Reuters/Ipsos: (Most) States
       |           

Welcome, Guest. Please login or register.
Did you miss your activation email?
March 29, 2024, 04:50:01 AM
News: Election Simulator 2.0 Released. Senate/Gubernatorial maps, proportional electoral votes, and more - Read more

  Talk Elections
  Election Archive
  Election Archive
  2016 U.S. Presidential General Election Polls
  Reuters/Ipsos: (Most) States
« previous next »
Pages: 1 2 3 4 5 6 [7] 8 9
Author Topic: Reuters/Ipsos: (Most) States  (Read 14955 times)
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #150 on: September 17, 2016, 09:46:32 AM »

Go to the turnout model and reduce everyone to 0 but Hispanics to 100. I can't do that right now but last time ir showed that there was not enough in the sample to measure for states like NM
Yes, and your point is? Huh

The point is child, that in the past two weeks out of 4,899 respondents, only 162 respondents are Hispanic. That's 3%. That sample isn't accurate enough to give you an accurate national poll, never mind states ones.
Not if you reweigh those Hispanics to the equivalent of your suggested turnout model, which it appears that Reuters has done. So Reuters in essence takes the 162 Hispanics and extrapolates them to the real number which is likely about 400 or so.

Whether they did it on a micro level for each state is the only real question that you have when attempting to reskew these polls.

These numbers fundamentally are fine and in line with most state polls within the margins. Of the four companies doing these 50-state polls (Morning Consult, Google, Survey Monkey and Reuters), the way Reuters is doing it makes the most sense to give you the most up-to-date polls possible.

It's the states with 6 or fewer EVs where you start to run into issues methodologically.
Where can one see Ipsos' crosstabs?
Logged
Dr. Arch
Arch
Atlas Icon
*****
Posts: 12,452
Puerto Rico


Show only this user's posts in this thread
« Reply #151 on: September 17, 2016, 10:34:14 AM »

Wait, they're projecting that Hispanic turnout will go down!? Hah! They're in for a rude awakening.
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #152 on: September 17, 2016, 10:49:19 AM »
« Edited: September 17, 2016, 10:58:29 AM by Little Big Adorable »

Wait, they're projecting that Hispanic turnout will go down!? Hah! They're in for a rude awakening.
You think, Hispanics [and Whites] lie? As far as I know, the answers to the questions ("Will you vote Nov 8?" and "How enthusiastic are you about the election?") are the most important to decide likelihood.

Quote
You must be logged in to read this quote.
Logged
Dr. Arch
Arch
Atlas Icon
*****
Posts: 12,452
Puerto Rico


Show only this user's posts in this thread
« Reply #153 on: September 17, 2016, 10:58:31 AM »
« Edited: September 17, 2016, 11:02:06 AM by Arch »

Wait, they're projecting that Hispanic turnout will go down!? Hah! They're in for a rude awakening.
You think, Hispanics [and Whites] lie? As far as I know, the answers to the questions ("Will you vote Nov 8?" and "How enthusiastic are you about the election?") are the most important to decide likelihood.

Listen, Trump has literally targeted Hispanics with his rhetoric. From my communication with Hispanic leaders all over my state and with friends and family in places like Florida and New York, the sentiment is not that of passing on voting, but on stopping Trump cold. If you think a community that's being threatened at a national level will not turn out more than in times that they weren't, then you don't understand or you just don't want to consider it, plain and simple.

More to consider, polls in places like FL aren't taking into account the large population influx of Puerto Rican Hispanics who vote overwhelmingly D. You can go to the FL poll thread that I elaborated more on this if you want more information.

Lastly, I remember reading on this forum even that Hispanic voter registration has skyrocketed in places like Colorado and Nevada.

The same applies to African-Americans, who have now been reminded of Trump's birtherism once more (those that forgot). Hillary is well-known and trusted among this community, and Obama is on the trail campaigning for her. I doubt voter turnout there will be suppressed much either.

