wow. Gallup Obama 52 McCain 41

[Willie99]

So you should only use LVs when it's closer to the date of voting? They are evidently more reliable then but less reliable the rest of the time?

That doesn't make any sense. The standards for measuring LVs doesn't change, it means you're trying to account for the people that vote historically, and weigh them differently than the people who don't vote historically.

Your article sounds like a lot of twisting in the wind to me. While we do know that LVs are more accurate than RVs near the election date, that can be proved, we have absolutely no idea if your author's theory is correct. It can't be tested.

I simply believe people who are more likely to vote are more likely to vote, that variable doesn't change day to day.

 

[gtc08]

if you use registered voter logic it'll be a even bigger deficit for mccain. in the state of pa for example the dems have 200,000 new registered voters, independents have 120k and the repubs have 34k.

 

[Willie99]

I'll let Gallup explain it

There are a variety of ways to estimate likely voters. Different pollsters and polling groups have different approaches. Gallup has spent decades developing our system, which we have found in election after election helps improve our accuracy in terms of how our final poll before an election compares to the actual vote percentages on Election Day itself.
Gallup's system consists of asking respondents a battery of questions about past voting, current interest in the election, and self-reported interest in voting. These include such questions as "How much thought have you given to the upcoming election for president?", "Do you happen to know where people who live in your neighborhood go to vote?", "Have you ever voted in your precinct or election district?", "Do you yourself plan to vote in the presidential election this November?", and "Rate your chances of voting in November's election for president on a scale of 1 to 10."
Putting all of this information together, we can assign each voter a score based on our estimate of his or her probability of actually voting. Based on assumptions about actual turnout, we use the scores to select the pool of voters that we think best represents a realistic pool of likely voters come Election Day. In the Sept. 5-7 poll, this group of likely voters went 54% for McCain, 44% for Obama.
Comparing across national adults, registered voters, and likely voters, one can see that at this point, shortly after the Republican National Convention, the more we winnow the sample down to voters with the highest likelihood of voting, the better McCain does. This is not unusual. The Republican candidate often benefits from a turnout advantage.
Here's an example. Gallup's final poll before the 2004 election showed the following:
Registered voters
George W. Bush 46%
John Kerry 48%
Likely voters
George W. Bush 49%
John Kerry 47%


----------------------------------------------------------------------

 

[cincy_]

Your article sounds like a lot of twisting in the wind to me. While we do know that LVs are more accurate than RVs near the election date, that can be proved, we have absolutely no idea if your author's theory is correct. It can't be tested.

They didn't "prove" anything ... they looked at the 2000 elections and they are making inferences ... I can't help you if you don't understand the damn article.

Your point is that LV's were obviously better and you RIDICULED someone. My point is that they both have advantages and disadvantages.

Willie based on your postings, I KNOW that you don't know shit on this topic ... so please give it up and don't waste your time and don't waste my time.

It's ok to not know this shit ... believe me ... but if you want to act like you do, write the Wall Street Journal instead ... tell them that their polling of RV's should be changed.

 

[3peet]

???? whats with the technicalities?? Obama's killin it in the MAJORITY of the polls.

Whats the problem?

 

[BetIt]

Willie: You do realize you've cited gallups registered voters polls before when touting McCain?

 

[cincy_]

Willie ... I will debate you on any other subject ... but as far as polling goes, this is my last post.

I can't waste my time with these juvenile copy/paste jobs and infantile conclusions.

 

[Willie99]

Cincy, nobody has to change a thing. They can report the polling data as they see fit, and we all can use the polling data as we choose. You need a fucking chill pill already.

History shows LVs are more accurate than RVs near election day, I'm truly sorry about that.

Some extrapolation of RVs vs LVs from early poll results is kinda worthless to me. I can't even imagine the ASSUMPTIONS they must be using. Change a variable in physics here or there, and pigs can fly too.

 

[Willie99]

Willie: You do realize you've cited gallups registered voters polls before when touting McCain?

I'm sure I have, so?

Did I ever argue RV's > LVs?

and you just happen to agree with me to.

 

[Willie99]

Willie ... I will debate you on any other subject ... but as far as polling goes, this is my last post.

I can't waste my time with these juvenile copy/paste jobs and infantile conclusions.

