Register | Sign In


Understanding through Discussion


EvC Forum active members: 65 (9162 total)
6 online now:
Newest Member: popoi
Post Volume: Total: 915,815 Year: 3,072/9,624 Month: 917/1,588 Week: 100/223 Day: 11/17 Hour: 0/0


Thread  Details

Email This Thread
Newer Topic | Older Topic
  
Author Topic:   Nate Silver's 538: 2018 House Predictions
Chiroptera
Inactive Member


(1)
Message 1 of 3 (838245)
08-16-2018 6:23 PM


Nate Silver's fivethirtyeight.com has published their predictions for the House of Representative elections this November.
For those people who were shocked at Trump's election in 2016, I'll go ahead and explain what the probabilistic predictions actually mean.
I will be talking about the predictions at this exact time: check the time stamp on this post to see when I wrote this.
The first graphic is a histogram that shows the probabilities for various numbers of Ds elections vs Rs election. Right now it peaks at about a majority of 18 or 19 more Ds than Rs. However, it is unlikely that this exact number will be elected, just like if you toss 100 fair coins you don't really expect to get exact 50 head and 50 tails.
Rather, you look at the sum of all the heights of the blue bars. It appears that the probability of a Democratic majority is slightly less than 75%. Thus, the odds of the Democrats picking up a majority is 3:1, if you like odds better than probabilities.
For those who were shocked at Trumps victory two years ago: This does not mean that the Democrats are a shoe-in. There is still (at this time) a 1 in 4 probability (odds are 1 to 3) that the Republicans will maintain their majority.
Furthermore, 538 presents the 80% confidence interverval: the probability is 80% that the actual numbers will lie within this range. Notice that a Republican majority does lie within this interval.
-
This is the main graphic I'll be checking on in the coming weeks. But the graphic below is interesting, too. It is a map of the Congressional districts and their likelihood that a Democrat or a Republican will be elected from that district.
What I find interesting is that the seats that are predicted to change parties are cross-hatched; it appears that all the districts that are more likely than not to change parties are predicted to change from R to D. At this time, I don't see any changing from D to R. (I'm not counting the one's colored gray as 50/50 toss-ups).
-
Anyway, enjoy.
-
Links and information, I think.
Edited by Chiroptera, : Typo

Oh, God! Pride of Man, broken in the dust again! -- Quicksilver Messenger Service

  
Newer Topic | Older Topic
Jump to:


Copyright 2001-2023 by EvC Forum, All Rights Reserved

™ Version 4.2
Innovative software from Qwixotic © 2024