SC: Harper: 4-way jumble for second (user search)
       |           

Welcome, Guest. Please login or register.
Did you miss your activation email?
June 14, 2024, 10:58:24 PM
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 Primary Election Polls
  SC: Harper: 4-way jumble for second (search mode)
Pages: [1]
Author Topic: SC: Harper: 4-way jumble for second  (Read 1244 times)
muon2
Moderators
Atlas Icon
*****
Posts: 16,823


« on: February 18, 2016, 01:37:04 PM »


How do you round to a negative number? Rounding doesn't mean you have to have exactly 100% in total... it just means that all of the numbers are rounded to their closest integer. To get -1% on anything you would need at least -0.5% of respondents to say something, which is impossible.

The "Other" number is automatically calculated by subtracting the sum of the other numbers from 100. If the candidate totals and the undecided number rounded sum to 101, then the "Other" number will be -1.

That's not how polls are reported when there is rounding error. The correct method is to state that the total does not add to 100% due to rounding, and Harper Polling in the link has that disclaimer. The Harper poll doesn't report an "other" category, and it should not be entered that way in the Atlas. I would also note that the Harper toplines have Undecided at 6%, so the total comes to 102% due to rounding.
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 0.023 seconds with 14 queries.