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

DemocratSinceBirth

(99,710 posts)
Fri Sep 28, 2012, 12:31 PM Sep 2012

The Recurring -- and Misleading -- Focus on Party Identification

The discussion of the party identification composition of poll samples comes up in every presidential election with which I've been involved. Interested observers often opine that when a given poll shows that Candidate X is ahead, it cannot be correct because there is a higher percentage of voters who identify with Candidate X’s party in the sample than there should be, based on comparison to some previous standard.

There are several reasons why this is a faulty approach to evaluating a poll's results.

Party identification is basically an attitudinal variable, not a stable population parameter. It is designed to vary. This is distinct from demographic variables such as age, gender, race/ethnicity,

http://pollingmatters.gallup.com/

2 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
The Recurring -- and Misleading -- Focus on Party Identification (Original Post) DemocratSinceBirth Sep 2012 OP
Eugene Robinson makes this point today Proud Public Servant Sep 2012 #1
Party ID Is Fluid* Only A Moron Would Suggest It's An Immutable Characteristic Like Race Or Gender DemocratSinceBirth Sep 2012 #2

Proud Public Servant

(2,097 posts)
1. Eugene Robinson makes this point today
Fri Sep 28, 2012, 12:36 PM
Sep 2012

in his column. Here's are the money quotes:

The Rasmussen daily tracking poll, however, saw the race as still tied. Why the anomaly? Because the Rasmussen firm weights its sample to achieve what it believes to be a representative balance of Democrats and Republicans. While other pollsters also ask about party affiliation, most of them weight their samples to reflect the nation’s demographic profile and do not seek a specific balance between R’s and D’s.


The problem is that party affiliation can be weak and changeable. Voters who describe themselves as Democrats one month can call themselves Republicans or independents the next. In this sense, it’s not something polls can assume as a precondition. It’s something polls discover.


If a polling sample shows Democrats outnumbering Republicans by, say, 32?percent to 24?percent (with most of the rest calling themselves independents), GOP partisans shouldn’t worry about a conspiracy. They should worry that this is a snapshot of how Americans feel about the two major parties.


Whole thing here: http://www.washingtonpost.com/opinions/eugene-robinson-republicans-deluded-by-skewed-polls/2012/09/27/b3dd7d40-08d3-11e2-afff-d6c7f20a83bf_story.html

DemocratSinceBirth

(99,710 posts)
2. Party ID Is Fluid* Only A Moron Would Suggest It's An Immutable Characteristic Like Race Or Gender
Fri Sep 28, 2012, 12:39 PM
Sep 2012





*except for me.
Latest Discussions»General Discussion»The Recurring -- and Misl...