Skip to comments.Has Rasmussen Changes His Polling Samples?
Posted on 10/13/2012 11:45:35 AM PDT by deltanine
I've seen mentioned in other venues that over the last few National surveys Rasmussen has changed his polling sample to R+3.
Anyone have access to the internals to verify this?
I am a platinum member so I see his samples.
He uses a D+3 (D 39 R 36 I 31) sample.
Thank you! I figured I was being exposed to Obama propaganda.
No place like Free Republic to get the truth.
Rasmussen used to set his party weighting based on his monthly polling of party affiliation. For some unknown reason, he stopped doing this and has arbitrarily weighted it as Dem +3.
Personally, I think that Ras was looking over his shoulder and saw that his numbers would be big outliers compared to the other polls if he went GOP +2... and got scared and went with Dem +3.
“Personally, I think that Ras was looking over his shoulder and saw that his numbers would be big outliers compared to the other polls if he went GOP +2... and got scared and went with Dem +3.”
You may be right there, Arthurio. It has to be unnerving to try to conduct honest polling and see your results so far off from everyone else. Even if you know you are reporting accurate numbers, at some point you would wonder if maybe the pack is right and you might be doing something wrong.
Well, lots of questions will be answered on election day. But, this campaign season has seen so many polls which seem to be doctored, to make it seem that Obama is more popular than he really is. Nov. 6th will reveal the truth.
Rasmussen seems to me to be hedging a little conservative (in terms of numbers, not politics) during the Romney surge. It's unlike the usual landscape to have many other polls moving in favor of the Republicans as much or more than Rasmussen. It's unusual for my own assessment to be 3 points greater than Rasmussen's.
I registered as a rat to vote against Hillary (my bad) since in the state where I vote there is virtually no way anyone but a rat will win and McCain already had the nomination.
And then there are the multitudes of rats who can no longer stomach zero....
Almost daring to feel optimistic about this election!
Yep. It makes no sense to poll for party id, and then throw them out the door when doing your poll. It’s a waste of money.
The only reason he’s doing it is to appease the Chicago thugs. Right now he has the party id at R+2.6. If he polled every day using that sample, Romney would be up about 5 points.
In 2004 Rasmussen had the party id (at this time) at D+1 and Bush won by 3.
In 2010 Rasmussen had the party id at D+2 and it was a GOP landlside.
At R+2.6 (plus the enthusiasm edge) we are looking at the biggest wipeout in history.
Unskewed Polls best place to look. It is +3 D. Make sure younlook there after next debate to see if the skewer changes on most polls. When Obama was leading by a lot the skewer was +7 to +13 (one +17). After we started pointing out that to justify their skewer the DemoRat turnout would have to either equal or exceed the 2008 turnout the skewer drooped to around +3 and now Romney is tied or slightly leading
Here’s the direct link to the Rasmussen archive with month-to-month party affiliation from 2004 to present.
Right. Some confuse the party affiliation poll with the sample he uses.
The party id is to gauge the number of Repubs/Dems/Other in the country. To get the trend and snapshot.
Rasmussen used to then apply these statistics to his daily polling.
He no longer does. For some reason he uses an arbitrary D+3 sample. I guess he is predicting the electorate will be a mix between 2008 (D+7) and 2004 (E).
We crawled over broken glass in 2010 without Obama on the ballot - just to send a message. Yet with Obama actually on the ballot - and to send him more than a message, but his actual walking papers - we aren’t as excited? I doubt that.
This will be a landslide defeat for Obama.
Seriously ~ all this stuff is garbage now. You really can't take polls with phone calls anymore.
We won in a blowout because nearly 40% of the Democrats didn't bother voting.
I guess I'm one of those.
When did he change, and has he said why he did?
I bet Rasmussen will start adjusting again when election is nearer. Being an outlier hurts with liberal media PR now (risking the koook factor), but his real goal is to match the real thing in Nov and become #1 in the field for 4 more years.
+3 Dem is the best possible outcome for the left. I’ll eat my cat if it ends up higher than that.
Mid terms and presidential. Comparing apples and oranges.
My point is the party id stat which still applies.
If people actually want to play the polling game they should probably stick to current polls against last previous election actuals.
There are a lot of possible explanations. As an American who despises Obama's far left fringe, I have no objection to Scott Rasmussen's decision regardless of his reasons. What Rasmussen is doing is close to the best possible option in terms of its effect on perceived momentum and on actual voting decisions.
It's my contention that bias is not the only reason polls lie - there are ordinary business reasons as well.
Ras has recently said he thinks the actual turnout will be D+2-4%. That explains his switch to a D+3 sample.
