Some Likely Voter Models are Suspect

[WeDidIt]

So Nate has something to say about these "Likely Voter" models.

Some Likely Voter Models are Suspect
There are eight current national polls that list separate sets of results for likely and registered voters. (In this case, for reasons that will be apparent momentarily, I am deliberately double-counting the two Gallup likely voter models). On average, Barack Obama leads by 9.8 points in the registered voter versions of these polls, but by 7.0 points in the likely voter versions -- nearly a 3-point difference:

<snip>

Note, however, that the likely voter models appear to segregate themselves into two clusters. In one cluster, there is a rather large, 4-6 point difference between registered and likely voter results. In the other cluster, there is essentially no difference.

The first cluster coincides with Gallup's so-called "traditional" likely voter model, which considers both a voter's stated intention and his past voting behavior. The second cluster coincides with their "expanded" likely voter model, which considers solely the voter's stated intentions. Note the philosophical difference between the two: in the "traditional" model, a voter can tell you that he's registered, tell you that he's certain to vote, tell you that he's very engaged by the election, tell you that he knows where his polling place is, etc., and still be excluded from the model if he hasn't voted in the past. The pollster, in other words, is making a determination as to how the voter will behave. In the "expanded" model, the pollster lets the voter speak for himself.

<snip>

Pollsters ought to make certain that they're asking people whether they've already voted. Moreover, they ought to be putting these early voters through their likely voter models as a sanity check. That is, they should be testing to see whether a substantial number of people who have actually voted would in fact have been excluded by their likely voter screens. If the answer to this question is yes, they ought to be asking themselves whether their likely voter models have any basis in reality.

Read The Entire Article Here

[WeDidIt]

1. Shameless self kick n/t

[yourguide]

2. oh right on!

Thanks for this!

[WeDidIt]

3. I bet a significant percentage of people who get dumped on the likely model

have already voted.

[HughMoran]

4. I can't help but wonder where younger first time voters fit into the model

At the Obama rally in NH, nearly 60% of the people there had never voted because they were not old enough to vote previously. Now, on the BBC this morning, they interviewed an early voter who was voting for her first time - she was very enthusiastic! So enthusiastic, in fact, that she had convinced her mother who was on the fence to not only vote for Obama, but to vote early at her daughter's insistence. How on earth does a pollster account for that dynamic?

[WeDidIt]

5. Traditional Likely Voter Models dump 'em

Any first time voter in a traditional likely voter model is immeidately dumped.

The voter in your example, if AP polled her, she was DUMPED from the likely voter model EVEN THOUGH SHE HAD ALREADY VOTED because they do not ask if the person being polled has already voted.

[Tansy_Gold]

6. Many of us have already been taking this into consideration

and treating it as a tentative "reserve" for actual voting.

"Traditionally," young, first-time-registered voters have NOT turned out in large percentages, so the pollsters are if anything erring on the side of caution. And yes, they may also be erring on the side of the media who want a nail-biter down to election day.

What the campaigns are doing with internal polling may be very different. I suspect they are doing much more detailed polling that is watching all these newly-registered voters -- including the ones who have already voted and all those who have voted early -- very very closely.

Polling those who have already voted is rather like exit polling on election day. I'm not sure if there are any agreements within the media on whether or not to keep those under wraps and allow everyone to vote as though there were only one day to vote.

But the idea that there are different "models" for the likely voter is nothing new. If there weren't different models, there probably wouldn't be much difference in the polls.

TG

[WeDidIt]

7. The primaries proved beyond any doubt

this is not a "traditional" election year.

[hvn_nbr_2]

8. Gallup's use of two models is CYA

They're too bound to their old ways to give it up, but they still see the handwriting on the wall.