Posted on 09/14/2012 9:03:41 PM PDT by Leto
Polls have caused a lot of consternation among my friends here. Some say to ignore polls, but this election season I have found them to be very consistent even thought the results vary quite a bit.
The key is understanding the turnout model the poll is using. In 2008 the turnout was +7.6% dem, in 2010 it was +1.3% R. In the last Rasmussen survey 8/2012 the party affiliation is +4.3% R.
Most polls are using turnout models that vary from +6 to +10% D. This is why Obama is leading in most polls.
The latest NYT/CBS poll has Obama +3 among likely voters 49-46%. Their turnout model is +6% D close to the 2008 turnout model. 35D/39R/32I for their likely voters in this poll.
I have a spreadsheet I use to see the results if the 2010 turnout model is used or any other model.
Below is the CBS NYT poll 'normalized' to reflect both the 2010 turnout model and the current Rasmussen party id.
<!-- BODY,DIV,TABLE,THEAD,TBODY,TFOOT,TR,TH,TD,P { font-family:"Arial"; font-size:x-small } -->
| Poll Normalizer | ||||||
| Media Poll results | Democrats | Republicans | Independents | |||
| Romney | 5.0% | 90.0% | 51.0% | |||
| Obama | 92.0% | 7.0% | 40.0% | |||
| Other | 2.0% | .0% | 2.0% | |||
| Undecided | 2.0% | 3.0% | 6.0% | |||
| Poll Sample | Democrats | Republicans | Independents | |||
| Corrected turnout model | 34.7% | 36.0% | 29.3% | |||
| Corrected Results | Inc Undecideds 3/2 challenger | |||||
| Romney | 48.6% | 51.21% | ||||
| Obama | 46.7% | 47.54% | ||||
| Other | 1.3% | |||||
| Undecided | 3.6% |
So using the 2919 turnout model Romney instead of being behind 3% is up by 2%, if the undecideds break 3/1 for the challenger Romney is up almost 4% and 'wins' 51.2 to 47.5.
Let's look at the result if the current party affiliation is applied to the CBS/NYT numbers
<!-- BODY,DIV,TABLE,THEAD,TBODY,TFOOT,TR,TH,TD,P { font-family:"Arial"; font-size:x-small } -->
| Poll Normalizer | ||||||
| Media Poll results | Democrats | Republicans | Independents | |||
|
|
|
|
|
|
|
|
| Romney | 5.0% | 90.0% | 51.0% | |||
| Obama | 92.0% | 7.0% | 40.0% | |||
| Other | 2.0% | .0% | 2.0% | |||
| Undecided | 2.0% | 3.0% | 6.0% | |||
|
|
|
|
|
|
|
|
| Poll Sample | Democrats | Republicans | Independents | |||
| Corrected turnout model | 33.30% | 37.60% | 29.20% | |||
|
|
Corrected Results | W Undecideds 3/1 to challenger | ||||
|
|
|
|
|
|
|
|
| Romney | 50.4% | 53.1% | ||||
| Obama | 44.9% | 45.8% | ||||
| Other | 1.3% | |||||
|
|
|
|
|
|
|
|
| Undecided | 3.5% |
We see in this case Romney is up by 5.5% not including undecided voters and 7.3% if undecided voters break 3/1 for the challenger.
This result is very close to the projection of the Univ of Colorado economic prediction from a few weeks ago, which has been correct since 1980.
Using this spreadsheet with a variety of polls from the CNN to ARG to Reuters the results have been very similar, WHEN THE SAME TURNOUT MODEL IS APPLIED TO THE RESULTS.
That is almost all these polls, have the candidate winning their party supporters by ~90 to 5%, the independents are going anywhere from +10-+15% for Romney over Obama.
The media gets the narrative they desire by using the turnout model that fits their narrative.
Having trouble with the preview hope the formatting turns out OK
Excellent work. Thanks for taking the time.
Woah! Thanks for creating this model. Should let a few Freepers sleep easier tonight.
This is close to my prediction. Romney 55% Obama 45%
Thanks for your work!
That was got it and going up by 3 points Tuesday
I believein line 6 above you MEANT 35D, 29R, 36I. No?
But the MSM pollsters say the 2010 results shouldn’t matter cause it’s going to be 2008 again, and if you don’t believe them they are just gonna put their fingers are in their ears and sing “la la la I can’t hear you”./
By the way, nice work. My prediction still stands at 53%-45% Romney.
Come on, Freepers! We have to get the word out about this! Too many on our side are seeing these BS polls and believing them and getting depressed enough to stay home on election day! This is what the lame-stream wants!
ALWAYS look at the poll internals to see the party identification break-down. As soon as you see Dims being over-sampled, get on to as many sites as possible to leave comments exposing this!
REMEMBER WISCONSIN?? On election day the exit polling (which over-sampled Dims) predicted the race was too close to call. Actual result: Walker won 53-47.
DON’T FALL FOR THE LAME STREAM SNAKE OIL!!
You are correct, it should be 39d/29r/36i
My bad.
This is going on Facebook
Thank you for taking the time to break this down.
Actually according to the NBC/Marxist poll 2012 is going to be BETTER then 2008 for Obama.
And even people here buy their nonsense!
Your effort is greatly appreciated.
Thnx for doing this
We don’t even need to see the internals really, just how the d/r/I voted for each candidate.
Pay special attention the indies, since the rat and pub bases are voting for their candidate by about the same amount.
I was especially taken aback by the Carville/Greenberg poll that had Romney +15 among the indies.
The message is not to buy into the media narrative,understand the game they are playing. IMO this election will not be anything like 2008 in terms of the turnout model.
Very nice work. Thanks again. Suggest you write article to WSJ on this.
The Dem/MSM internal polls are probably showing similar, and that is why they are throwing everything they can against the wall to see what sticks.
I have said in other posts that this election is going to either be a 1980 style landslide for Romney; or, if the Dem/Lib/MSM polls are accurate, be so close that a few dozen votes in a dozen states will determine the election.
With the state of the economy, joblessness, some inflation, and now the foreign affairs problems, I just don’t see how Obama is really maintaining or being ahead of Romney.
QUESTION:
Has mid-term turnout been used by these pollsters to predict previous presidential elections? Did these pollsters use the 2004 Presidential or the 2006 Mid-Term elections to poll the 2008 elections?
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.