Jump to content

The definitive work on the oversampling of Ds in the polls.


Recommended Posts

http://www.redstate....obama-is-toast/

It’s hard to make sense of why so many pollsters are showing this as a tight race under these circumstances, with independents consistently breaking heavily to Romney and all the indicators of turnout suggesting at least a much smaller Democratic advantage than 2008 and – if you believe Gallup’s and Rasmussen’s surveys – a Republican wave unlike any we’ve seen in a presidential election in our lifetimes. Bob Krumm notes that the GOP advantage in national polls is directly correlated to how tight their likely-voter screens are; Romney also, for whatever reason, tends to do better in polls with larger samples.

This is interesting....as "smaller" samples implies meddling, to me

But the reasons can await the inevitable mid-November recriminations over what the polls missed and why. The important point is, a D+7 electorate is gone, and it’s not coming back.

This is fact-based, and extensive analysis. If you want to be critical of it, point out where it goes wrong with your own fact-based, extensive analysis. Go ahead and say Nate Silver...and see what I post.

 

Otherwise, accept that I have been right about the oversampling of the polls/idiocy of using 2008 as a model. (Suggestion: you might want to get that out of the way now, rather than waiting for Nov. 7th) The question of turnout reality vs. fantasy is now resolved. (With the caveat that Nevada...is Nevada...so who the F knows?)

 

Next question: what is the O/U on days until Nate Silver's 538 prediction models move away from this D+7 fantasy? Or, when he stops over-weighting polls from 4 weeks ago, and under-weighting polls from yesterday? :rolleyes:

 

And, yes, I know that 538 is the only thing keeping you Ds from a meltdown...but...you might as well disabuse yourselves from Nate now, rather than later, as well.

 

Just sayin'

Edited by OCinBuffalo
Link to comment
Share on other sites

  • Replies 70
  • Created
  • Last Reply

Top Posters In This Topic

Rasmussen's latest Ohio poll shows Romney up 50-48

 

http://www.rasmussenreports.com/public_content/politics/elections/election_2012/election_2012_presidential_election/ohio/election_2012_ohio_president

 

Rasmussen's Electoral Map has Obama up in Nevada, tied in Wisconsin and Iowa, and Romney up in Colorado, Florida, Virginia, and New Hampshire

http://www.rasmussenreports.com/public_content/archive/2012_electoral_college_scoreboard

Link to comment
Share on other sites

This is getting interesting. I was one a while ago that posted I wanted Romney to win, but expected PBO to...

 

Historically, in the tied and real close races, the small percentage of undecided going into election day, break for the challenger.

 

I'm still not going to bet on the RR rodeo, but things look a lot closer than I expected...

Link to comment
Share on other sites

This is getting interesting. I was one a while ago that posted I wanted Romney to win, but expected PBO to...

 

Historically, in the tied and real close races, the small percentage of undecided going into election day, break for the challenger.

 

I'm still not going to bet on the RR rodeo, but things look a lot closer than I expected...

 

If I'm not mistaking wasn't Carter winning by 10 points in the polls just a few weeks before the 1980 election before Reagan caught up and beat him by election day?

 

I have a feeling Obama felt the same way you did going into his first debate. Big mistake on his part. It ain't over till it's over.

Link to comment
Share on other sites

If I'm not mistaking wasn't Carter winning by 10 points in the polls just a few weeks before the 1980 election before Reagan caught up and beat him by election day?

 

I have a feeling Obama felt the same way you did going into his first debate. Big mistake on his part. It ain't over till it's over.

 

Funny you mention the Carter/Reagan election... You see, the Jimmy fiasco of the Iranian hostages are one of the reasons we have problems today in the Mid East. And like Carter, Obama just self destructed on foreign policy. PBOs biggest problem in comparison however is, at least the hostages in Iran came home, alive, after 444 days.

 

Remember... Obama is the incumbent that has humiliated himself, our military, and our country... Not the come from behind kid you hope for...

