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

7worldtrade

(85 posts)
Sat Oct 13, 2012, 07:53 AM Oct 2012

Woke up to Nice Movement in Rand Tracking Poll This Morning

https://mmicdata.rand.org/alp/index.php?page=election

Different "experts" have different takes on the Poll. Nate Silver uses it. He thinks its methodology is unorthodox but reliable.

Also, click on the various sub-tabs on the top to see additional responses by the participants. For instance, who they predict the winner will be, which, I understand, is a very powerful tool to actually predict who the winner will be.

5 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies
Woke up to Nice Movement in Rand Tracking Poll This Morning (Original Post) 7worldtrade Oct 2012 OP
Rand shows something starting 4 days back unc70 Oct 2012 #1
Is this reliable? If so it looks good. Tennessee Gal Oct 2012 #2
What does the intention to vote graph mean? ananda Oct 2012 #3
Don't worry 7worldtrade Oct 2012 #5
How Come? JGug1 Oct 2012 #4

unc70

(6,114 posts)
1. Rand shows something starting 4 days back
Sat Oct 13, 2012, 08:02 AM
Oct 2012

Something started about Tuesday with their various measures. Wonder what.

7worldtrade

(85 posts)
5. Don't worry
Sat Oct 13, 2012, 08:22 AM
Oct 2012

Unlike other polls that do a likely voter screen and then don't count anyone's voting preference if they fail the screen, this poll asks each person who they will vote for and the likelihood that they will vote. It then weighs the preference with the likelihood. Say someone says they prefer Obama but there's only a 1 in 3 chance they will vote, then their preference is only given 1/3 of a point. So, even when you see the graph that shows lower voter intention to vote for Obama that is already factored into the main poll.

The fact that the intention to vote graph doesn't look good is consistent with other polls that give Obama a lead in the registered voter universe but not necessarily in the likely voter universe.

The statisticians behind this poll think that's a better measure than the likely voter screen.

JGug1

(320 posts)
4. How Come?
Sat Oct 13, 2012, 08:09 AM
Oct 2012

Is the upward trend a measure of some moderating of the direction of the poll that followed the President's poor performance in his debate or is there some of Biden's excellent performance being measured? (I think less likely since VP debates don't generally change much but more desirable because it would mark a relatively surprising real strength for the administration. Too bad Biden doesn't get to do it again)

Latest Discussions»General Discussion»Woke up to Nice Movement ...