Juvenile cut and paste? I just let Gallup explain the difference in their own polls to you. Kinda thought that might be relevant.

in the meantime, I can only surmise you believe your cut and paste job of some reporters theory based on some unstated assumptions of variables carries the day.

OK, we can just agree to disagree, I good with that.

 

[BetIt]

I'm sure I have, so?

Did I ever argue RV's > LVs?

and you just happen to agree with me to.

Well you can't just totally toss out the poll because it's not convenient. I think RCP & Pollster does a great thing by looking at all of them. I also think this is what you have to....look at all of them together....just don't tout one because you like the numbers best (which 99% of people do on here).

I do agree with Cinci when he says both have their advantages and disadvantages...which is why I say look at them all.

 

[cincy_]

Cincy, nobody has to change a thing. They can report the polling data as they see fit, and we all can use the polling data as we choose. You need a fucking chill pill already.

History shows LVs are more accurate than RVs near election day, I'm truly sorry about that.

Some extrapolation of RVs vs LVs from early poll results is kinda worthless to me. I can't even imagine the ASSUMPTIONS they must be using. Change a variable in physics here or there, and pigs can fly too.

The posts in which you're trying to act like you know anything about polling is a waste of time and effort (yours and mine) ... as for assumptions, read the damn article and tell me which assumption you disagree with. Geeezzzz. It's a peer reviewed paper and the work was funded by the NSF.

Willie ... you can admit that you don't know jack about polls ... it's ok ... it really is ... call me a fucking geek instead ... it's ok.

PS: In the 90's, I worked for Ohio Poll.

 

[Willie99]

Well you can't just totally toss out the poll because it's not convenient. I think RCP & Pollster does a great thing by looking at all of them. I also think this is what you have to....look at all of them together....just don't tout one because you like the numbers best (which 99% of people do on here).

I do agree with Cinci when he says both have their advantages and disadvantages...which is why I say look at them all.

Betit, I didn't just throw it out, I give it less weight.

Stop beating around the bush, what polls to you believe to be the most accurate, LVs or RVs?

Furthermore, if one particular poll of Rvs is way way way off from the other polls, what is your first inclination regarding such poll?

 

[tiznow]

just give up willie

economy toast while dubya still in office

so obama wins

i hate saying this but its true

terrorist attack mccain's only ray of hope at this point

 

[Willie99]

just give up willie

economy toast while dubya still in office

so obama wins

well, that's one big hurdle to overcome, no denying that.

 

[gtc08]

mccain's a democrat anyways so what does it matter.

 

[Willie99]

well, I want the most conservative Democrat then gtc, as opposed to a liberals' liberal.

 

[tiznow]

i say have let them have their liberal, liberal during a very fucked up time economically

and than a TRUE conservative can step in, in 4 years to clean this socialistic commie crooked fascist corportistic big government nonsense up after we have to go through years of pain.....

and return the power to the people where it belongs

obama can't "fix" this problem that much i know....he can make it a bit less painful near term....and drag it out longer with more debt and government spending....but he can't cure it.....

 

[cincy_]

I will try one last time to explain what the paper said about the perils of using LV.

Suppose:

• Obama names Biden his VP candidate
• A hardcore liberal Hillary supporter is PISSED he didn't choose Hillary
• She is very likely to vote in November
• The pollster calls and asks how likely she is to vote
• She says she isn't enthusiastic ... she is now considered "unlikely" to vote by the pollster
• An "unlikely" McCain voter is also called, and he is so stoked by the non-selection of Hillary that he says he'll vote for sure.
• He is actually unlikely to vote on Nov 4th, but on Oct 4th, he thinks he will.
• The polls change ... it looks like Obama lost votes by not selecting Hillary
• The polls have changed because of enthusiasm and not because anyone has changed his/her mind
• The problem is that enthusiasm now won't translate into enthusiasm on Nov 4th. The mood can change over time so a LV on Oct 4th might not vote on Nov 4th (and vice versa).
• That being said, one can assume that enthusiasm a day before the election WILL translate into enthusiasm on Election Day so a LV probably will vote

PS: That scenario was outlined for the people who want to understand the distinction ... since you already know this shit, Willie I hope you don't feel there is a need to comment.

 

[Willie99]

and LVs are more accurate than RVs on election day, the only objective measurement we have.

I don't disagree with much of what you say, I just think it's far more subjective.

people who vote tend to vote, people who tend to not vote don't vote. All the other variables just tweak the starting point some.