If they project lower turnout in light of all this, they're not going to get a good screen and so their topline numbers and projections will suffer.
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #154 on: September 17, 2016, 11:11:44 AM »

Wait, they're projecting that Hispanic turnout will go down!? Hah! They're in for a rude awakening.
You think, Hispanics [and Whites] lie? As far as I know, the answers to the questions ("Will you vote Nov 8?" and "How enthusiastic are you about the election?") are the most important to decide likelihood.

Listen, Trump has literally targeted Hispanics with his rhetoric. From my communication with Hispanic leaders all over my state and with friends and family in places like Florida and New York, the sentiment is not that of passing on voting, but on stopping Trump cold. If you think a community that's being threatened at a national level will not turn out more than in times that they weren't, then you don't understand or you just don't want to consider it, plain and simple.

More to consider, polls in places like FL aren't taking into account the large population influx of Puerto Rican Hispanics who vote overwhelmingly D. You can go to the FL poll thread that I elaborated more on this if you want more information.

Lastly, I remember reading on this forum even that Hispanic voter registration has skyrocketed in places like Colorado and Nevada.

The same applies to African-Americans, who have now been reminded of Trump's birtherism once more (those that forgot). Hillary is well-known and trusted among this community, and Obama is on the trail campaigning for her. I doubt voter turnout there will be suppressed much either.

If they project lower turnout in light of all this, they're not going to get a good screen and so their topline numbers and projections will suffer.
There are a lot of reasons why turnout among non-white might be lower than 2012. If almost all the polls show [right now] that, why would you not believe them?

They [all pollsters, not just Ipsos] might be wrong, of course, but it is more likely that they are right.
Logged
Ozymandias
Jr. Member
***
Posts: 470


Show only this user's posts in this thread
« Reply #155 on: September 17, 2016, 11:14:33 AM »

These numbers fundamentally are fine and in line with most state polls within the margins. Of the four companies doing these 50-state polls (Morning Consult, Google, Survey Monkey and Reuters), the way Reuters is doing it makes the most sense to give you the most up-to-date polls possible.

How so? I thought Survey Monkey is the one that actually came closest to conducting 50 separate state polls (which is why it has the highest weights at 538)?

And for what it's worth, Survey Monkey is more strongly correlated with the Morning Consult MRP analysis (R=0.94) than with Reuters/Ipsos (R=0.88) or Google (R=0.79).
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #156 on: September 17, 2016, 11:25:39 AM »

http://fivethirtyeight.com/features/the-polls-were-skewed-toward-democrats/

Quote
You must be logged in to read this quote.
Does it sound familiar, Arch?

I am not saying it is the case this year, but pollsters on average are better than conventional wisdom and "Hispanic leaders" (who the hell are they anyway?) Tongue
Logged
‼realJohnEwards‼
MatteKudasai
Jr. Member
***
Posts: 1,867
United States


Political Matrix
E: -6.19, S: -4.87

Show only this user's posts in this thread
« Reply #157 on: September 17, 2016, 11:30:43 AM »

Wait, they're projecting that Hispanic turnout will go down!? Hah! They're in for a rude awakening.
You think, Hispanics [and Whites] lie? As far as I know, the answers to the questions ("Will you vote Nov 8?" and "How enthusiastic are you about the election?") are the most important to decide likelihood.

Listen, Trump has literally targeted Hispanics with his rhetoric. From my communication with Hispanic leaders all over my state and with friends and family in places like Florida and New York, the sentiment is not that of passing on voting, but on stopping Trump cold. If you think a community that's being threatened at a national level will not turn out more than in times that they weren't, then you don't understand or you just don't want to consider it, plain and simple.

More to consider, polls in places like FL aren't taking into account the large population influx of Puerto Rican Hispanics who vote overwhelmingly D. You can go to the FL poll thread that I elaborated more on this if you want more information.

Lastly, I remember reading on this forum even that Hispanic voter registration has skyrocketed in places like Colorado and Nevada.

