WaPo/SurveyMonkey: All 50 states! (user search)
       |           

Welcome, Guest. Please login or register.
Did you miss your activation email?
March 29, 2024, 03:13:08 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
  WaPo/SurveyMonkey: All 50 states! (search mode)
Pages: [1]
Author Topic: WaPo/SurveyMonkey: All 50 states!  (Read 10425 times)
Mallow
Jr. Member
***
Posts: 737
United States


« on: September 06, 2016, 08:06:35 AM »

In a 50-state poll two or three state results should be outside the margin of error based on statistics alone.

Yep. People automatically say "junk" to these 50-state polls because of odd inconsistencies, but odd inconsistencies are to be expected simply from statistical noise. That doesn't mean all the data is worthless. It means we should be considering all polls, regardless of whether they're released as a single state poll or a group of them, with the proper amount of skepticism. They're useful, but there's bound to be errors.
Logged
Mallow
Jr. Member
***
Posts: 737
United States


« Reply #1 on: September 06, 2016, 11:59:45 AM »

Why would you poll all 50 states but not DC? It has a higher population than either Vermont or Wyoming, and I don't see anything that would make it extraordinarily difficult to poll.

It says right in the article that the sample size was too small for DC. Just because its population is higher doesn't mean more people were surveyed.
Logged
Pages: [1]  
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 0.024 seconds with 13 queries.