Welcome, Guest. Please login or register.
Did you miss your activation email?
March 20, 2019, 11:13:53 pm
HomePredMockPollEVCalcAFEWIKIHelpLogin Register
News: Please delete your old personal messages.

+  Atlas Forum
|-+  Election Archive
| |-+  Election Archive
| | |-+  All Archived Boards
| | | |-+  2016 U.S. Presidential General Election Polls (Moderators: AndrewTX, Likely Voter)
| | | | |-+  NC-SurveyUSA: Trump +7 (search mode)
Pages: [1] Print
Author Topic: NC-SurveyUSA: Trump +7  (Read 21632 times)
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,673
Sweden


View Profile
« on: November 01, 2016, 03:12:48 pm »

This is happening...


Img
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,673
Sweden


View Profile
« Reply #1 on: November 01, 2016, 03:15:34 pm »

Even GOP internals still have Trump losing here...
No. Only "a former anonynomous FBI agent and Top GOP pollster"... Roll Eyes
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,673
Sweden


View Profile
« Reply #2 on: November 01, 2016, 03:16:47 pm »

Obamacare premium hikes affecting the middle class voters weigh more on their moods and pockets than Trumps groping it seems.

This and the email story (if it is not going away in the news in the next days) could be the kiss of death for her ...
I am not sure which of us is enjoing it more though Angry


Ah, here's probably a major source of the disagreement:

Quote
SurveyUSA polled 659 people statewide Friday through Monday who have already cast their ballots or are likely to vote in the election and found Trump with a 51 to 44 percent lead over Democratic rival Hillary Clinton.

Did they not poll Unaffiliateds or something?
They always has strange crosstabs though...
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,673
Sweden


View Profile
« Reply #3 on: November 01, 2016, 03:58:16 pm »

Img
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,673
Sweden


View Profile
« Reply #4 on: November 01, 2016, 04:25:37 pm »

cohn also implies that the urban numbers (only +10 C) are trash.

As did Liam Donovan, a longtime GOP operative

So did Nate Silver about Trump in the primary. He dismissed all the polls as a trash (as Dems did this week, actually) Tongue
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,673
Sweden


View Profile
« Reply #5 on: November 01, 2016, 04:33:40 pm »

It is an outlier. It happens. But it doesn't mean that you completely dismiss it. Deal with it and average it. BTH, do you think that Sienna/Upshot poll could be an outllier?

Trashing 1 poll methodology vs trashing all polls and building a model that used endorsements to predict the primary winner are not the same thing.

ABC, IBD and SUSA, all A pollsters has been trashed, when they showed... guess what Smiley

And even Monmouth↓↓↓

It's difficult to envision Trump significantly outperform Romney's margins here (+10%).
« Last Edit: November 01, 2016, 04:35:31 pm by Happy Sad Trumpista »Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,673
Sweden


View Profile
« Reply #6 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
Pages: [1] Print 
Jump to:  


Login with username, password and session length
Logout

Terms of Service

Powered by SMF 1.1.21 | SMF © 2015, Simple Machines