Free Republic
Browse · Search
News/Activism
Topics · Post Article

To: BlessedBeGod
The final 2012 Rand poll (11/6/12) had Obama 49.4%/Romney 46.8%, 2.6% spread.

Actual 2012 election result: Obama 51.1%/Romney 47.2%, 3.9% spread.

At 3.2%, this is a wider poll points spread than 2012.

IBD was #1 in 2012 and Rand -- now the USC Dornsife/Los Angeles Times "Daybreak" poll -- was #4. Both show a Trump lead.

Can the majority of the polls be wrong?

Of course, if they are done badly! I don't see that it makes any sense to weight the worst performing polls in 2012 as much as the best ones, but the news stories weight them higher!

Gallup -- the "gold standard" for presidential election polling between 1936 and 2012 -- gave up on presidential election polling after their dismal 2012 performance. They (apparently) think it's impossible to do this accurately at a reasonable cost today. Most, if not all, of the major alphabet polls showing a Clinton lead are done much the same way as Gallup did its 1936 poll -- telephones and live, probably majority young female, interviewers -- but with a much smaller sample size.

(I have a red lizard mailbox flag. I didn't know it was political.)

166 posted on 11/08/2016 3:07:48 AM PST by Sooth2222 ("Every nation has the government it deserves." - Joseph de Maistre (1753-1821))
[ Post Reply | Private Reply | To 1 | View Replies ]


To: Sooth2222

Here is the 2012 graph for comparison to the 2016 final linked in the opening thread.

https://alpdata.rand.org/?page=election2012

Although Obama didn’t have a dramatic trend downward at the end, Romney was clearly surging. It wasn’t enough and the differential held. Pray that the 2016 poll is as accurate as this one.


167 posted on 11/08/2016 3:17:35 AM PST by Nicojones
[ Post Reply | Private Reply | To 166 | View Replies ]

Free Republic
Browse · Search
News/Activism
Topics · Post Article


FreeRepublic, LLC, PO BOX 9771, FRESNO, CA 93794
FreeRepublic.com is powered by software copyright 2000-2008 John Robinson