Welcome, Guest. Please login or register.
Did you miss your activation email?
February 27, 2020, 12:23:52 am
News: Please delete your old personal messages.

  Atlas Forum
  Election Archive
  Election Archive
  2016 U.S. Presidential General Election Polls
  USC Dornsife/L.A. Times Daybreak National Tracking: 11/7 - Trump +3.2
« previous next »
Pages: 1 ... 15 16 17 18 19 [20] 21 22 23 24 25 ... 30 Print
Author Topic: USC Dornsife/L.A. Times Daybreak National Tracking: 11/7 - Trump +3.2  (Read 63810 times)
Pro-Life Single Issue Voter
ExtremeRepublican
YaBB God
*****
Posts: 7,460


Political Matrix
E: 8.39, S: 7.83

Show only this user's posts in this thread
« Reply #475 on: September 30, 2016, 06:45:56 am »

These tracking polls are at least good to see how the race might be changing before traditional polls are able to capture that shift.
Logged
Panda Express
YaBB God
*****
Posts: 2,149


Show only this user's posts in this thread
« Reply #476 on: September 30, 2016, 07:15:26 am »

My issue with this poll is that it gets included in the RCP everyday. A poll that has the same sample over and over shouldn't be repeatedly put in the RCP.
Logged
Seriously?
YaBB God
*****
Posts: 3,029
United States


Show only this user's posts in this thread
« Reply #477 on: September 30, 2016, 07:45:51 am »

My issue with this poll is that it gets included in the RCP everyday. A poll that has the same sample over and over shouldn't be repeatedly put in the RCP.
Of course it should, with the latest results only, as RCP does. It's not like it's given a disproportional weight.
Logged
Absolution9
Full Member
***
Posts: 132


Show only this user's posts in this thread
« Reply #478 on: September 30, 2016, 08:07:25 am »

My issue with this poll is that it gets included in the RCP everyday. A poll that has the same sample over and over shouldn't be repeatedly put in the RCP.

I think RCP included it because its being sponsored by a major newspaper (it wasn't included under RAND in 2012), otherwise I agree, its a panel poll not a random sample poll.  In 2012 when RAND was running it the result was pretty accurate but its a small sample and they could have just gotten lucky.  In 2012 the cross tabs weren't available, this year they are and look pretty screwy.
Logged
Edu
Ufokart
YaBB God
*****
Posts: 7,278
Argentina


Show only this user's posts in this thread
« Reply #479 on: September 30, 2016, 11:09:27 am »

Logged
Seriously?
YaBB God
*****
Posts: 3,029
United States


Show only this user's posts in this thread
« Reply #480 on: September 30, 2016, 11:36:02 am »
« Edited: September 30, 2016, 11:42:25 am by Seriously? »

Oh thanks. Keep them coming, you hack. I was ultimately correct in my assumption. Ohio finished at +3.

Why don't you post my 2014 posts where I was right and you weren't?
Logged
Gustaf
Moderators
YaBB God
*****
Posts: 29,596


Political Matrix
E: 0.39, S: -0.70

P
Show only this user's posts in this thread
« Reply #481 on: September 30, 2016, 11:52:41 am »

Oh thanks. Keep them coming, you hack. I was ultimately correct in my assumption. Ohio finished at +3.

Why don't you post my 2014 posts where I was right and you weren't?

You're not even trying now. PPP's poll had Obama +5, the result was Obama +3 - well within the margin of error. You're the one who is a deluded hack arguing over the polls now as well as then.

EDIT: Also, how could he post your 2014 posts when no such posts exist? Are you so deluded you forgot you had no posts here for a 4 year period?
Logged
Iosif
YaBB God
*****
Posts: 1,609


Political Matrix
E: -1.68, S: -3.65

Show only this user's posts in this thread
« Reply #482 on: September 30, 2016, 12:05:39 pm »

We should start a support group for Seriously. The next few months are going to be rough for him.
Logged
Seriously?
YaBB God
*****
Posts: 3,029
United States


Show only this user's posts in this thread
« Reply #483 on: September 30, 2016, 01:37:31 pm »

We should start a support group for Seriously. The next few months are going to be rough for him.
They are? Thanks Nostradamus.
Logged
Buh her emails!
diskymike44
YaBB God
*****
Posts: 2,382


Show only this user's posts in this thread
« Reply #484 on: September 30, 2016, 01:37:59 pm »

