed out the decimal points, yet.

[mondale84]

One more point: I don't have it on me, but in grad school I did a short paper on party ID and two-party vote share. It's lost to history, my old college email server, and a fried laptop, but the basic results: (and you can run the numbers yourself using Roper's exit poll data, which dates back to 1976)

There is virtually no relationship between party ID and that party's presidential vote share. In fact, for the elections 1976-2004 there is actually a very slight negative correlation for both parties. A hell of a lot more people claimed to be Democratic than actually voted for Carter in both 1976 and 1980. If you remove those two elections and run only 1984-2004 (the post Solid South era), you get a positive correlation, but one that's so weak (below .25) that it's basically equivocal.

The correlation for the differences between party IDs and presidential vote shares is a little better - but still weak. (And it gets demolished if you add 1980 and 1976, of course).

None of this includes 2008, because that election hadn't occurred when I ran the numbers. But the bottom line is that the relationship basically doesn't exist - the 1984, 1988, and 1992 electorates were all 38D-35R, for example.

"Self-professed party ID is very volatile, and a dependent variable of voter intention."

lol no and certainly not today.
 
"In other words, if you think that topline results are due to party ID, you've got it backwards."

Yes I think and polls for now confirm that.

Guy, I'm on this forum since 2003 and I can say to you that the party id is the base of the polling. Each day it's confirmed. Look at the last washington post poll with a D +9 sample, look at the ppp polls each week: there is a very strong correlation between the result of obama and the difference between democrats and republicans: greater the gap is, greater the obama result is.

And if Ras gives better results to Romney, it's due to the fact that the numbers of republicans is more important than in others polls.

And I can continue again and again... it's quite logical: Obama will do better in a sample with 40 % of democrats than 30 %...

Just because you've been here for a long time doesn't mean you actually know anything...

...what it does tell us is that you've been trolling this forum for almost nine years and it would be nice if you would stop today.