The same applies to African-Americans, who have now been reminded of Trump's birtherism once more (those that forgot). Hillary is well-known and trusted among this community, and Obama is on the trail campaigning for her. I doubt voter turnout there will be suppressed much either.

If they project lower turnout in light of all this, they're not going to get a good screen and so their topline numbers and projections will suffer.
There are a lot of reasons why turnout among non-white might be lower than 2012. If almost all the polls show [right now] that, why would you not believe them?

They [all pollsters, not just Ipsos] might be wrong, of course, but it is more likely that they are right.
It's not polls which are showing lower turnout, it is Ipsos's weighting scheme.
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #158 on: September 17, 2016, 11:31:53 AM »

It's not polls which are showing lower turnout, it is Ipsos's weighting scheme.
Explain
Logged
Mallow
Jr. Member
***
Posts: 737
United States


Show only this user's posts in this thread
« Reply #159 on: September 17, 2016, 12:29:14 PM »

It's not polls which are showing lower turnout, it is Ipsos's weighting scheme.
Explain

Pollsters re-weight their poll results to match a pre-determined demographic breakdown, which varies from pollster to pollster based on their own assumptions of the race. If they didn't, the raw numbers would be all over the place, since the sample size isn't large enough to capture the proper demographic proportions. This is not the same thing as the "registered" versus "likely" voter issue--that's based on the questions you were discussing earlier, but not the demographic breakdown.

"Unskewing," at least as it pertains to the action often derided here and in political polling circles in general, usually involves saying you don't believe a poll because they didn't sample enough Latinos, or blacks, or something along those lines. That is not the same as what's being done here, which is arguing that the poll's demographic weighting seems unreasonable.
Logged
Seriously?
Sr. Member
****
Posts: 3,029
United States


Show only this user's posts in this thread
« Reply #160 on: September 17, 2016, 01:37:58 PM »
« Edited: September 17, 2016, 01:56:24 PM by Seriously? »

These numbers fundamentally are fine and in line with most state polls within the margins. Of the four companies doing these 50-state polls (Morning Consult, Google, Survey Monkey and Reuters), the way Reuters is doing it makes the most sense to give you the most up-to-date polls possible.

How so? I thought Survey Monkey is the one that actually came closest to conducting 50 separate state polls (which is why it has the highest weights at 538)?

And for what it's worth, Survey Monkey is more strongly correlated with the Morning Consult MRP analysis (R=0.94) than with Reuters/Ipsos (R=0.88) or Google (R=0.79).
It's the staggered releases, which to me makes them more relevant. If the poll is big enough, Reuters releases them over a 1, 2 or 3 week cycle.

Google's samples are 1-week and generally too small in smaller states. Google just balances their samples based on age and gender. They don't even ask any other questions.

Survey Monkey and Morning Consult go over a longer period. (a month), so your snapshot is not as accurate as the race changes over the course of a month.
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #161 on: September 17, 2016, 02:07:18 PM »

Pollsters re-weight their poll results to match a pre-determined demographic breakdown, which varies from pollster to pollster based on their own assumptions of the race. If they didn't, the raw numbers would be all over the place, since the sample size isn't large enough to capture the proper demographic proportions. This is not the same thing as the "registered" versus "likely" voter issue--that's based on the questions you were discussing earlier, but not the demographic breakdown.

"Unskewing," at least as it pertains to the action often derided here and in political polling circles in general, usually involves saying you don't believe a poll because they didn't sample enough Latinos, or blacks, or something along those lines. That is not the same as what's being done here, which is arguing that the poll's demographic weighting seems unreasonable.
Lol, what? 99% of pollsters re-weight RV demographic to match RV Census Bureau statistic. Own assumption LMAO

#uneducatedUnskewersHillary2016
Logged
Ozymandias
Jr. Member
***
Posts: 470


Show only this user's posts in this thread
« Reply #162 on: September 17, 2016, 02:18:20 PM »
« Edited: September 17, 2016, 02:26:43 PM by Ozymandias »

Google's samples are 1-week and generally too small in smaller states. Google just balances their samples based on age and gender. They don't even ask any other questions.

