CBS News / YouGov: Braun +3 (IN), Sinema +3 (AZ), Tied in FL
       |           

Welcome, Guest. Please login or register.
Did you miss your activation email?
March 28, 2024, 05:42:30 AM
News: Election Simulator 2.0 Released. Senate/Gubernatorial maps, proportional electoral votes, and more - Read more

  Talk Elections
  Election Archive
  Election Archive
  2018 Senatorial Election Polls
  CBS News / YouGov: Braun +3 (IN), Sinema +3 (AZ), Tied in FL
« previous next »
Pages: 1 [2] 3 4
Author Topic: CBS News / YouGov: Braun +3 (IN), Sinema +3 (AZ), Tied in FL  (Read 5299 times)
Aurelio21
Rookie
**
Posts: 131
Germany


Show only this user's posts in this thread
« Reply #25 on: October 28, 2018, 10:51:56 AM »


Why would you think 12% might be too high for the 18-29 cohort?  If anything, it seems too low to me.
 
According to exit polls in Florida, 18-29 constituted 14% of the electorate in 2014 and 17% of the electorate in 2016.  And Florida is older than the average state.  I couldn't find exist polls in IN for 2016 or 2014, but in a 2012 exit poll, the IN electorate was 20% 18-29.


FWIW, the exit polls have long been known to over-sample college graduates.

That being said, midterm elections are exactly when college graduates would punch over their weight. Working class voters tend to experience a dropoff in midterms.

Basically I agree with this take than rather plainly saying "YouGov is a junk pollster". Yet this poll does not reveal its weighting. The WWC-class voters who agree that the Democrats are abondening their own country for migrants might be motivated by the "Caravan / FoxNews"-scare. Who knows.
Mr Braun does this good as he keeps his mouth shut thus leaving enough projectional potential for the WWC.
It is up to Mr Donelly to reconnect emotionally with these voters via an protectionist message / displaying himself as better leader for their needs.(Hint: Calling Mr Trump a liar does not get through to these disappointed Democrats and Independents open to economic populism).
Logged
Aurelio21
Rookie
**
Posts: 131
Germany


Show only this user's posts in this thread
« Reply #26 on: October 28, 2018, 10:56:20 AM »

Are we really dissecting YouGov crosstabs guys

Yes, we should not find their flaws within their methology. We must indulge into our own confirmation bias! I want to believe.

Honestly, this is the only sense I can make out of a poll with 8 % undecided voters 9 days before a pivotal election. I hate this political spining loaded with false equivalencies and What-Aboutisms
Logged
DataGuy
Rookie
**
Posts: 217


Show only this user's posts in this thread
« Reply #27 on: October 28, 2018, 11:04:37 AM »

YouGov is a terrible pollster. Don’t take seriously

It seems to me that pretty much every pollster is "terrible" according to this forum.

In reality, YouGov is B-rated pollster with a mean-reverted bias of only D+0.3 over 375 polls analyzed. That is not bad at all.

The fact is that pollsters aren't necessarily bad just because they don't come up with your desired outcome. They aren't necessarily bad just because they don't show the same results the herd is showing. Oftentimes, a so-called "outlier" poll ends up being the one that nails the result.

And don't forget the margin of error. In Indiana, which I presume is the least popular result of the three, the MOE is +/- 3.7%. So even though it's Braun +3 on the surface, it's actually telling you that it considers plausible any result from Donnelly +4.4 to Braun +10.4. If, in the end, Donnelly ekes out a narrow victory, you cannot call this poll "wrong," because it anticipated that result within its range of likely outcomes. A poll is only truly wrong if the result ends up being outside its margin of error, like Donnelly +6.

In fact, people should stop obsessing over topline results and instead think of polls as presenting a range of possibilities. Had that been done in 2016, we would have seen that Hillary was not quite as inevitable as she appeared on the surface.
Logged
UWS
Junior Chimp
*****
Posts: 5,220


Show only this user's posts in this thread
« Reply #28 on: October 28, 2018, 11:07:03 AM »

When it comes to Arizona, this poll is not quite accurate because according to OH Predictive Insights, the Republicans are ahead by 94 000 votes overall in Arizona in the early vote.
Logged
Gass3268
Moderators
Atlas Star
*****
Posts: 27,478
United States


Show only this user's posts in this thread
« Reply #29 on: October 28, 2018, 11:10:20 AM »


538 has YouGov with a house effect of R+2.4.  So the adjusted values they're using are Braun+0.6, Nelson+2.4, and Sinema+5.4, which seem closer to CW.

