Ann Selzer "worried "about number of independents in her Des Moines Register Poll

[Herman Munster]

She doesn't sound very confident about her own poll and recognizes there could be problems with it.

http://www.desmoinesregister.com/apps/pbcs.dll/article?AID=/20080101/NEWS09/80101001/-1/2006_primary

Ann Selzer, president of the firm Selzer & Co., which polls for The Des Moines Register, said the poll didn�t �oversample� independents or employ any sort of a new model.

We used the same method we used in 2004 to define likely caucusgoers,� Selzer said. And, yes, we have more independents than in 2004, and more than in our past polls in 2007. It's something we worry about, along with many other things.

Selzer weighted the results to look like the proportion of party participants in 2004 and Clinton would�ve won, she said.

She said: "It is true, Senator Clinton leads with Democrats. It is also true that other campaigns have courted independents."

This is really a sit-and-wait time for pollsters, Selzer said.

[davidinalameda]

1. I never did understand how you can poll caucus goers anyway

[sandnsea]

2. Pick up the phone and call them

:shrug:

[Honeycombe8]

5. Yeah, I've heard the pundits explaining the caucus process and how hard to poll.

But the Des Moines Register has experience with it, at any rate, and got it right their last poll before the '04 caucus. So they must be doing something right.

I'm keeping an eye on this poll more than the others.

I have seen two stories on TV in recent months showing how many more Independents there are in the country now, compared with 2004. And in Iowa I saw recently that there are a WHOLE BUNCH OF 'EM! I THINK - and I'm just going by memory - that there are more Independents in Iowa than there are Democrats or Republicans. Next are Democrats. The smallest group is the Republican group.

[jefferson_dem]

3. Survey researchers always "worry" about having the proper partisan representation in their sample.

This is a major issue, actually, with some firms weighting sample numbers to better reflect their population. Good for her for being honest.

[Pastiche423]

27. What does "weighting" mean?

[aquart]

4. So Dems go for Hillary but she'll lose because non-Dems can caucus Dem?

So non-Democrats get to decide the Democratic candidate? And this is a good idea...?

[KingofNewOrleans]

7. Well, they do have to become Dems to participate

in the caucus.

[sniffa]

10. yes, that's an awesome idea

DUers can complain all they want to when it comes to their candidate, but fuck that - i'm voting in the primaries regardless of my unenrolled status, and everyone should.

[Adelante]

12. No, they will be Dems when they caucus - they have to register Dem first nt

[DemocratSinceBirth]

13. Lots Of Different Assumptions Were Built Into The 04 Poll

If the same methodology was used in this poll as in the 04 poll Hillary would win...

Ms. Selzer admits the methodology is different...I forgot the exact number but 45% or 55% in Ms.Selzer's models will be independents who registered Democrat just to caucus ... We shall see soon..

[Jane Austin]

18. She specifically said

"In terms of the first-time caucus goers, even if we statistically play with the data and say, 'Okay, let's make it look like 2004,' Barack Obama still wins.

"That's a pretty robust finding and we feel pretty good about it."



I played it back on TiVo, so this is an accurate quote of what she said.

[DemocratSinceBirth]

19. I Am Not Attacking Her Model...I Am Putting It In Context...

Lots of assumptions are built into a statistical model...

This is from David Yepsen of the Des Moine Register:


A lot of Democratic caucus-goers aren't all that Democratic. Some 40 percent of the Democratic caucus-goers say they are independents, and another 5 percent say they are Republicans. (Technically, they'll all have to re-register as Democrats to participate, but that can be done at the caucus site.) Put another way, 54 percent of the Democratic caucus-goers say they're Democrats. In 2004, it was 80 percent.

That will raise some eyebrows among party pros. While we all know the Democratic turnout will be large, the events just haven't attracted that many newcomers in the past. If that happens as the poll suggests, the caucuses will no longer be affairs of the party activists and faithful, but more like primaries.

Will some of these fair-weather Democrats not bother to show up? If they don't, it will change the outcome. If pollsters adjust the party identifications in 2008 to look like they did in 2004, Clinton could beat Obama 31 percent to 29 percent.

http://www.desmoinesregister.com/apps/pbcs.dll/article?AID=/20071231/OPINION01/71231038/-1/iowapoll07

[jenmito]

21. Yup. I watched her this morning and was very glad to hear her confidence in the polling.

[Jane Austin]

6. II just watched her on The News Hour (PBS)

and she was supremely confident in her methods.

She said the number of new caucus goers in 2004 was 45%, so it's not that amazing that there would be 60% new caucus goers this year with the excitement of several Democratic candidates.

BTW, they didn't call "new caucus goers", they called Iowans and determined then that they were going to the Dem caucus and that they were first- or second- or long-time caucus goers, so it's not like the sample was skewed that way.

She said she didn't assume "anything" that it's what the data showed her.

[calteacherguy]

8. Excellent.

:thumbsup:

[Adelante]

9. The poll was conducted the same way as in 2004

Is that right, janeaustin? Thanks.

[DemocratSinceBirth]

14. Please See Post Thirteen

I answered in the wrong place...