Trash poll.
Logged
King
intermoderate
YaBB God
*****
Posts: 29,409
United States


Show only this user's posts in this thread
« Reply #485 on: September 30, 2016, 02:30:42 pm »

This is just a huge scheme to get old conservatives to buy subscriptions to the LA Times.
Logged
michelle
MikeWells12
YaBB God
*****
Posts: 3,989
United States


Political Matrix
E: -4.13, S: 0.35

P

Show only this user's posts in this thread
« Reply #486 on: September 30, 2016, 02:42:00 pm »

Anyway, time for the formula! But first, some of Seriously?'s 2014 posts, to be fair:

https://uselectionatlas.org/FORUM/index.php?action=profile;u=9758;sa=showPosts;start=2450

There are a few good ones.

9/29 Trump +8
Trump 47% (+1)
Clinton 39% (-5)
Logged
Joe Republic
YaBB God
*****
Posts: 34,999
Kiribati


Show only this user's posts in this thread
« Reply #487 on: September 30, 2016, 03:07:00 pm »

Why don't you post my 2014 posts where I was right and you weren't?

These literally don't exist.
Logged
Maxwell
mah519
YaBB God
*****
Posts: 28,519
Germany


Political Matrix
E: -6.45, S: -6.96

Show only this user's posts in this thread
« Reply #488 on: September 30, 2016, 03:10:11 pm »

It's pretty hilarious to lie about posting on this forum in 2014.
Logged
Buh her emails!
diskymike44
YaBB God
*****
Posts: 2,382


Show only this user's posts in this thread
« Reply #489 on: September 30, 2016, 07:51:47 pm »

Someone should rename this thread the "the roasting of Seriously"
Logged
Edu
Ufokart
YaBB God
*****
Posts: 7,278
Argentina


Show only this user's posts in this thread
« Reply #490 on: September 30, 2016, 11:13:53 pm »

You're not even trying now. PPP's poll had Obama +5, the result was Obama +3 - well within the margin of error. You're the one who is a deluded hack arguing over the polls now as well as then.

EDIT: Also, how could he post your 2014 posts when no such posts exist? Are you so deluded you forgot you had no posts here for a 4 year period?

Funny thing is that not only he apparently didn't post at all, but I also didn't make any predictions in 2014. Hell, I don't think I even wrote about the election in the whole year. It must be cool living in another dimension like this guy.
Logged
Seriously?
YaBB God
*****
Posts: 3,029
United States


Show only this user's posts in this thread
« Reply #491 on: October 01, 2016, 02:13:13 am »

USC/LA Times national tracking poll (through 9/30) Trump +4.3%
Trump: 46.7% (-0.6%)
Clinton: 42.3% (+0.6%)
Logged
Smeulders
Newbie
*
Posts: 15
Belgium


Show only this user's posts in this thread
« Reply #492 on: October 01, 2016, 12:50:44 pm »

I've been following the discussion about this tracking poll for a bit and so far I've mostly followed the 538 opinion. This poll is useful as long as you use it to track trends, not as an accurate indicator of the race. However, today inspired by "the formula" I've been thinking about what the daily fluctuations of this poll can tell us. Looking at these, it appears that this poll is very elastic, likely exaggerating swings in both directions. (Apologies if anyone remarked on this previously, I didn't read through the complete thread yet.)

Let's take a look at today's numbers. Today the results are C:42.3%, T:46.7%. Yesterday it was C:41.7%, T:47.3%. Assuming that the "daily cohorts" are all of an equal size, we see the following:
x_{t-7} / 7 + (6/7)y = 41.7%
x_t / 7 + (6/7)y = 42.3%
with x_t the % Clinton supporters in the Saturday cohort today, x_{t-7} the % Clinton supports in the Saturday cohort last week and y the % Clinton supports in the other cohorts polled over the previous 6 days.

Solving this (and doing the same for Trump) we see that among the Saturday cohort, there has been a massive 8.4 percentage point swing for Clinton over the last week. Doing the same for the Friday cohort, there has been an even larger 11.2 percentage point swing for Trump. In fact, during September there have been 7 swings of over 10 points (including one 23.1 points swing) among daily cohorts in a weeks time. Even though the daily cohorts are fairly small and have high MOE, such regular large swings should probably be much rarer.