Google doesn't balance by racial demographics?  

Wow, no wonder their polls are so useless...
Logged
Ozymandias
Jr. Member
***
Posts: 470


Show only this user's posts in this thread
« Reply #163 on: September 17, 2016, 02:26:18 PM »
« Edited: September 17, 2016, 02:27:59 PM by Ozymandias »

It's the staggered releases, which to me makes them more relevant. If the poll is big enough, Reuters releases them over a 1, 2 or 3 week cycle.

Google's samples are 1-week and generally too small in smaller states. Google just balances their samples based on age and gender. They don't even ask any other questions.

I can see the argument that 1-week cycles provide a valuable snapshot, but once you get up to two weeks or more, I think a poll loses any value as a "snapshot", which is why I think the much larger Survey Monkey samples are far more relevant for most states.

Also, Reuters/Ipsos only had 1-week windows for 8 states: IL, CA, TX, FL, VA, NY, OH, PA, two of which are clear outliers (CA: C+38, TX: T+23) relative to all the other recent polling.

So I'm VERY dubious that these Reuters/Ipsos polls are providing any useful info at all (though they're not as bad as the Google polls).
Logged
Mallow
Jr. Member
***
Posts: 737
United States


Show only this user's posts in this thread
« Reply #164 on: September 17, 2016, 02:29:37 PM »
« Edited: September 17, 2016, 02:31:12 PM by Mallow »

Pollsters re-weight their poll results to match a pre-determined demographic breakdown, which varies from pollster to pollster based on their own assumptions of the race. If they didn't, the raw numbers would be all over the place, since the sample size isn't large enough to capture the proper demographic proportions. This is not the same thing as the "registered" versus "likely" voter issue--that's based on the questions you were discussing earlier, but not the demographic breakdown.

"Unskewing," at least as it pertains to the action often derided here and in political polling circles in general, usually involves saying you don't believe a poll because they didn't sample enough Latinos, or blacks, or something along those lines. That is not the same as what's being done here, which is arguing that the poll's demographic weighting seems unreasonable.
Lol, what? 99% of pollsters re-weight RV demographic to match RV Census Bureau statistic. Own assumption LMAO

#uneducatedUnskewersHillary2016

I'm talking about the pollsters' demographic turnout breakdown. That being said, I am not sure where I remember reading about that (FiveThirtyEight?), and it's very possible I'm remembering wrong. Memory is a fickle thing. If that's the case, disregard my previous message.

That being said, your attitude is out of line (if I'm wrong, a simple correction would have sufficed). Have a nice election season.
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #165 on: September 17, 2016, 02:51:36 PM »

I'm talking about the pollsters' demographic turnout breakdown.

= LV-model
Logged
Seriously?
Sr. Member
****
Posts: 3,029
United States


Show only this user's posts in this thread
« Reply #166 on: September 17, 2016, 02:56:28 PM »

Google's samples are 1-week and generally too small in smaller states. Google just balances their samples based on age and gender. They don't even ask any other questions.

Google doesn't balance by racial demographics?  

Wow, no wonder their polls are so useless...
It's literally like a 3-4 question poll.. Likelihood to vote, Voter Intention, Gender and Age.
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #167 on: September 17, 2016, 03:15:44 PM »

Google's samples are 1-week and generally too small in smaller states. Google just balances their samples based on age and gender. They don't even ask any other questions.

Google doesn't balance by racial demographics?  

Wow, no wonder their polls are so useless...
It's literally like a 3-4 question poll.. Likelihood to vote, Voter Intention, Gender and Age.

I don't mind any polls, but Google is weird (though it has B rating on 538). One can probably use it apple-to-apple comparison (as 538 does). But... it still is weird...
Logged
NOVA Green
Oregon Progressive
Atlas Icon
*****
Posts: 11,418
United States


Show only this user's posts in this thread
« Reply #168 on: September 17, 2016, 04:29:52 PM »



Reading this correctly, it's Battleground Michigan for all the marbles.

