Umm, Guess What??? That New, AWESOME Newsweek Poll... POLLED CELL PHONES

http://www.newsweek.com/2010/10/22/poll-obama-approval-jumps-dems-more-fired-up.html

-snip--

This poll was conducted by Princeton Survey Research Associates International on October 20–21, 2010. Telephone interviews were conducted with a nationally representative sample of 1,005 adults, age 18 years and over, including 672 adults reached on a landline telephone and 333 adults reached on a cell phone. The overall margin of sampling error is plus or minus 3.8 percentage points for results based on 1,005 adults. Results based on smaller subgroups are subject to larger margins of sampling error. The margin of error is plus or minus 4.2 percentage points for results based on 848 registered voters and plus or minus 4.3 percentage points for results based on 773 likely voters. In addition to sampling error, the practical difficulties of conducting surveys can also introduce error or bias to poll results.

--snip--

Hmmmm. Imagine that. Decent sample size too.

:woohoo:

As does Pew, which has us losing 40-60 seats. As do almost all live-interview pollsters, none of which has such good results.

Newsweek usually is more Democratic-leaning than other pollsters. They had Obama vs. McCain polls at one point where Obama was winning by something like 15 points. I don't think it's the cell phone issue.

link supporting that, because I have read otherwise. Thanks.

http://www.gallup.com/poll/110383/does-gallup-call-cell-phones.aspx

"Gallup includes cell phones in each national Gallup poll. Gallup has been including cell phone-only households in all national telephone Gallup polls since January 2008. Further, cell phone-only households are now as likely to fall into national Gallup polls samples as those living in traditional landline households."

http://people-press.org/reports/pdf/666.pdf

"Results for this survey are based on telephone interviews conducted October 13-18, 2010 among a national sample of 2,251 adults 18 years of age or older living in the continental United States (1,487 respondents were interviewed on a landline telephone, and 764 were interviewed on a cell phone, including 311 who had no landline telephone)."

users weren't accessible for polls so I stand corrected, at least with these two orgs.

Pray tell. Let's see proof of that.

I wonder whose is closer to reality? Guess we'll see.

I'm just saying it has little to do with cell phones.

While Gallup is way off (I think and hope), Newsweek is likely off in the other direction.

Aggregates, or at least COULD.

Robopollsters like Rasmussen historically aren't that inaccurate. Rasmussen had Obama winning by 6, and he won by 7. Despite not calling a single cell phone. They might be off by a point or two, but they aren't usually off outside the margin of error (any more than cell phone pollsters are).

If you have unweighted samples, of course no cell phones will probably produce a bias (and probably a large one). But if you weight to take into account gender, race, etc, the difference becomes much less clear.

n/t

For example, they have hispanic voters who went 2 to 1 for Obama, flipping to 50-something - 40 something -- with the Rethugs on top. Even with all the anti-immigration rhetoric of the Rethugs. That can't be accurate. Something's wrong with their "likely voter" sample.

computed an approximation of the Hispanic subgroup given other data.

The reason they don't release it is because subgroups have much smaller sample sizes, and the smaller the sample size goes, the more error you get. Most polls have some subgroups that are wildly divergent from reality, but their top line ends up being accurate.

(For example, if you were to take a 1000 LV sample, and then look at the subgroup of people with blue eyes and red hair, your margin of error on that subgroup will will be in high double digits, even though the margin of error on the whole sample is only around 3%.)

I think their likely voter methodology is underestimating turnout. But the small-sample Hispanic result you are talking about isn't the main reason.

NEWSWEEK Poll: Obama Approval Rating Jumps, Democrats Close ‘Enthusiasm Gap’

Sorry... was that too loud?

:evilgrin:

:thumbsup:

:thumbsup::thumbsup:

:hi:

bodes well!