Link to comment
Share on other sites

If I'm not mistaking wasn't Carter winning by 10 points in the polls just a few weeks before the 1980 election before Reagan caught up and beat him by election day? I have a feeling Obama felt the same way you did going into his first debate. Big mistake on his part. It ain't over till it's over.

No, you aren't mistaken. No, this is not the first time the media has purposely skewed polls in favor of the D incumbent. Ben Bradlee, Washington Post editor, when told that his dishonest polls made Nancy Reagan so nervous about losing California that she demanded money, that would have gone to winning MN(and getting all 50), go to California instead:

 

"Tough sh…t, Rollins, I'm glad it cost you plenty. It's my in-kind contribution to the Mondale campaign." Feel free to google that.

 

So, let's not lie to ourselves about the MSM/Democrats purposely F'ing with polls. It's not new, it's not even that uncommon. In the face of 2010, the obvious mood of the country, 100 other factors, and Holy God himself...today's dishonest/delusional keep using a D+7-8 turnout model, and weighting their samples by that. This is the only thing keeping these polls close.

 

A few months ago, it was used to make the right/independents worried about losing....as it was intended to. The only chance Obama ever had? Making Rs stay home. Now? It's merely making people like Nate Silver embarrass themselves. (See M.D. I'm merely getting warmed up)

Nate Silver....Nate Silver. :w00t: Let 'er rip!

Nate Silver got credit last time for correctly picking 49 of 50 states. If we think about it....it's not that amazing of a feat, without any #s at all. I bet that most of the people on this board could have picked 47-49 states last time, with minimal analysis.

 

But really? The worst kept secret is that the Obama campaign was feeding Silver their data. So, he took the answer, and worked backwards to create models. Viola...his model works. Any # of models could have been produced, and as long as they came out with the same trends/data, they are "right".

 

The raw data for 2012, the makeup of the electorate, is not going to be what it was in 2008. However, OFA is feeding Nate Silver the idiocy that it will be, and demanding that he, and others(Gallup) agree with them...about things like "whites will make up 68%, not 74%, of the overall electorate". :blink:

 

Obama himself recently said: "Should I win a second term, a big reason I will win a second term is because the Republican nominee and the Republican Party have so alienated the fastest-growing demographic group in the country, the Latino community."

 

This ALL goes back to a single, poorly researched book, that claims that the Republican party is going to die...because latinos/blacks/asians will not only overpopulate whites, but that all will vote 80%+ for Democrats. Events have overtaken this book. See here: http://www.realclear...rticles/2012/10/29/changing_demographics_wont_mean_the_end_of_republican_party_115941.html Perhaps we should ask:

Chris Christie what he thinks about Asian voters

Ds why they think treating Latinos...like they have treated blacks...will work

Ds why they think selling unfettered abortion to Latinos will work

Ds why, when many Latinos have risked life and limb to come here to work and become successful, they think those same people are going to want to pay more taxes and/or become dependent on the government. IF they wanted that...they would have stayed home.

 

What we have here is wishful thinking supporting a nonsensical theory. Everything is based on starting with this Latinos Rising theory, and searching for facts to support it. It's the worst sort of selective fact gathering, and this directly informs Nate Silver's poll weighting "methodology". Any poll that shows whites below 70 gets weighted higher than a poll that shows them above 70, because it reflects the "accurate" :rolleyes: electorate.

 

Yeah that's circular reasoning, and confirmation bias.

 

Nothing has changed from 2008....for Silver. He is still using what OFA is feeding him. Too bad for him, this time, it's not even close to being right. It's a delusion. It's a delusion that says Democrats don't have to be accountable for their awful policies, because they can keep marketing themselves to 1st time voters.

 

This is folly, but why should we stop them? Let them ignore the plumbers...and focus on college kids, professors, lawyers and latinos, none of which have the consistent, election after election, voting record of plumbers. Like I said: folly.

