Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search
12 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
***New Monmouth NH poll HRC +4*** (Original Post) triron Oct 2016 OP
This is an outlier - no worries. Joe941 Oct 2016 #1
Or stop looking at polls and get to work for Hillary awake Oct 2016 #2
+1 Agschmid Oct 2016 #4
+2 Peaches999 Oct 2016 #9
Can't keep saying that. Its baffling he's gaining traction Thrill Oct 2016 #7
nah... look at the other polls. Clinton is gaining actually. Joe941 Oct 2016 #8
Oh Noes! book_worm Oct 2016 #3
ignore the polls and vote, please. Sunlei Oct 2016 #5
Obama carroed Lefthacker Oct 2016 #6
Statistics are your friend ... VMA131Marine Oct 2016 #10
Marist has her plus 9 sharp_stick Oct 2016 #11
this. Joe941 Oct 2016 #12

VMA131Marine

(4,149 posts)
10. Statistics are your friend ...
Wed Oct 26, 2016, 04:55 PM
Oct 2016

Think of it this way: there is about a 20% chance of a single poll result falling within ±1/4 of the MOE of the true state of the race. So if the MOE is ±3% and true support for a candidate is 45%, there is only a 1-in-5 chance that the poll result will be between 44.3% and 45.8%. There is a 68% (or about 2-in-3) chance that the poll result will be between 42% and 48% and a 95% chance that the poll result will be between 39% and 51%.

Another way to look at this is to say that if there are 20 polls of the same race, at least one will likely be off by more than 2 times the MOE in either direction and at least six will be off by more than the MOE in either direction.

Latest Discussions»Retired Forums»2016 Postmortem»***New Monmouth NH poll H...