Rasmussen and the National House Ballot

by: Chris Bowers

Fri Sep 04, 2009 at 13:27

Currently, the National House Generic Ballot at Pollster.com shows Republicans with a narrow 41.5%-40.7% advantage.  Some may object to this, pointing out that without Rasmussen, Democrats actually hold a sizable 43.2%--38.8% advantage, showing that a single polling firm is heavily influencing the overall figure.  Since a House generic ballot is a reasonably accurate measure of which party leads in the national House popular vote (though, admittedly, is not a very accurate predictor of seat totals), it is worth asking which figure is more accurate.  Which major party is actually ahead right now.

Here are some thoughts on how to solve this problem:

  1. First, removing Rasmussen from the figures altogether does not appear justifiable.  Despite their huge error in 2000, their 2004, 2006 and 2008 polling appeared perfectly sound.  Whatever problems it may have had a decade ago, automated IVR polling has emerged as a methodologically viable alternative to live-interview polls.

  2. Second, in the fall of 2010, significantly more polling firms will be measuring the national generic ballot than currently are doing so.  In 2006, seven polling firms conducted generic ballot tests in the final week of the campaign.  In 2008, eight polling firms published generic ballot tests (seven here, plus Rasmussen).  By way of comparison, in August of 2009, only five polling firms, including Rasmussen, conducted national generic ballot tests.
What I conclude from this is that Rasmussen should be included in the overall figures, but that it is still skewing the results too heavily.  Assuming for a moment that additional polling firms would produce national generic ballot results equal to the simple mean of the four non-Rasmussen polling firms (Dem 42.25%--40.00 Rep%), here is what the national generic ballot would currently look like with more polling firms included in the measurement:

Six polls: Dem 41.1%--40.5% Rep
Seven polls (2006 level): Dem 41.4%--40.4% Rep
Eight polls (2008 level): Dem 41.5%--40.4% Rep
Nine polls: Dem: 41.7%--40.3% Rep

These hypothetical projections all fall into the same range, showing a narrow Democratic advantage.  They also match-up well with the current median of the five firms that have published national generic ballots, the Pew poll showing Democrats ahead 45%-44%.

Given that the mean error on generic ballot simple means since 1998 has been 1.8%,  projecting a 1.0% Democratic advantage instead of a Republican advantage of 0.8% doesn't change much.  This shift is rendered even less significant by the inaccuracy of predicting specific seat totals in the House from the national popular vote.  Within that range, either party could still end up with 230 seats (I hope to have an article explaining why this is the case next week).

Still, I hope that this analysis adds some depth to discussions of the national popular vote.  I doubt it is as simple as either discarding Rasmussen entirely, or thinking that Rasmussen's numbers should be given such significant weight simply because they poll more often.

Chris Bowers :: Rasmussen and the National House Ballot

Tags: , , (All Tags)
Print Friendly View Send As Email

The House is lost (0.00 / 0)
Democrats historically need at least a three point lead in the generic ballot to hold control of the House.  Look at historical generic ballot polling:

2006:  Dems +7, win 233 seats in House
2002:  GOP+6, GOP wins 229 seats in the House
1998:  Dem+4, GOP wins 223 seats in the House
1994:  GOP+8, GOP wins 230 seats in the House
1990:  Dem+8, Dems win 267 seats in the House
1986:  Dems+12, Dems win 258 seats in the House
1982:  Dems+10, Dems win 269 seats in the House
1978:  Dems+10, Dems win 277 seats in the House
1974:  Dems+20, Dems win 291 seats in the House
1970:  Dems+6, Dems win 255 seats in the House
1966:  Dems+6, Dems win 247 seats in the House
1958:  Dems+14, Dems win 283 seats in the House
1954:  Dems+4, Dems win 232 seats in the House
1950:  Dems+2, Dems win 235 seats in the House


If Republicans win are ahead 51%-49% in the generic ballot in late 2010, expect them to win a majority in the House.  

I see (4.00 / 2)
So, fourteen months out, eliminating half of all elections, looking at only one polling firm, and not even coming up with average for the extremely few numbers you kept, you are declaring the House lost.

