Pew apparently has Romney leading Obama 49-45. (user search)
       |           

Welcome, Guest. Please login or register.
Did you miss your activation email?
April 28, 2024, 11:26:50 AM
News: Election Simulator 2.0 Released. Senate/Gubernatorial maps, proportional electoral votes, and more - Read more

  Talk Elections
  Election Archive
  Election Archive
  2012 Elections
  2012 U.S. Presidential General Election Polls
  Pew apparently has Romney leading Obama 49-45. (search mode)
Pages: [1]
Author Topic: Pew apparently has Romney leading Obama 49-45.  (Read 4115 times)
cinyc
Atlas Icon
*****
Posts: 12,719


« on: October 08, 2012, 03:24:01 PM »


Yes.  And even in 2008, their polls tended to be all over the place, showing larger deficits than other pollsters.
Logged
cinyc
Atlas Icon
*****
Posts: 12,719


« Reply #1 on: October 08, 2012, 06:55:49 PM »

^ Yeah, the internals pretty much erase any worries I had about this.

I mean, look at this. 2/3 of respondents over 50? Am I misreading this?



That's the raw data - and having a large percentage of 50+s in a polling sample is pretty common.  Which group is more likely to be home during the daytime to answer a phone?  Pew and most other pollsters then weigh the sample for things like age, race and geography.  In fact, Pew says:

"The combined landline and cell phone sample are weighted using an iterative technique that matches gender, age, education, race, Hispanic origin and nativity and region to parameters from the March 2011 Census Bureau’s Current Population Survey and population density to parameters from the 2010 Decennial Census."
Logged
cinyc
Atlas Icon
*****
Posts: 12,719


« Reply #2 on: October 08, 2012, 11:19:43 PM »

I'm unsure how this poll is weighted but 83% of the respondents here were white, way too high to be legit. I know its weighted but I'd like to see more. Additionally, the number of southerners is really high and white southerners well, vote a lot differently than whites elsewhere.

Again:

"The combined landline and cell phone sample are weighted using an iterative technique that matches gender, age, education, race, Hispanic origin and nativity and region to parameters from the March 2011 Census Bureau’s Current Population Survey and population density to parameters from the 2010 Decennial Census."

So no.
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 15 queries.