Welcome, Guest. Please login or register.
Did you miss your activation email?
November 21, 2019, 11:26:05 pm
News: 2019 Gubernatorial Endorsements Close today at noon

  Atlas Forum
  Election Archive
  Election Archive
  2016 U.S. Presidential General Election Polls
  NC-SurveyUSA: Trump +7
« previous next »
Pages: 1 2 3 4 [5] Print
Author Topic: NC-SurveyUSA: Trump +7  (Read 23167 times)
Speed of Sound
LiberalPA
YaBB God
*****
Posts: 14,183
United States


Show only this user's posts in this thread
« Reply #100 on: November 01, 2016, 06:36:45 pm »

Lotta reasons to not worry about this one. SUSA is a great pollster, but the crosstabs are too far off, especially on early voters. Throw it in, mix 'em up. NC will be close, that's a reality. Know that this poll exists and keep watching the numbers.
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #101 on: November 01, 2016, 07:05:42 pm »

Lotta reasons to not worry about this one. SUSA is a great pollster, but the crosstabs are too far off, especially on early voters. Throw it in, mix 'em up. NC will be close, that's a reality. Know that this poll exists and keep watching the numbers.

IDK, this is definitely is an outlier, but one should generally not look too much into crosstabs.

Why? Because it is a lot of them: youngs, older, liberals, conservatives, black, white, blue, red, male, female,  rural, suburban, urban, educated, non-educated, low-income, middle, early voting etc, etc. Each group is about 100-400 in an average poll, which gives 5-10 MOE, and ~10-20 MOE of difference. But that sort of cancels out each other (for example, Trump might do to good among EV, but too bad among non-EV). At least in theory. Undersampled groups might though cause bigger errors (but EV in this particular poll wasn't undersampled, I guess).

That basically means, that you always find a odd-looking subsample. By chance. Always. I never look at subsamples < 400. That's why I don't like Monmouth (they totally has just ~400 LV); they are good on average, but pretty often give weird swings.

But OK, you don't like early voters, right?
Totally EV = 659*40% = 264
Then Hillary's and Trump's MOE would be ~ 6.04
The MOE of difference               would be ~11.95

So does this result of EV look so strange, given those MOE?

Both Nates wrote about "how to read polls". Atlas should read it Roll Eyes
Logged
JJC
Sr. Member
****
Posts: 446


Show only this user's posts in this thread
« Reply #102 on: November 01, 2016, 07:12:01 pm »

“Registered Democrats are 3.4 percent behind their same-day totals from 2012, while registered Republicans are ahead of their same-day totals at 6.2 percent and registered unaffiliated voters continue to move ahead of their same-day totals, at 37.7 percent.”

“While white voters are 15 percent ahead of their same-day totals from 2012, black voters continue to lag their 2012 same-day totals, down 16 percent.”

http://www.oldnorthstatepolitics.com/

The caveat for Trump is that while EV is way better for him than Romney, he's not nearly as popular as Romney was. (But again, Trump's saving grace is that he's running against someone equally as unpopular).

NC will be close, but I think Trump will carry it.

For the record I think Trump will carry OH and FL comfortably by 3-5% each. Strange how NC is likely to vote to the left of those states. Either way we'll know how the election is shaping up pretty early since NC is one of the first to vote.
Logged
Speed of Sound
LiberalPA
YaBB God
*****
Posts: 14,183
United States


Show only this user's posts in this thread
« Reply #103 on: November 01, 2016, 07:16:09 pm »

Both Nates wrote about "how to read polls". Atlas should read it Roll Eyes

I get why you prefer to respond to many of the trolls around here this way. It really doesn't give people looking to have a real convo much interest in engaging you deeply, though.

