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

2016 Postmortem

DemocratSinceBirth

(99,710 posts) Fri Nov 4, 2016, 08:10 AM Nov 2016

Clinton Nov. win probability: random drift 98%, Bayesian >99%

http://election.princeton.edu/

3 replies

= new reply since forum marked as read

Highlight:

*****Clinton Nov. win probability: random drift 98%, Bayesian >99%***** (Original Post) DemocratSinceBirth Nov 2016 OP

Nate Silver lowered Clinton's odds Charles Bukowski Nov 2016 #1

3% at least! regnaD kciN Nov 2016 #2

Nate Silver factors in all the polls, whether they are reliable or not, and constructs his model still_one Nov 2016 #3

Charles Bukowski

(1,132 posts)

1. Nate Silver lowered Clinton's odds

Reply to DemocratSinceBirth (Original post)

Fri Nov 4, 2016, 08:15 AM

Nov 2016

2% upon hearing this news.

regnaD kciN

(26,044 posts)

2. 3% at least!

Reply to Charles Bukowski (Reply #1)

Fri Nov 4, 2016, 08:21 AM

Nov 2016

still_one

(92,190 posts)

3. Nate Silver factors in all the polls, whether they are reliable or not, and constructs his model

Reply to Charles Bukowski (Reply #1)

Fri Nov 4, 2016, 08:22 AM

Nov 2016

from that data.

With the election a few days away, no one is going to change their vote. They know who they are voting for. Whether the polls are adequately reflecting such factors as republican cross-over votes, Latinos, or other demographics we will know in the course of time, but for those pollsters using 2012 as a model to base 2016, I think is a faulty assumption.

Most important thing is to GOTV through call banking and canvassing in swing states

The rest will take care of itself

Reply to this discussion