Seriously? Do you have a link so I can pull up the statewide numbers.

As an older man my eyesight isn't nearly as good as it used to be and wanted to be able to update my spreadsheet without squinting. Wink
Logged
Erich Maria Remarque
LittleBigPlanet
YaBB God
*****
Posts: 3,646
Sweden


Show only this user's posts in this thread
« Reply #169 on: September 17, 2016, 04:38:01 PM »

Seriously? Do you have a link so I can pull up the statewide numbers.

As an older man my eyesight isn't nearly as good as it used to be and wanted to be able to update my spreadsheet without squinting. Wink

http://www.reuters.com/statesofthenation/
Logged
NOVA Green
Oregon Progressive
Atlas Icon
*****
Posts: 11,418
United States


Show only this user's posts in this thread
« Reply #170 on: September 17, 2016, 04:53:49 PM »

Seriously? Do you have a link so I can pull up the statewide numbers.

As an older man my eyesight isn't nearly as good as it used to be and wanted to be able to update my spreadsheet without squinting. Wink

http://www.reuters.com/statesofthenation/

Thanks Little Big!

You are absolutely adorable, especially on the polling threads.... Wink
Logged
Wells
MikeWells12
YaBB God
*****
Posts: 4,069
United States


Show only this user's posts in this thread
« Reply #171 on: September 17, 2016, 08:28:08 PM »

Here's the map, if anyone's interested, LOL:



Vermont to the right of both Carolinas? Sure. . .
Logged
Lief 🗽
Lief
Atlas Legend
*****
Posts: 44,876


Show only this user's posts in this thread
« Reply #172 on: September 17, 2016, 08:47:50 PM »

Vermont red, Maine toss-up, NH blue.

Congrats TN Volunteer!!
Logged
The world will shine with light in our nightmare
Just Passion Through
Atlas Legend
*****
Posts: 45,175
Norway


Political Matrix
E: -6.32, S: -7.48

P P P

Show only this user's posts in this thread
« Reply #173 on: September 18, 2016, 12:55:22 AM »

#BattlegroundWyoming

Here's the map, if anyone's interested, LOL:



Vermont to the right of both Carolinas? Sure. . .

Berniebros obvz
Logged
Doimper
Doctor Imperialism
Sr. Member
****
Posts: 3,030


Show only this user's posts in this thread
« Reply #174 on: September 18, 2016, 12:59:09 AM »

Pollsters re-weight their poll results to match a pre-determined demographic breakdown, which varies from pollster to pollster based on their own assumptions of the race. If they didn't, the raw numbers would be all over the place, since the sample size isn't large enough to capture the proper demographic proportions. This is not the same thing as the "registered" versus "likely" voter issue--that's based on the questions you were discussing earlier, but not the demographic breakdown.

"Unskewing," at least as it pertains to the action often derided here and in political polling circles in general, usually involves saying you don't believe a poll because they didn't sample enough Latinos, or blacks, or something along those lines. That is not the same as what's being done here, which is arguing that the poll's demographic weighting seems unreasonable.
Lol, what? 99% of pollsters re-weight RV demographic to match RV Census Bureau statistic. Own assumption LMAO

#uneducatedUnskewersHillary2016

I'm talking about the pollsters' demographic turnout breakdown. That being said, I am not sure where I remember reading about that (FiveThirtyEight?), and it's very possible I'm remembering wrong. Memory is a fickle thing. If that's the case, disregard my previous message.

That being said, your attitude is out of line (if I'm wrong, a simple correction would have sufficed). Have a nice election season.

It would be nice if the moderators enforced some level of civil discourse, wouldn't it?
Logged
Pages: 1 2 3 4 5 6 [7] 8 9  
« 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 0.068 seconds with 14 queries.