CNN - Trump and Sanders lead IA

[Zanas]

Math has your answers, folks!

Men: 63-32 Bernie
Women: 56-38 Hillary

Actual (hypo, but the sampling was equal) - 50/50 men-women, 140 EACH

UNSKEWED TO 2008 REALITY 120 MEN, 160 WOMEN

Among men: 76 vote Bernie, 39 vote Hillary
Among women: 61 vote Bernie, 90 vote Hillary

Overall: Bernie 137, Hillary 129

49 - 46

So there ya go.  Unskewed or whatever.  It's a dead heat by 2008 turnout. 

Ahem.

This is not 50/50. They give an 8 pt MoE for the Dem female sample, which points to roughly 150 women, and an 8.5 pt MoE for the male sample, which points to roughly 130 men. This is 53.5/46.5, which is still probably too masculine.

The whole subsample section of this poll is a laugh. It's 50 pages well worth reading for anyone with any notion of statistics !

[Alcon]

Thanks, Watermelon.

Also, it's important to note that MoE applies to subsamples, as well.  You'll occasionally get polls with quirky demographic results and that's in the nature of sampling.  "Unskewing" these polls interferes with the process of collecting a ton of data where the noise averages out.  That's not to say I'm against weighting -- I just think this is a silly exercise to do with every poll.

[yankeesfan]

Among 2012 caucus-goers:

Cruz 30%
Trump 28%
Rubio 16%

This poll cast a very wide net

[Mike Thick]

CNN is calling it "the makings of a political avalanche" for Trump. I'm increasingly inclined to believe them.

[Starbucks Union Thug HokeyPuck]

Thanks, Watermelon.

Also, it's important to note that MoE applies to subsamples, as well.  You'll occasionally get polls with quirky demographic results and that's in the nature of sampling.  "Unskewing" these polls interferes with the process of collecting a ton of data where the noise averages out.  That's not to say I'm against weighting -- I just think this is a silly exercise to do with every poll.

Did my un-serious-ness come across?  Guess not.

There's not much to take away from this poll other than a close race. 

[Alcon]

Thanks, Watermelon.

Also, it's important to note that MoE applies to subsamples, as well.  You'll occasionally get polls with quirky demographic results and that's in the nature of sampling.  "Unskewing" these polls interferes with the process of collecting a ton of data where the noise averages out.  That's not to say I'm against weighting -- I just think this is a silly exercise to do with every poll.

Did my un-serious-ness come across?  Guess not.

There's not much to take away from this poll other than a close race.  

Sorry, wasn't really specifically responding to your post.  Your point was totally valid -- that even with a hard weight this is still a slight Sanders lead

[Tender Branson]

Wow, if we look at all the recent polls this is going to be really tight.

Good that I took Feb. 2 off from work so I can follow the results all night ...

[pho]

On the Democratic side:
Sanders 51% (+15)
Clinton 43% (-11)
O'Malley 4% (+0)
Someone else <1% (-2)
None 1% (+<1%)
No Opinion 1% (-2)

Wow, a 26 point swing to Sanders. If anyone is imploding, it's Clinton.

[Tender Branson]

On the Democratic side:
Sanders 51% (+15)
Clinton 43% (-11)
O'Malley 4% (+0)
Someone else <1% (-2)
None 1% (+<1%)
No Opinion 1% (-2)

Wow, a 26 point swing to Sanders. If anyone is imploding, it's Clinton.

Don't tell the Clinton-supporters. They are living in their own world (... of denial).

[Landslide Lyndon]

On the Democratic side:
Sanders 51% (+15)
Clinton 43% (-11)
O'Malley 4% (+0)
Someone else <1% (-2)
None 1% (+<1%)
No Opinion 1% (-2)

Sorry but unless Hillary was caught eating a live baby on national TV there is no way to justify such a swing. Even Obama after his Iowa win didn't post such numbers.

[ProgressiveCanadian]

On the Democratic side:
Sanders 51% (+15)
Clinton 43% (-11)
O'Malley 4% (+0)
Someone else <1% (-2)
None 1% (+<1%)
No Opinion 1% (-2)

Sorry but unless Hillary was caught eating a live baby on national TV there is no way to justify such a swing. Even Obama after his Iowa win didn't post such numbers.

Sorry lyndon but it is plausible. In an election where the voters are going toward anti establishment candidates Clinton is being shown as corrupt and dishonest. I've been saying for months that this race will tighten and it has. Anyone who doubts that is a hack and doesn't believe in polling.

[Hillary pays minimum wage]

On the Democratic side:
Sanders 51% (+15)
Clinton 43% (-11)
O'Malley 4% (+0)
Someone else <1% (-2)
None 1% (+<1%)
No Opinion 1% (-2)

Sorry but unless Hillary was caught eating a live baby on national TV there is no way to justify such a swing. Even Obama after his Iowa win didn't post such numbers.

Sorry lyndon but it is plausible. In an election where the voters are going toward anti establishment candidates Clinton is being shown as corrupt and dishonest. I've been saying for months that this race will tighten and it has. Anyone who doubts that is a hack and doesn't believe in polling.

I'd have to say I agree.  If Clinton doesn't win IA or NH she's finished.

[Mr. Morden]

Nate Silver's already attacking this poll on Twitter for being too loose.

Who knew that he'd resort to slut-shaming?

[Landslide Lyndon]

On the Democratic side:
Sanders 51% (+15)
Clinton 43% (-11)
O'Malley 4% (+0)
Someone else <1% (-2)
None 1% (+<1%)
No Opinion 1% (-2)

Sorry but unless Hillary was caught eating a live baby on national TV there is no way to justify such a swing. Even Obama after his Iowa win didn't post such numbers.

Sorry lyndon but it is plausible. In an election where the voters are going toward anti establishment candidates Clinton is being shown as corrupt and dishonest. I've been saying for months that this race will tighten and it has. Anyone who doubts that is a hack and doesn't believe in polling.

Obviously you have no clue how elections work but whatever makes you sleep at night kiddo.

[Badger]

Nate Silver's already attacking this poll on Twitter for being too loose.

What does Silver know? The trends are clear! Turnout need only triple from 2012, and Trump and Sanders is a shoe-in!