Note to Romney

[AK Forty Seven]

Quote from jem:

I just showed you why a poll going D plus 9 is outrageously irresponsible.

you will be the one manning up. (unless there is a war.)

Jem,if the results from a poll says +9 dems thats what it is


Its irresponsible to rigg a poll to take out dems and add Rs if those weren't the actual results



This is what happens when you do that

http://fivethirtyeight.blogs.nytime...rate-quinnipiac-surveyusa-performed-strongly/



Rasmussen Polls Were Biased and Inaccurate




Every election cycle has its winners and losers: not just the among the candidates, but also the pollsters.

On Tuesday, polls conducted by the firm Rasmussen Reports — which released more than 100 surveys in the final three weeks of the campaign, including some commissioned under a subsidiary on behalf of Fox News — badly missed the margin in many states, and also exhibited a considerable bias toward Republican candidates.


The 105 polls released in Senate and gubernatorial races by Rasmussen Reports and its subsidiary, Pulse Opinion Research, missed the final margin between the candidates by 5.8 points, a considerably higher figure than that achieved by most other pollsters. Some 13 of its polls missed by 10 or more points, including one in the Hawaii Senate race that missed the final margin between the candidates by 40 points, the largest error ever recorded in a general election in FiveThirtyEight’s database, which includes all polls conducted since 1998.

 

[jem]

I get it... you do not understand what I am saying. The pollsters very much do rig the poll results they produce.

they conduct the poll.... then they filter it on registered voters, somtimes they filter it on likely voters... .. then they slant it to the mix they want, then they tell you Obama is in the lead..





When I say D plus 9... I am saying they included the choice of 45 democrats vs 36 republicans.

so that poll produces results very slanted to obama.

would you think much of a poll which sampled 45 Republicans vs 36 Dems?

Quote from AK Forty Seven:

Jem,if the results from a poll says +9 dems thats what it is


Its irresponsible to rigg a poll to take out dems and add Rs if those weren't the actual results



This is what happens when you do that

http://fivethirtyeight.blogs.nytime...rate-quinnipiac-surveyusa-performed-strongly/



Rasmussen Polls Were Biased and Inaccurate




Every election cycle has its winners and losers: not just the among the candidates, but also the pollsters.

On Tuesday, polls conducted by the firm Rasmussen Reports — which released more than 100 surveys in the final three weeks of the campaign, including some commissioned under a subsidiary on behalf of Fox News — badly missed the margin in many states, and also exhibited a considerable bias toward Republican candidates.


The 105 polls released in Senate and gubernatorial races by Rasmussen Reports and its subsidiary, Pulse Opinion Research, missed the final margin between the candidates by 5.8 points, a considerably higher figure than that achieved by most other pollsters. Some 13 of its polls missed by 10 or more points, including one in the Hawaii Senate race that missed the final margin between the candidates by 40 points, the largest error ever recorded in a general election in FiveThirtyEight’s database, which includes all polls conducted since 1998.

 

[AK Forty Seven]

Quote from jem:



would you think much of a poll which sampled 45 Republicans vs 36 Dems?

If they called 81 people and those were the results then its a good poll

 

[jem]

Quote from AK Forty Seven:

If they called 81 people and those were the results then its a good poll

that is not what they do...

almost all of them filter then cook to desired mixture.

 

[AK Forty Seven]

Quote from jem:

that is not what they do...

almost all of them filter then cook to desired mixture.

They all do not weight their surveys based on preordained assumptions about the party identification of voters in each state like Rasmuessen does

 

[mrbill]

Quote from jem:

I just showed you why a poll going D plus 9 is outrageously irresponsible.

you will be the one manning up. (unless there is a war.)

Ok, let me recap: Margin of error, Dem's over sampled, bumper stickers, whatever that econometrics crap was, and now we have to add Unless there's a war? OK, anything else? Perhaps the Mayan calendar? Come on Jem, to stand by your man is one thing, to just completely disregard facts is something else.

But, I still respect you, and do think it's closer than the polls show.

 

[jem]

Quote from AK Forty Seven:

They all do not weight their surveys based on preordained assumptions about the party identification of voters in each state like Rasmuessen does

You do not know what you are talking about.
By my memory you have only produced 1 random poll in the last 60 days...

all the other are filtered on Registered voters, likely voters.
The close polls which come out within the margins have may not have been subject to alteration beyond that (like the GWU poll) .... however, most all the other ones have been skewed.

go look for yourself when the polls give the totals.


but to make it clear.

the other day you or someone cited a poll which said nascar people favor Obama.

and the sample was d plus 4 democrats.

I went and found pretty much the only recent study of Nascar fans... it was done in 2011... and in that study of nascar fans... they found there were more republicans than dems.

therefore the recent nascar study is sure to be cooked.

--

now when you go into Florida and come out with a sample of D plus 9 and I just showed you that the electorate is far closer to balanced... you know your poll cooked the results.


Further, when the polls give you the details... they show your the raw numbers, then the registered voters, then the likely voters, then they skew the result how they wish...

otherwise... they would tell you it was a random poll.

 

[Navin Johnson]

Quote from jem:

that is not what they do...

almost all of them filter then cook to desired mixture.

+1

I think polls that survey "all adults" are the exception. That is why they are rarely conducted, and are almost always worthless information.