YouGov has a R+2.4 house effect.
Logged
ON Progressive
OntarioProgressive
Junior Chimp
*****
Posts: 6,106
Canada


Political Matrix
E: -6.06, S: -8.70

Show only this user's posts in this thread
« Reply #30 on: October 28, 2018, 11:10:34 AM »

When it comes to Arizona, this poll is not quite accurate because according to OH Predictive Insights, the Republicans are ahead by 94 000 votes overall in Arizona in the early vote.

That’s based off party registration though. There are a lot of registered Rs that are open to voting D in AZ. GOP had a 20+ percent lead in registration in AZ-08’s special but Lesko only won by 5.
Logged
DataGuy
Rookie
**
Posts: 217


Show only this user's posts in this thread
« Reply #31 on: October 28, 2018, 11:11:31 AM »

Are we really dissecting YouGov crosstabs guys

Yes, we should not find their flaws within their methology. We must indulge into our own confirmation bias! I want to believe.

Honestly, this is the only sense I can make out of a poll with 8 % undecided voters 9 days before a pivotal election. I hate this political spining loaded with false equivalencies and What-Aboutisms

It's poor practice to attempt to discredit polls based on their crosstabs. The crosstabs always have much larger margins of error than the poll in general and were never really meant to considered accurate in the first place. You might be correct in saying that a certain crosstab is wrong, but that really proves nothing about the poll overall because errors in the other crosstabs might counteract it and balance things out.
Logged
Aurelio21
Rookie
**
Posts: 131
Germany


Show only this user's posts in this thread
« Reply #32 on: October 28, 2018, 11:13:44 AM »

When it comes to Arizona, this poll is not quite accurate because according to OH Predictive Insights, the Republicans are ahead by 94 000 votes overall in Arizona in the early vote.

.. and omitting totally that the YouGov poll has taken this into account, But please, continue spinning the results into your personal confirmation bias.
Logged
KingSweden
Atlas Icon
*****
Posts: 11,227
United States


Show only this user's posts in this thread
« Reply #33 on: October 28, 2018, 11:14:31 AM »

Are we really dissecting YouGov crosstabs guys

Yes, we should not find their flaws within their methology. We must indulge into our own confirmation bias! I want to believe.

Honestly, this is the only sense I can make out of a poll with 8 % undecided voters 9 days before a pivotal election. I hate this political spining loaded with false equivalencies and What-Aboutisms

It's poor practice to attempt to discredit polls based on their crosstabs. The crosstabs always have much larger margins of error than the poll in general and were never really meant to considered accurate in the first place. You might be correct in saying that a certain crosstab is wrong, but that really proves nothing about the poll overall because errors in the other crosstabs might counteract it and balance things out.

Right, and I’m leery about Internet polls to begin with, which is why wandering into their crosstabs strikes me as a fools errand
Logged
Former Dean Phillips Supporters for Haley (I guess???!?) 👁️
The Impartial Spectator
Junior Chimp
*****
Posts: 7,761


Show only this user's posts in this thread
« Reply #34 on: October 28, 2018, 11:17:54 AM »

It seems to me that pretty much every pollster is "terrible" according to this forum.

In reality, YouGov is B-rated pollster with a mean-reverted bias of only D+0.3 over 375 polls analyzed. That is not bad at all.

I could make up numbers close to the polling averages of other firms and be a B-rated pollster.

I think the main reason why YouGov, and a lot of other pollsters are criticized as being "terrible" ("not the best" would probably be a better and fairer way to put it) is not so much just a matter of pollster rating, but their methodology. YouGov is an online pollster, and despite online polling having been around for several cycles at this point, it remains less proven and less trusted/accurate methodologically than live phone polling. The same can be said for IVR/Robopollsters. Of course, with each passing year, live phone polling becomes a bit more suspect as well as response rates constantly go down, though so far live phone polls' accuracy seem to usually have not been hurt too much by this.



Anyway, these are not good polls for Dems. The only optimistic take for Dems on them is that maybe they are wrong, and the chances that they are wrong are a bit higher for YouGov than the chances that some other pollster would be wrong.

But hoping that maybe the polls are wrong is never where you want to be.

