2016 Official Polling Map Thread (user search)
       |           

Welcome, Guest. Please login or register.
Did you miss your activation email?
March 29, 2024, 12:20:01 AM
News: Election Simulator 2.0 Released. Senate/Gubernatorial maps, proportional electoral votes, and more - Read more

  Talk Elections
  Election Archive
  Election Archive
  2016 U.S. Presidential General Election Polls
  2016 Official Polling Map Thread (search mode)
Pages: 1 [2]
Author Topic: 2016 Official Polling Map Thread  (Read 119017 times)
Mr. Morden
Atlas Legend
*****
Posts: 44,073
United States


« Reply #25 on: May 08, 2015, 11:58:29 AM »

Before anyone asks me why I am not using the UNH-WMUR poll for New Hampshire -- the sample is R+5. New Hampshire was D+1 in 2014. It might be appropriate for the caucuses; I expect heavy R participation in the caucuses and light D participation in the caucuses. The big one? The general election? That's the one I have my focus on.

You are not using the NH poll because it shows Republicans ahead, that's the only reason.

First Mason-Dixon, now this ...

I may as well lock this thread or delete it if you are not using all polls.

A caucus vote is not relevant to November 2016. The general electorate vote of 2016 will be very different from the primary of caucus vote in any state.

What are you talking about ?

This was a poll of GE voters in NH, not "caucus" voters.

Not to mention, as I said, there is no caucus in NH.  I don't know what pbrower is on about.
Logged
Mr. Morden
Atlas Legend
*****
Posts: 44,073
United States


« Reply #26 on: May 08, 2015, 05:54:44 PM »

Quote
You must be logged in to read this quote.

It's about the primary election -- not the general election! Hillary Clinton is practically a foregone conclusion in the Democratic primary; the Republicans look to have plenty of choices.

Does anyone think that the New Hampshire general election is going to go 42% Republican, 37% Democratic?

No, you don't understand how polling works.  This is like the third time I've explained this on this board in the past week.  You can't say 229/627 = 37%, so they're making this sample 37% Democratic, because like every pollster they use weighting.  They're sampling an excess number of Democratic voters and an excess number of Republican voters (because they're simultaneously doing a primary polling question, and then weighting them a certain way in the GE matchup questions to match what they consider "likely GE voters".  Half the polls you post here are doing the same thing (though most of them are weighting to registered voters).  Their actual partisan breakdown, when they do weighting, is on page 6 of the writeup:

undeclared 45%
Republican 30%
Democrats 25%

You might also consider that too Republican-heavy, but have you actually been scrutinizing all of the partisan breakdowns for all the other polls you've been posting here, or did you just pick this one to toss out on these grounds, because you don't like the result?
Logged
Mr. Morden
Atlas Legend
*****
Posts: 44,073
United States


« Reply #27 on: May 08, 2015, 07:19:38 PM »

I saw no indication of weighting on partisan identity. Other things -- but not partisan identity. Yes, it is possible to get a statewide prediction for a state that splits nearly 50-50 even if one has a 6-1 edge in polling numbers for one party.

Page 6 of the poll, from the PDF you posted:

Party Registration
144 Democrat 25%
260 Undeclared 45%
170 Republican 30%

Party Identification
249 Democrat 40%
102 Independent 17%
266 Republican 43%

This is different from the 229 Democratic primary voters and 293 Republican primary voters you mentioned, because they're weighting differently for the two primary polling subsamples that they did, whereas the numbers that I just listed above are the general election sample.  Lots of pollsters conduct primary and general election polling in the same poll, and you've never had a problem with it before, so I don't see what the issue is.
Logged
Pages: 1 [2]  
Jump to:  


Login with username, password and session length

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

Powered by SMF 1.1.21 | SMF © 2015, Simple Machines

Page created in 0.03 seconds with 13 queries.