I get what you're at, but sometimes an outlier is just that. This just isn't close to anything SUSA or anyone else reputable has ever found in NC. That probably means that at least one thing (and probably more) is throwing off the sample a lot. Like I said, know it exists, place it where you want. This one alone, without at least one corresponding poll, looks like a heavy outlier. I don't tend to give much weight to heavy outliers. If more polls come in to show this might be on track, I'll give it another look over.
Logged
Clarence Boddicker
Full Member
***
Posts: 229


Political Matrix
E: -7.35, S: -5.91

Show only this user's posts in this thread
« Reply #104 on: November 01, 2016, 08:35:24 pm »

https://www.youtube.com/watch?v=i7gIpuIVE3k
Logged
DavidB.
YaBB God
*****
Posts: 11,971
Finland


Political Matrix
E: 0.06, S: 6.00

Show only this user's posts in this thread
« Reply #105 on: November 01, 2016, 08:36:52 pm »

Yikes, this thread might be just as bad as this poll. When it's LBP who's actually being the most reasonable one in the entire thread I suggest people just calm down.

It is an outlier. It happens. But it doesn't mean that you completely dismiss it. Deal with it and average it.
^ This exactly.
Logged
rafta_rafta
YaBB God
*****
Posts: 926


Show only this user's posts in this thread
« Reply #106 on: November 01, 2016, 09:22:34 pm »

Trump EV numbers are very good in NC, but I don't think they will hold. He might still win if tightening continues, but it would be by 2-3 points, not 7
Logged
Green Line
YaBB God
*****
Posts: 5,490
United States


Show only this user's posts in this thread
« Reply #107 on: November 01, 2016, 09:30:07 pm »

Balderdash poll
Logged
Vern
vern1988
Atlas Politician
YaBB God
*****
Posts: 1,740
United States


Political Matrix
E: 0.26, S: -2.43

P P P

Show only this user's posts in this thread
« Reply #108 on: November 01, 2016, 09:39:44 pm »

If you believe this poll then you are stupid.
Logged
NOVA Green
Oregon Progressive
YaBB God
*****
Posts: 5,031
United States


Show only this user's posts in this thread
« Reply #109 on: November 01, 2016, 10:03:42 pm »

Trump EV numbers are very good in NC, but I don't think they will hold. He might still win if tightening continues, but it would be by 2-3 points, not 7

This....

Exactly what I have been saying for months, even with the inevitable roller-coaster ride that is Atlas every four years, NC will not be a +4/5 D/R state in 2016 and go all the way to the wire until late in the evening...
Logged
Maeglin
Newbie
*
Posts: 1
New Zealand


Show only this user's posts in this thread
« Reply #110 on: November 01, 2016, 11:07:24 pm »

I'm not going to dismiss the poll out of hand, but perhaps we could wait until we get some more data out of there before panicking?
Logged
Storebought
YaBB God
*****
Posts: 3,905
Show only this user's posts in this thread
« Reply #111 on: November 01, 2016, 11:12:16 pm »

This poll implies that, at the moment it was taken, Trump was leading in NC. The same can be said about that D+8 W&M poll from FL -- at the moment it was conducted, Clinton was ahead. The margin itself is immaterial and largely meaningless.
Logged
rob in cal
YaBB God
*****
Posts: 1,799
Show only this user's posts in this thread
« Reply #112 on: November 02, 2016, 12:51:30 am »

  SUSA crosstabs often are interesting and not what we'd expect.
Logged
mencken
YaBB God
*****
Posts: 2,233
Show only this user's posts in this thread
« Reply #113 on: May 12, 2017, 08:18:01 am »


SurveyUSA was closer to the final outcome than PPP.
Logged
DavidB.
YaBB God
*****
Posts: 11,971
Finland


Political Matrix
E: 0.06, S: 6.00

Show only this user's posts in this thread
« Reply #114 on: May 31, 2017, 07:45:01 am »

Ha, good catch. Especially that PPP tweet...
Logged
Pages: 1 2 3 4 [5] Print 
« previous next »
Jump to:  


Login with username, password and session length
Logout

Terms of Service - DMCA Agent and Policy - Privacy Policy and Cookies

Powered by SMF 1.1.21 | SMF © 2015, Simple Machines

© Dave Leip's Atlas of U.S. Elections, LLC