The better thing to hope (for Dems) is that maybe when we get out of this damn polling desert, we'll get some polls from other pollsters like CNN and FOX that do live phone polls, and hopefully those will be better.
Logged
Aurelio21
Rookie
**
Posts: 131
Germany


Show only this user's posts in this thread
« Reply #35 on: October 28, 2018, 11:20:30 AM »
« Edited: October 28, 2018, 11:28:36 AM by Aurelio21 »

Are we really dissecting YouGov crosstabs guys

Yes, we should not find their flaws within their methology. We must indulge into our own confirmation bias! I want to believe.

Honestly, this is the only sense I can make out of a poll with 8 % undecided voters 9 days before a pivotal election. I hate this political spining loaded with false equivalencies and What-Aboutisms

It's poor practice to attempt to discredit polls based on their crosstabs. The crosstabs always have much larger margins of error than the poll in general and were never really meant to considered accurate in the first place. You might be correct in saying that a certain crosstab is wrong, but that really proves nothing about the poll overall because errors in the other crosstabs might counteract it and balance things out.


@DataGuy: My post was a hyperbole/sarcasm to those on both sides who discard polls which do not please them. I totally agree with you about technical terms of statistics need to be understood and applied to a poll.

My premise is that you only could directly discard a poll via crosstabs if it would fail more sophisticated testing like student t-Test, but pollsters usually do not repeat their poll until they have a relative standard deviation. And they cannot admit their own mean-reverted biases / accuracy and precision flaws themselves.

I find these crosstabs interesting under the sociological view of the voter coalitions of each candidate relative to their state.
Logged
Hindsight was 2020
Hindsight is 2020
Atlas Icon
*****
Posts: 13,196
United States


Show only this user's posts in this thread
« Reply #36 on: October 28, 2018, 11:22:47 AM »

This might sound weird but I’m actually feeling a lot better after this poll. I’ve been mr. Doom and gloom lately because I thought Sinema was crashing and burning and the possibility that we didn’t pick up either NV and AZ while losing IN, ND, and MO had me bummed. But NV is looking good and there is now too much smoke to dismiss the possibility Sinema is winning 8-10% of reps rendering the EV #’s useless. Also winning NV and AZ while losing ND, IN, and having either a wash or R +1 come down to MO is fine with me
Logged
IceSpear
Atlas Superstar
*****
Posts: 31,841
United States


Political Matrix
E: -6.19, S: -6.43

Show only this user's posts in this thread
« Reply #37 on: October 28, 2018, 11:33:19 AM »

This might sound weird but I’m actually feeling a lot better after this poll. I’ve been mr. Doom and gloom lately because I thought Sinema was crashing and burning and the possibility that we didn’t pick up either NV and AZ while losing IN, ND, and MO had me bummed. But NV is looking good and there is now too much smoke to dismiss the possibility Sinema is winning 8-10% of reps rendering the EV #’s useless. Also winning NV and AZ while losing ND, IN, and having either a wash or R +1 come down to MO is fine with me

I think people think they're horrible polls because they were for some reason convinced that Indiana was a likely D race (muh ancient junk polls, muh infallible Nate Silver.)
Logged
Former Dean Phillips Supporters for Haley (I guess???!?) 👁️
The Impartial Spectator
Junior Chimp
*****
Posts: 7,761


Show only this user's posts in this thread
« Reply #38 on: October 28, 2018, 11:41:46 AM »

This might sound weird but I’m actually feeling a lot better after this poll. I’ve been mr. Doom and gloom lately because I thought Sinema was crashing and burning and the possibility that we didn’t pick up either NV and AZ while losing IN, ND, and MO had me bummed. But NV is looking good and there is now too much smoke to dismiss the possibility Sinema is winning 8-10% of reps rendering the EV #’s useless. Also winning NV and AZ while losing ND, IN, and having either a wash or R +1 come down to MO is fine with me

I think people think they're horrible polls because they were for some reason convinced that Indiana was a likely D race (muh ancient junk polls, muh infallible Nate Silver.)

Likely D would be exaggerated, but Tilt D is (or at least would have been) probably fair. Donnelly has led (by small amounts) in most polls.