I still think his party affiliation makes more sense, so his reasoning confounded me.
Like you, I think we're about to witness a blowout of epic proportions. In that scenario the only way to explain a D+3 turnout is to realize that alot of Dems will vote for Romney.
It's the premise of this thread.
Sly one, that Rasmussen. :)
Rasmussen has to consider his own business, as well. He’s been producing the most Republican numbers of national polls. Most other polls are using D+6 or greater. So, with a D+3, Rasmussen will be closest as long as turnout is more Republican than D+4.5... which would be the second biggest D wave since Reagan.
Second, we have yet to hold an election where Ras showed more Rs than Ds the month before the election. November 2010 was the very first time Ras ever showed Rs outnumbering Ds. So, he doesn’t really have any data to guide him on what will happen on Election Day under that situation. He DOES know, though, that since Reagan got elected, turnout has been between even and D+4 every single election except 2008, with an average of D+2.5. That gives him a nice, safe model that is easy to defend. I don’t blame Ras one bit for that.
I think Ras is playing it smart. No fault can be found with that. He’ll still end up closer than anyone else, IMO.
That's a far more powerful source of victory than planning on a bunch of Democrats coming down the street to pull the levers repeatedly for a Republican (which is pretty much like imagining that you could have an undecided 5 to 10% independent vote somewhere in the middle in a voting public that has no middle).
The Reagan Democrats, Nixon Democrats, McCain Democrats, Bush Democrats, and Obama Republicans would probably see it differently.
Of the above, the Reagan Democrats were quite a factor in 1980 and 1984. Reagan actually expanded on the Nixon model (Nixon Democrats-also known as the Silent Majority).
I wouldn't be the least bit surprised to be reading articles next year about the influence of the Romney Democrats on the 2012 election.
The process of bringing Conservative Catholics into the Republican movement is taking just about as long and so far we only have the observant ones.
Which is to say the Reagan Democrats were already motivated to vote Republican and had done so before, and with the full acquisition of the black vote, began to do so on the state and local levels.
For the most part the two great coalition political parties in this country GROW by adding or attracting factions ~ individual conversions are of a lesser consequence.
The lesson is this ~ don't count your chickens twice ~ once as eggs and once as parts in the fry pan. You get your voters from your base, and the base is huge ~ certainly far more than the 63+ million 'W' was able to draw, or the 69 million 'obamugabe' found ~ in either party.
It is a mistake to abandon 40% of your Republican base of Socons to attract a couple of guys who write for Time magazine.
Historically, at least since 1952, the most successful candidate campaigns electorally not only held virtually their entire base, but attracted large numbers of voters from the opposite party.
Eisenhower, Johnson, Nixon(72),Reagan, and Bush(88) all put up popular and electoral vote totals that swamped the other guy. None of them abandoned their base to achieve those landslides.
The big work on growing the base involves securing the support of entire factions ~ not just individuals on the other side.
The three biggest modern transfers of factions involved black voters (North and South, and augmented through passage of special voting rights legislation and enforcement), Southern white voters, and Roman Catholic voters.
Today a full 40% of the effective voting strength of the Democrat party in states where they are dominant is made up of black voters. They control ~ but do not dominate the Democrat parties in those states, and in the cities where they exercise control they dominate politics with an incredible totality.
40% of the Republican base consists of Social Conservatives ~ and a great deal of that base arises out of social groups who did not regularly vote in the past, or simply didn't vote in elections in areas where traditional Republican Conservatives dominated politics. This is a 'new growth' situation, not like the 'voter transfer' situation encountered with black voters.
The old Republican merchant and professional class voters have been popularized as the new TEAParty ~ and they're about 40% of the Republican vote. The remaining 20% is divided up among a residual group in New England ~ true 'Bitter Enders' ~ and the GOP-e which is representative of disembodied financial interests and their hired professional politicians.
In all of my analyses of the situation ~ going back to the 1850s, I usually set aside Eisenhower and Grant as special cases. Neither one really needed to campaign. Both were considered representative of the victors in truly great wars ~ Civil War for Grant and WWII for IKE, and he had also been SUPREME ALLIED COMMANDER!
Even Truman wanted IKE to run for President as a Democrat.
It stands to reason that any successful candidate must secure and maximize his base and then motivate them to vote. It's easy to agree on that, it almost goes without saying.
My previous replies were to your original assertion that "usually you never get any votes from the other side". The opposite is the case with most winning candidates, and particularly those who have won by huge margins. It's just a matter of to what degree.
It would be logical to expect to never win any votes from the ideological core of the opposing party. That we can agree on.