Un-Skewing the Polls

| September 24 2012
Christopher Cook

I have been contending for quite some time now that the polls are wrong. A combination of the how indies are breaking (and how undecideds will break), inescapable economic realities, and the enthusiasm gap all point to a Romney win. Chances are very good that in spite of the close polls, Romney is ahead in most states.

A website called UnSkewedPolls.com takes this same view. The polls are dramatically oversampling Democrats and over-estimating Democrat turnout, and they are not re-weigting their results accordingly. UnSkewedPolls.com’s methodology is simple: They use registration numbers as their baseline:

The purpose of unskewing the polls is to arrive at accurate numbers, not to show one candidate or the other ahead in the presidential race. The analysis process in unskewing polls relies on the Rasmussen Reportspartisan data measured from hundreds of thousands of voters by Rasmussen Reports, which measures the partisan percentages at 37.6 percent Republicans, 33.3 percent Democrats and 29.2 percent independents.

Here is the current set of UnSkewed polls, using the new weighting:

UnSkewed Polling Data
Monday, September 24, 2012 10:19:37 AM
Poll Date Sample MoE Obama(D) Romney(R) Spread
UnSkewed Avg. 9/4 – 9/20 44.0 51.8 Romney +7.8
Reason/Rupe 9/13 – 9/17 787 LV 4.3 45.0 52.0 Romney +7
Reuters/Ipsos 9/12 – 9/20 1437 LV 2.9 44.0 54.0 Romney +10
NBC News/WSJ 9/12 – 9/16 736 LV 3.6 44.0 51.0 Romney +7
Monmouth Univ. 9/13 – 9/16 1344 LV 2.5 45.0 50.0 Romney +5
QStarNews 9/10 – 9/15 2075 3.0 44.0 55.0 Romney +11
NY Times/CBS News 9/8 – 9/12 1162 LV 3.0 44.0 51.0 Romney +7
Democracy Corps 9/8 – 9/12 1000 LV 3.1 43.0 52.0 Romney +8
Fox News 9/9 – 9/11 1056 LV 3.0 45.0 48.0 Romney +3
Wash. Post/ABC News 9/7 – 9/9 826 LV 4.0 45.0 52.0 Romney +7
CNN/ORC 9/7 – 9/9 875 RV 3.5 45.0 53.0 Romney +8
IBD/CSM/TIPP 9/4 – 9/9 808 RV 3.5 41.0 50.0 Romney +9
ARG 9/4 – 9/6 1200 LV 3.0 43.0 53.0 Romney +10

Obviously this can only work well for national polls, because the weighting is going to differ in various states. However, if the national polls are off by some amount, this will translate to state polls as well.

Dean Chambers of UnSkewed suggests that the poor weighting is happening for several agenda-based reasons:

The mainstream media has no intentions of sitting on the sidelines and merely objectively reporting the news of the election contest while watching Barack Obama become another Jimmy Carter. They will create the perception, via skewed polls, that Obama is winning and then hope the campaign can take advantage of this perception and steal enough votes to actually win the election. Then the perception, and the polls, will validate the stolen election and make it look all so plausible and realistic. If you don’t believe they are doing this, then ask yourself how a president who is doing worse economically than Jimmy Carter was can somehow be reelected?

[ . . . ]

The other factor less covered in the analysis and commentary on these issues is how the mainstream media are manipulating the polls to help the president get re-elected. Just recently, the Washington Post/ABC poll was shown to be heavily skewed toward Obama as well as some polls that were released last week. These polls are not skewed simply to make Obama look like he’s winning when he’s not. The reason is far more sinister than that. The polls are skewed with the belief that doing so actually influences voter decisions, and that many voters want to be voting for who they believe will win the election, and therefore if they have little other reason for their choice and want to be sure to be voting for the winning candidate, they will vote for Obama if they believe he’s going to win. This concept is called the “bandwagon effect” that voters will choose the candidate they believe will win.

The bandwagon effect is a real thing. People want to vote for the winner. But that doesn’t just mean that people who vote end up voting for the winner, it also means that people who don’t think their guy will win simply stay home. The media is hoping for, and working to create, this effect in earnest.

Chambers does have a prescription, one that I share most ardently:

The more that voters are aware that these major mainstream polls are skewed toward Obama, and see Romney competing well in the very few legitimate polls if they know that those polls are legitimate, the less ability the mainstream media has to sway public opinion, if they have much at all, with the skewed polls.

If the media can’t successfully create a illusion that Obama is winning in the polls, it will be that tougher for the campaign to engage in enough vote-scamming to win. And the more we do at the state level to insure the integrity of the voting system from voter fraud, such an enacting and implementing voter identification laws, the less they will be able to engage in vote fraud. More voters should realize this is precisely why Obama’s Justice Department under Attorney General Eric Holder is fighting voter identification laws so strongly. They know they are far less likely to win the if the election if honest and fair.

If we do not let them get away with the lies they are telling about Romney to try to undermine his support, the less likely they are able to get close enough in the polls for the other efforts to be able to succeed. The more the public sees through the viciously negative advertisements being being run by the Obama campaign and the unofficial groups that support him, the more they will realize just how dishonest this president is and how much he seeks to avoid being accountable for his own failure to perform as president.

It all comes down to exposing what they’re doing. Exposing the lies in their ads, exposing the skewed mainstream media polls exposing the strategy behind all of this only renders it ineffective if voters understand what is being attempted. A well-informed voter is the very individual on election day the Obama campaign has the most to worry about.

It is probably the case the UnSkewed polls is overestimating Romney’s strength by some amount. Chances are, turnout nationwide will be somewhere between 2008 and 2010 levels, (D+7 to D+0). But UnSkewed is also probably closer to the truth than many of the other mainstream polls being run right now.

The only way Obama wins this is if the media and dishonest pollsters manage to depress Republican turnout. Do not let that happen. Spread the word.

0 comments
Sort: Newest | Oldest