The main thing Braun has going for him is IN's partisan lean. I am afraid - and more so after this YouGov poll, that enough of the undecideds break to him for IN to be an R pickup.
Logged
IceSpear
Atlas Superstar
*****
Posts: 31,841
United States


Political Matrix
E: -6.19, S: -6.43

Show only this user's posts in this thread
« Reply #39 on: October 28, 2018, 11:43:28 AM »

This might sound weird but I’m actually feeling a lot better after this poll. I’ve been mr. Doom and gloom lately because I thought Sinema was crashing and burning and the possibility that we didn’t pick up either NV and AZ while losing IN, ND, and MO had me bummed. But NV is looking good and there is now too much smoke to dismiss the possibility Sinema is winning 8-10% of reps rendering the EV #’s useless. Also winning NV and AZ while losing ND, IN, and having either a wash or R +1 come down to MO is fine with me

I think people think they're horrible polls because they were for some reason convinced that Indiana was a likely D race (muh ancient junk polls, muh infallible Nate Silver.)

Likely D would be exaggerated, but Tilt D is (or at least would have been) probably fair. Donnelly has led (by small amounts) in most polls.

The main thing Braun has going for him is IN's partisan lean. I am afraid - and more so after this YouGov poll, that enough of the undecideds break to him for IN to be an R pickup.

538's junk model unironically had Indiana at likely D until today, with Heitkamp having a higher chance than Braun, lol. Now it is a mere lean D.
Logged
Former Dean Phillips Supporters for Haley (I guess???!?) 👁️
The Impartial Spectator
Junior Chimp
*****
Posts: 7,761


Show only this user's posts in this thread
« Reply #40 on: October 28, 2018, 11:45:26 AM »

538's junk model unironically had Indiana at likely D until today, with Heitkamp having a higher chance than Braun, lol. Now it is a mere lean D.

Yeah, that is pretty stupid. I don't even look at the 538 Senate model any more.
Logged
Dr Oz Lost Party!
PittsburghSteel
Atlas Icon
*****
Posts: 14,931
United States


P P
Show only this user's posts in this thread
« Reply #41 on: October 28, 2018, 11:46:16 AM »

When it comes to Arizona, this poll is not quite accurate because according to OH Predictive Insights, the Republicans are ahead by 94 000 votes overall in Arizona in the early vote.

That’s based off party registration though. There are a lot of registered Rs that are open to voting D in AZ. GOP had a 20+ percent lead in registration in AZ-08’s special but Lesko only won by 5.

Wasn’t it estimated that Hiral Tipirneni won at least 20% of the Republican vote in the 6th special election?
Logged
2016
Junior Chimp
*****
Posts: 7,303


Show only this user's posts in this thread
« Reply #42 on: October 28, 2018, 11:51:29 AM »

McSally at 84% of Republicans but she leads Indies 46-43. That's enough to disqualify that AZ Poll. McSally ain't going to win Independent Voters and neither will she get only 84% of Republicans. This is garbarge.
Logged
Pollster
YaBB God
*****
Posts: 3,756


Show only this user's posts in this thread
« Reply #43 on: October 28, 2018, 11:59:56 AM »

Bizarre Indiana toplines...YouGov is projecting incredibly low AA turnout and incredibly high turnout among voters with HS or less educational attainment.
Logged
2016
Junior Chimp
*****
Posts: 7,303


Show only this user's posts in this thread
« Reply #44 on: October 28, 2018, 12:08:06 PM »

Democrats need all 3 Races. If they lose IN early in the Night it's over.
Logged
DataGuy
Rookie
**
Posts: 217


Show only this user's posts in this thread
« Reply #45 on: October 28, 2018, 01:10:25 PM »

It's not really fair to immediately trash 538's model just because Braun has taken a small lead in a handful of recent polls. Data-driven models are intentionally cautious in reacting to new polling data. They are meant to have an element of stability based on other factors independent of polling, such as fundamentals (although it's fair to debate what should actually count as a fundamental).

A very clear trend over several credible polls is required to counteract those fundamentals. It's a feature, not a bug. If your probabilities swing wildly with each new poll, you don't really have a model. You have just a regular polling average, and a very noisy one at that. Even most ordinary polling averages collect polls over an extended period of time to minimize statistical noise.

YouGov is the first non-partisan pollster in a long time to show Braun ahead, so any expectation that the models will swing dramatically just of because of that is absolutely unrealistic and uninformed.
Logged
Zaybay
Junior Chimp
*****
Posts: 6,076
United States


Political Matrix
E: -7.25, S: -6.50

Show only this user's posts in this thread
« Reply #46 on: October 28, 2018, 01:21:41 PM »

It's not really fair to immediately trash 538's model just because Braun has taken a small lead in a handful of recent polls. Data-driven models are intentionally cautious in reacting to new polling data. They are meant to have an element of stability based on other factors independent of polling, such as fundamentals (although it's fair to debate what should actually count as a fundamental).

