Custom Search

Thursday, September 27, 2012

Pollster That Oversamples Dems Admits Same Democratic Skew In November Election 'Probably Unlikely'

By Susan Duclos

Liberals are waving away Conservatives reaction to polling data that has come out recently where Democrats in the poll heavily outweigh Republicans and pollsters are defending that practice, yet when cornered into answering a direct question of whether it is believed that the turnout in November's presidential election will match the heavily oversampled Democrats in the polling, Peter Brown, assistant director of the Quinnipiac polling, admits it is "probably unlikely."

Via NewsBusters:

Interviewed last month by conservative talk show host Hugh Hewitt, Peter Brown, assistant director of the Quinnipiac polling operation was particularly squeamish about sampling under tough questioning from Hewitt about a poll which Quinnipiac had released showing Democrats with a 9 percentage point advantage in the state of Florida.

In the conversation, Brown defended Quinnipiac’s sampling techniques but admitted that he did not believe that Democrats would outnumber Republicans to that degree in Florida come November. Pressed by Hewitt, the pollster said he believed that was a “probably unlikely” scenario. Instead, Brown kept saying that he thought his poll was an accurate snapshot of reality at the time.
Remember, this is the same pollster that trumpeted the latest headline blaring that Obama has opened up a lead in Ohio, Florida and Pennsylvania, using a model that oversampled Democrats and admitting that it is probably unlikely the real turnout will reflect those samples.

It does beg the question that if these pollsters do not believe the actual turnout will reflect the oversampling of Democrats that their polls are using for their polling data, then why not weigh that accurately with the other demographics instead of waiting to do so until the last couple of weeks before the election date?

Via Da Tech Guy's Blog:

So with a sample that is D+9 in Florida, Barack Obama has a +9 lead on Mitt Romney! In Ohio with a D+9 Sample Obama has a +10 Lead and in Pennsylvania with a D+11 sample he has +12 lead.

 The Rasmussen numbers show that Romney and Obama both tally in at 46 percent each. With leaners they are tied at 48 percent each. In Rasmussen's swing state tracking poll both candidates are also tied at 46 percent.

It is worth noting that In December 2009, a full 11 months before the 2010 midterms, a Democratic strategist concluded that if the Rasmussen Reports Generic Congressional Ballot data was accurate, Republicans would gain 62 seats in the House during the 2010 elections. Other polls at the time suggested the Democrats would retain a comfortable majority. The Republicans gained 63 seats in the 2010 elections.

That is not to say that Rasmussen has not been wrong on individual races at times, but overall, their modeling and their attention to voter ID, often puts them ahead of the curve. Democratic pollsters do not agree with that analysis.

The reason I highlight the Democratic strategist 2009 article is because of something noted at the end of the article:

If Rasmussen is starting off with a disproportionately Republican sample of adult citizens, then their likely voter sample is almost certain to also include a disproportionate share of Republican identifiers.

Rasmussen accurately called the turnover of the House of Representative to Republican control, but his final projections actually understated how well Republicans would do compared to the final results.

The point is, the Democratic argument back in 2009, that an unrealistically high sample of one particular party, will skew the results,  is the argument that Democrats and Liberals are now waving away, that these pollsters now that are using a Democrat heavy D+9 and D+11 samples are skewing the results.

I am not assigning nefarious intent to the pollsters skewing the polls, but instead think they are relying heavily on the turnout in 2008 without regard to how the political landscape showed such massive changes in 2010 where party turnout was even and Republicans took the largest turnover of seats from Democrats in 70 years.


All told, we see a statistically significant relationship between Obama's margin and the Democratic advantage in partisan identification. In other words, there appears to be a bimodal distribution of the polls. They are not converging around a single point. Instead, some (notably Rasmussen, Purple Strategies, Survey USA, and Mason-Dixon) see Obama ahead by just 1 to 3 points in the key swing states, while others (notably the Washington Post, Fox News, PPP, and NBC News/Marist) see an Obama lead that ranges between 4 and 8 points. And the difference looks to be built around how many Democrats are included in the polling samples. 

If it comes down to whether or not this will be a repeat of 2008 -- which is basically what the latter camp of pollsters is suggesting -- then my money is on no. Of course, it is possible that I am wrong. I have no crystal ball looking forward. All I can do is look back through history, where I see on average a nationwide Democratic identification edge of about 3 points, which is also roughly the midpoint between 2004 and 2008. That is my guess about 2012. It is an informed guess, but it is still a guess. If I’m right, then Rasmussen, Purple Poll, Mason-Dixon, and Survey USA are closer to the mark. But I could be wrong, in which case Fox, PPP and Washington Post are closer to the mark.

One more thing, I see many saying the media outlet polls are oversampling Democrats to depress Republican voters, but the flaw in that line of thinking from what I am seeing my social media is that the oversampling is revving up Conservatives to trot their butts to the polls and cast their votes in November while Democrats are being told "it's in the bag," which encourages the thought that every vote isn't needed.

Reminder: The Presidential Debates begin on October 3, 2012, schedule here.

(Changes have been made t this post)