• This is a political forum that is non-biased/non-partisan and treats every person's position on topics equally. This debate forum is not aligned to any political party. In today's politics, many ideas are split between and even within all the political parties. Often we find ourselves agreeing on one platform but some topics break our mold. We are here to discuss them in a civil political debate. If this is your first visit to our political forums, be sure to check out the RULES. Registering for debate politics is necessary before posting. Register today to participate - it's free!
  • Welcome to our archives. No new posts are allowed here.

Unskewed Polling [W:536]

Also thank you Winston. Everyone pays FICA now. Was that the same during Reagan?
 
Also thank you Winston. Everyone pays FICA now. Was that the same during Reagan?

We should call for a tax revolution! Because people are sick and tired of paying taxes. So don't work!
 
Just keep ignoring the fact that you were wrong about Reagan Conservative. You live in a fantasy world.
 
Just keep ignoring the fact that you were wrong about Reagan Conservative. You live in a fantasy world.

Try to understand that no matter how many times you try to divert from the Obama record, it will be that record on the ballot in November. Why don't you just admit that you support the direction Obama is taking this country which is a large central govt. economy where everything is controlled in Washington D.C. Apparently states have no responsibility in your world.
 
Nate Silver smashes the GOP's hilarious "skewed polls" fantasy here:

Poll Averages Have No History of Consistent Partisan Bias - NYTimes.com

That is a final poll issue. There are approximately 4 to 5 polls that are essentially liberal push polls and those are CBS/NYT, ABC, NBC, Ipsos and Marist.

Quinnipiac is pretty decent, Gallup as well. Rasmussen is accused of being left leaning but his model is just different from everyone elses and uses likely voters rather than plain voters.

Anytime you sample higher by 5% then current party ID or current year registration numbers, you arent polling, youre pushing.
 
That is a final poll issue. There are approximately 4 to 5 polls that are essentially liberal push polls and those are CBS/NYT, ABC, NBC, Ipsos and Marist.

Quinnipiac is pretty decent, Gallup as well. Rasmussen is accused of being left leaning but his model is just different from everyone elses and uses likely voters rather than plain voters.

Anytime you sample higher by 5% then current party ID or current year registration numbers, you arent polling, youre pushing.

So you didn't read or the article, or you just didn't get it?
 
So you didn't read or the article, or you just didn't get it?

I get it. You didnt. The difference in final polling and during the race is there, but you have to look for it. Nate Silver did not. As the election moves closer, polling always moves closer to the final result. But, in between now and say 3 weeks including the last 6 months, you will see a lot of push polling.

Ill ask you, why vary from a model that shows epected turnout (registration data and party ID numbers) to sample at as high as +11 Dem if you are trying to get an honest poll?
 
I get it. You didnt. The difference in final polling and during the race is there, but you have to look for it. Nate Silver did not. As the election moves closer, polling always moves closer to the final result. But, in between now and say 3 weeks including the last 6 months, you will see a lot of push polling.

Ill ask you, why vary from a model that shows epected turnout (registration data and party ID numbers) to sample at as high as +11 Dem if you are trying to get an honest poll?

No, you didn't get it. The way people self identify is tied in the the results of the poll. It's not something that you can or should correct for, because you would be skewing the results if you did.

Silver has previously looked at the results of polls taken 45 days out, and those polls successfully called the winner of presidential elections 17 out of 19 times.
 
No, you didn't get it. The way people self identify is tied in the the results of the poll. It's not something that you can or should correct for, because you would be skewing the results if you did.

Silver has previously looked at the results of polls taken 45 days out, and those polls successfully called the winner of presidential elections 17 out of 19 times.

Current results and voting registrations dont indicate party ID being tied. You can and should correct for party ID as it is occurring otherwise you dont have polling you have historical data which is not an indicator of future results.
 
Mason-Dixon used to pretty good at establishing baselines though they oversampled conservatives a bit. Are they no longer polling?
 
Back
Top Bottom