Talk Elections

Presidential Elections - Analysis and Discussion => Polling => Topic started by: CARLHAYDEN on July 15, 2012, 12:21:36 PM



Title: Partisan identification in polls
Post by: CARLHAYDEN on July 15, 2012, 12:21:36 PM
Here is a key quote from a posting by Jay Cost, about three years ago:

Gallup and Pew Consistently Underestimate Republican Identifiers Relative to the Exit Poll.

Pew tends to be more pessimistic about the GOP's standing than Gallup, but both always show fewer Republicans than the exit polls. The difference is typically 5 to 7 points.

www.realclearpolitics.com/horseraceblog/2009/05/understanding_recent_changes_I.html


Title: Re: Partisan identification in polls
Post by: Brittain33 on July 15, 2012, 12:51:01 PM
I recall your making a similar point prior to the AZ-8 special as to why polls showing a Barber lead were inaccurate.


Title: Re: Partisan identification in polls
Post by: krazen1211 on July 15, 2012, 01:24:12 PM
Incidentally one of the theories I've seen concerning exit polls is that exit pollsters are more likely to exit poll young females compared to other demographics in the electorate.