I appreciate the effort to tie your views to numbers, but you really need to come up with something more substantive. What you have here isn't convincing. At all.

[ Parent ]
For example (4.00 / 1)
To explain more of what I am discussing, here is what you would need to do:

1--Use all House elections, not just midterms
2--Use all polls, not just Gallup
3--Calculate the relationship of the final polls to the national vote totals.
4--Calculate the relationship between the final vote totals and final seat allocation.
5--Produce a range of error with your results, rather than just stating an average as a single determined point.

That would be very interesting, and useful. But even then, it would still only apply to polls 13-14 months from now.

[ Parent ]
You cant use Presidential elections (0.00 / 0)
Because the turnout model is completely different.  You are also dealing with Presidential coattails that distort the generic ballot in Presidential years.  Look at this:


In 1980, Democrats had a big 15 point lead in the generic ballot, but that lead was pulled downward by the Reagan landslide and Democrats barely won the House popular vote and lost 35 seats.  

That is why I am excluding Presidential years in my analysis.  

[ Parent ]
Turnout doesn't matter (0.00 / 0)
Turnout doesn't matter. Polling is polling. The size of the electorate doesn't change the margin of error in the polls.

[ Parent ]
If the election were held today.... (4.00 / 1)
...then, yes, probably...  but, it's not being held today, and it's no surprise that dems are doing poorly.  They look totally incompetent at the moment.

That may continue, it may not, but it's way too soon to tell.

REID: Voting against us was never part of our arrangement!
SPECTER: I am altering the deal! Pray I don't alter it any further!
REID: This deal keeps getting worse all the time!

[ Parent ]
Also.... (0.00 / 0)
Since you are focusing on gallup, we still have a 5 point lead over there...  so, your analysis is way off...

REID: Voting against us was never part of our arrangement!
SPECTER: I am altering the deal! Pray I don't alter it any further!
REID: This deal keeps getting worse all the time!

[ Parent ]
Things change (4.00 / 2)
Partisan hardening + more effective gerrymandering makes reaching into the mists of history problematic for reading current circumstances.

Major swings in total numbers remain possible (see: 2006, 2008), but ancient history is increasingly a less reliable guide to current circumstances.

Not to mention that if the economy improves substantially between now and next summer, or is perceived as improving, then the Dems will retain control.

My biggest complaint about strategy is that the Dem leadership continues to play footsy with the GOPers when they should be doing everything in their power to ensure that they pay a price for their positions.  By this I mean slamming them for insisting that poor Grandma's health be left to the decision making of the death panels of unscrupulous corporations who control the opposition.  That, and making sure that people understand that the weaknesses in the bill that will be passed are there because of the GOPers.

Call me partisan, but I think you attack, attack, attack the GOPers at every turn, all with a smile on your face.  We need more charges of "Party of No" and less wishcasting about bipartisanship.

Did they get you to trade your heroes for ghosts? Hot ashes for trees? Hot air for a cool breeze? And cold comfort for change?

[ Parent ]
The final margins (4.00 / 1)
are not usually 51%-49% because of the number of minor parties...also the number of candidates matter too, if more Republicans are running unopposed, they tend to do better.

The generic ballot was close in late summer/fall/winter 2007 too. I remmeber panic then. Anyone remember how Niki Tsongas almost lost MA-05?

One of the biggest reasons why we see the generic ballot the way it is now is the same reason it was close in late 2007...because a lot of people are in wait and see mode. It only becomes important in about nine months.

The meatiest part of legislating comes between now and next May. Lets see what gets done.  

[ Parent ]
While I think its smart to be worried.. (4.00 / 1)
I also think the poll numbers will improve in September. (This is anecdotal but Obama's base tends to be MIA in August.)

And if he pulls off health insurance reform........

Partisan when they can be (4.00 / 3)
My sense is Rasmussen is a GOP tool except just before elections, when reality provides a check and his numbers must conform to maintain his credibility.  

Self-refuting Christine O'Donnell is proof monkeys are still evolving into humans


Open Left Campaigns



Advanced Search

Powered by: SoapBlox