A very clear trend over several credible polls is required to counteract those fundamentals. It's a feature, not a bug. If your probabilities swing wildly with each new poll, you don't really have a model. You have just a regular polling average, and a very noisy one at that. Even most ordinary polling averages collect polls over an extended period of time to minimize statistical noise.

YouGov is the first non-partisan pollster in a long time to show Braun ahead, so any expectation that the models will swing dramatically just of because of that is absolutely unrealistic and uninformed.

This is the correct take right here.

Logged
Zaybay
Junior Chimp
*****
Posts: 6,076
United States


Political Matrix
E: -7.25, S: -6.50

Show only this user's posts in this thread
« Reply #47 on: October 28, 2018, 01:26:30 PM »

Gonna be honest, when I heard YouGov was gonna release some polls, I thought AZ would be R, IN would be R and FL would be a tie/a tiny bit D. I was surprised, but not in the way I thought I would be.

My reasoning for this was because, and this is important, YouGov is an online pollster. Their polls are not really that great put next to Fox, Q, Monmouth or other live callers/interviewers. Because of this, its likely they will get odd results, as other online pollsters(such as Ipsos) have gotten.

Its funny, looking at Ipsos and YouGov, both are really the inverse of each other. Ipsos constantly overestimates D chances, but has also been rather swingy, having them lead by 15 one day and 2 by the next. YouGov, however, constantly underestimate D chances, but is much more static(insert every GCB poll YouGov has done).

Anyway, its a datapoint, but not one to treat as the end of the world, and that goes for both sides.

But if there is one thing to discount, its that FL poll, that thing is complete and utter garbage.
Logged
2016
Junior Chimp
*****
Posts: 7,303


Show only this user's posts in this thread
« Reply #48 on: October 28, 2018, 01:36:34 PM »

It's not really fair to immediately trash 538's model just because Braun has taken a small lead in a handful of recent polls. Data-driven models are intentionally cautious in reacting to new polling data. They are meant to have an element of stability based on other factors independent of polling, such as fundamentals (although it's fair to debate what should actually count as a fundamental).

A very clear trend over several credible polls is required to counteract those fundamentals. It's a feature, not a bug. If your probabilities swing wildly with each new poll, you don't really have a model. You have just a regular polling average, and a very noisy one at that. Even most ordinary polling averages collect polls over an extended period of time to minimize statistical noise.

YouGov is the first non-partisan pollster in a long time to show Braun ahead, so any expectation that the models will swing dramatically just of because of that is absolutely unrealistic and uninformed.

Actually it doesn't matter if Braun or Donnelly is ahead. Republicans have locked up the Senate. ND is GONE, Missouri is now leaning their way. Getting IN would only be the icing on the cake and would spare us Political Junkies of a long Night.
Logged
IceSpear
Atlas Superstar
*****
Posts: 31,841
United States


Political Matrix
E: -6.19, S: -6.43

Show only this user's posts in this thread
« Reply #49 on: October 28, 2018, 01:43:00 PM »

It's not really fair to immediately trash 538's model just because Braun has taken a small lead in a handful of recent polls. Data-driven models are intentionally cautious in reacting to new polling data. They are meant to have an element of stability based on other factors independent of polling, such as fundamentals (although it's fair to debate what should actually count as a fundamental).

A very clear trend over several credible polls is required to counteract those fundamentals. It's a feature, not a bug. If your probabilities swing wildly with each new poll, you don't really have a model. You have just a regular polling average, and a very noisy one at that. Even most ordinary polling averages collect polls over an extended period of time to minimize statistical noise.

YouGov is the first non-partisan pollster in a long time to show Braun ahead, so any expectation that the models will swing dramatically just of because of that is absolutely unrealistic and uninformed.

The problem is that having it at "likely D" at any point was completely ludicrous.
Logged
Pages: 1 [2] 3 4  
« previous next »
Jump to:  


Login with username, password and session length

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

Powered by SMF 1.1.21 | SMF © 2015, Simple Machines

Page created in 0.06 seconds with 14 queries.