[Jane Austin]

15. Yes, that's what I recall her saying.

The big differences are that in 2004, the weekend before the caucuses was a day or two before caucus day - not four days before - because the caucuses were on a Monday last time; and that the polling wasn't done during the Christmas vacation last time, because the last weekend before the caucus was the middle of January in 2004, not the end of December.

[WheelWalker]

11. k&r!

[Joe the Revelator]

16. Keep imploding Herman

Its fun to watch!

[DemocratSinceBirth]

17. There Are Some Intersting Discussions Of The Poll Here And Here

http://www.pollster.com/blogs/poll_des_moines_registerselzer_1.php

http://marcambinder.theatlantic.com/archives/2007/12/my_one_question_about_the_regi.php


Maybe her model is right...Maybe it isn't...

[KingofNewOrleans]

22. Thanks for the links

Pretty much what we've been chewing on the last 24 Hrs. Except by my math, turnout will have to be 200,000 or more for 1st time caucus goers to top 60%.

[DemocratSinceBirth]

23. She's The Expert...She Presumably Has A PhD...She Built A Model

She could be right...

[jenmito]

20. She was on C-Span this morning defending the poll...

and she said they looked deep into the internals to see if there was a different likely outcome and they couldn't find it. Like you quoted, "J. Ann Selzer, president of the firm Selzer & Co., which polls for The Des Moines Register, said the poll didn’t “oversample” independents or employ any sort of a new model."

[Herman Munster]

24. yet she is worried

she is worried that this poll is an outlier because it is not in line with her own polls in 2004 or any of the previous polls in 2007 or any of the polls from other polling organizations.

[jenmito]

25. Nah. Nothing out of the ordinary "concern" about wanting to be right. She's confident...

but feel free to spin it any way you need to to keep your dream alive! :hi:

[DemocratSinceBirth]

26. Why Are You Allowing Yourself To Get Baited, My Friend?

She built a model...Her model is different than most of the other models...Maybe she's right...Maybe she isn't...

There are 3,000,000 or so adult voters in Iowa...Only about five perecent or so of them will caucus...That makes getting a good sample difficult...

[Jane Austin]

28. She didn't say anything about being worried

on the News Hour tonight.

Quite the opposite.

[Adelante]

33. Ann Selzer discussing Des Moines Register Poll

Here is some of the transcript:

Today’s Iowa poll is out. You’re assuming that 60 percent of the voters in the Democratic caucuses will be first-time caucus attendees. How did you assume that? Why did you assume it?

ANN SELZER, Des Moines Register: Well, actually, I assumed nothing. That’s what my data told me.

We put our method in place, and we let the voters speak to us. And we found that 60 percent of the people who told us they were definitely or probably going to the caucus indicated that it would be their first time at caucus.

It’s not all that much bigger than 2004. It was 45 percent then. But this stands to be a historic caucus, in terms of turnout.

-snip

ANN SELZER: Well, of course they’re reacting, because they’re not in the lead. And I would expect them to find criticisms.

In terms of the first-time caucusgoers, even if we statistically play with the data and say, “OK, well, let’s make it look like 2004,” Barack Obama still wins. So that’s a pretty robust finding, and we feel pretty good about it.

-snip

JUDY WOODRUFF: You’re also saying that 40 percent of the voters in the Democratic caucuses are going to be independents. How do you know that?

ANN SELZER: Well, again, that’s what our data is telling us. And is that a surprise? Sure. It’s something that would raise an eyebrow, because that’s more independents than would have come to any previous caucus.

But as you know in this campaign, just keeping your ear to the ground, there are a lot of people who are independent who are planning to come to caucus. The campaigns are certainly courting independents.

-snip

JUDY WOODRUFF: And, again, you were looking at voters who say they are either definitely or…

ANN SELZER: Or probably…

JUDY WOODRUFF: … probably.

ANN SELZER: … going to attend. And that gives us the advantage, Judy, also to take a look at just those definite attenders and say, “OK, well, what’s the core of what’s going to happen here?” And when you look only at those, it is still a Barack Obama win.

http://www.pbs.org/newshour/bb/politics/july-dec07/precaucus_1-1.html

[jenmito]

34. This is the key line that shows her confidence:

ANN SELZER: … going to attend. And that gives us the advantage, Judy, also to take a look at just those definite attenders and say, “OK, well, what’s the core of what’s going to happen here?” And when you look only at those, it is still a Barack Obama win.

[DemKR]

29. this poll is DEF a bunch of bullshit n/t

[DemocratSinceBirth]

30. Ipse Dixit

~

[jenmito]

31. You wish.

[candymarl]

32. I don't understand polling methodology

However, I did once reside in Iowa. Then, it was pretty strongly Republican. That began to change just before I moved away. I believe it changed because of the actions of the Repub governor at the time (I forget his name). A member of his family caused an accident that killed two people. He was under the influence. No charges were ever filed and the victims received no justice. People in Iowa were outraged. That's when the Dems began a comeback. So the poll may not be skewed. Perhaps some of those former Repubs didn't want to become Dems but didn't want to remain Repubs. That's just a guess of course.

[Zynx]

35. I don't buy this 40% Independents nonsense.

With competition from the Republican Caucus for the group, I don't see how it will be so much more than 2004. I just don't buy it. Whenever they call for a revolutionary election it doesn't happen.

[jenmito]

36. It's not nonsense. And you should read her quote from post #34. n/t