The methodology of this poll can explain the elasticity. Remember that this poll weights based on self-reported likelihood to vote. Good or bad news for a candidate thus doesn't only influence the amount of supporters, but through increased enthusiasm further amplifies swings.
Logged
Alcon
YaBB God
*****
Posts: 30,909
United States


Show only this user's posts in this thread
« Reply #493 on: October 01, 2016, 12:52:32 pm »

Great post, Smeulders -- welcome to the forum! Smiley
Logged
cinyc
YaBB God
*****
Posts: 12,000


Show only this user's posts in this thread
« Reply #494 on: October 02, 2016, 02:19:31 am »

USC/LA Times national tracking poll (through 10/1) Trump +4.7%
Trump: 46.9% (+0.2)
Clinton: 42.2% (-0.1)
Logged
cp
YaBB God
*****
Posts: 1,145
United Kingdom


Show only this user's posts in this thread
« Reply #495 on: October 02, 2016, 03:21:28 am »

I've been following the discussion about this tracking poll for a bit and so far I've mostly followed the 538 opinion. This poll is useful as long as you use it to track trends, not as an accurate indicator of the race. However, today inspired by "the formula" I've been thinking about what the daily fluctuations of this poll can tell us. Looking at these, it appears that this poll is very elastic, likely exaggerating swings in both directions. (Apologies if anyone remarked on this previously, I didn't read through the complete thread yet.)

Let's take a look at today's numbers. Today the results are C:42.3%, T:46.7%. Yesterday it was C:41.7%, T:47.3%. Assuming that the "daily cohorts" are all of an equal size, we see the following:
x_{t-7} / 7 + (6/7)y = 41.7%
x_t / 7 + (6/7)y = 42.3%
with x_t the % Clinton supporters in the Saturday cohort today, x_{t-7} the % Clinton supports in the Saturday cohort last week and y the % Clinton supports in the other cohorts polled over the previous 6 days.

Solving this (and doing the same for Trump) we see that among the Saturday cohort, there has been a massive 8.4 percentage point swing for Clinton over the last week. Doing the same for the Friday cohort, there has been an even larger 11.2 percentage point swing for Trump. In fact, during September there have been 7 swings of over 10 points (including one 23.1 points swing) among daily cohorts in a weeks time. Even though the daily cohorts are fairly small and have high MOE, such regular large swings should probably be much rarer.

The methodology of this poll can explain the elasticity. Remember that this poll weights based on self-reported likelihood to vote. Good or bad news for a candidate thus doesn't only influence the amount of supporters, but through increased enthusiasm further amplifies swings.

Great analysis! From my non-mathematical lay observations I've noticed that the poll seems to lag about a week behind the consensus of other pollsters/trackers. That said, I've been getting more skeptical of the underlying methodology (self-reporting, only using 2012 voters).

Also, for those of us who also don't have the time to read through the entire threat, could someone (re)explain the 'formula' and how it comes to its parallel numbers each day? Smiley
Logged
michelle
MikeWells12
YaBB God
*****
Posts: 3,989
United States


Political Matrix
E: -4.13, S: 0.35

P

Show only this user's posts in this thread
« Reply #496 on: October 02, 2016, 08:08:16 am »

8/1 Trump +6
Trump 48%
Clinton 42%
Logged
Trends are real, and I f**king hate it
Antonio V
YaBB God
*****
Posts: 51,301
United States


Political Matrix
E: -7.87, S: -3.83


Show only this user's posts in this thread
« Reply #497 on: October 02, 2016, 10:00:58 am »

Why are trackers the only polls that show Drumpf ahead?
Logged
skoods
YaBB God
*****
Posts: 537
United States


Show only this user's posts in this thread
« Reply #498 on: October 02, 2016, 10:38:54 am »

Why are trackers the only polls that show Drumpf ahead?

The same reason Rasmussen tracking and Gallup tracking were the only ones that showed Romney ahead in the final polls before the 2012 election.
Logged
ApatheticAustrian
ApathicAustrian
YaBB God
*****
Posts: 6,613
Austria


Show only this user's posts in this thread
« Reply #499 on: October 02, 2016, 10:50:34 am »

i guess those are the least "adjusted for reality" and must mostly stick with their chosen way/sample.
Logged
Pages: 1 ... 15 16 17 18 19 [20] 21 22 23 24 25 ... 30 Print 
« previous next »
Jump to:  


Login with username, password and session length
Logout

Terms of Service - DMCA Agent and Policy - Privacy Policy and Cookies

Powered by SMF 1.1.21 | SMF © 2015, Simple Machines

© Dave Leip's Atlas of U.S. Elections, LLC