Edited by OCinBuffalo
Link to comment
Share on other sites

No, you aren't mistaken. No, this is not the first time the media has purposely skewed polls in favor of the D incumbent. Ben Bradlee, Washington Post editor, when told that his dishonest polls made Nancy Reagan so nervous about losing California that she demanded money, that would have gone to winning MN(and getting all 50), go to California instead:

 

"Tough sh…t, Rollins, I'm glad it cost you plenty. It's my in-kind contribution to the Mondale campaign." Feel free to google that.

 

So, let's not lie to ourselves about the MSM/Democrats purposely F'ing with polls. It's not new, it's not even that uncommon. In the face of 2010, the obvious mood of the country, 100 other factors, and Holy God himself...today's dishonest/delusional keep using a D+7-8 turnout model, and weighting their samples by that. This is the only thing keeping these polls close.

 

A few months ago, it was used to make the right/independents worried about losing....as it was intended to. The only chance Obama ever had? Making Rs stay home. Now? It's merely making people like Nate Silver embarrass themselves. (See M.D. I'm merely getting warmed up)

 

Nate Silver got credit last time for correctly picking 49 of 50 states. If we think about it....it's not that amazing of a feat, without any #s at all. I bet that most of the people on this board could have picked 47-49 states last time, with minimal analysis.

 

But really? The worst kept secret is that the Obama campaign was feeding Silver their data. So, he took the answer, and worked backwards to create models. Viola...his model works. Any # of models could have been produced, and as long as they came out with the same trends/data, they are "right".

 

The raw data for 2012, the makeup of the electorate, is not going to be what it was in 2008. However, OFA is feeding Nate Silver the idiocy that it will be, and demanding that he, and others(Gallup) agree with them...about things like "whites will make up 68%, not 74%, of the overall electorate". :blink:

 

Obama himself recently said: "Should I win a second term, a big reason I will win a second term is because the Republican nominee and the Republican Party have so alienated the fastest-growing demographic group in the country, the Latino community."

 

This ALL goes back to a single, poorly researched book, that claims that the Republican party is going to die...because latinos/blacks/asians will not only overpopulate whites, but that all will vote 80%+ for Democrats. Events have overtaken this book. See here: http://www.realclear...rticles/2012/10/29/changing_demographics_wont_mean_the_end_of_republican_party_115941.html Perhaps we should ask:

Chris Christie what he thinks about Asian voters

Ds why they think treating Latinos...like they have treated blacks...will work

Ds why they think selling unfettered abortion to Latinos will work

Ds why, when many Latinos have risked life and limb to come here to work and become successful, they think those same people are going to want to pay more taxes and/or become dependent on the government. IF they wanted that...they would have stayed home.

 

What we have here is wishful thinking supporting a nonsensical theory. Everything is based on starting with this Latinos Rising theory, and searching for facts to support it. It's the worst sort of selective fact gathering, and this directly informs Nate Silver's poll weighting "methodology". Any poll that shows whites below 70 gets weighted higher than a poll that shows them above 70, because it reflects the "accurate" :rolleyes: electorate.

 

Yeah that's circular reasoning, and confirmation bias.

 

Nothing has changed from 2008....for Silver. He is still using what OFA is feeding him. Too bad for him, this time, it's not even close to being right. It's a delusion. It's a delusion that says Democrats don't have to be accountable for their awful policies, because they can keep marketing themselves to 1st time voters.

 

This is folly, but why should we stop them? Let them ignore the plumbers...and focus on college kids, professors, lawyers and latinos, none of which have the consistent, election after election, voting record of plumbers. Like I said: folly.

 

 

http://washingtonexaminer.com/obama-dispatches-election-lawyers-all-across-the-country/article/2511996#.UI7KkkLdI20

 

 

Ryan, a long-time White House correspondent known for her news-making interviews, also pressed the president on the high joblessness among blacks and Hispanics. The president responded by saying he would focus on "communities of color" in his second term because those two groups are the "future workforce" of America.

But as he has throughout his four years in office, the president said that would be part of a larger effort to put all Americans back to work. He told Ryan: "My target is anybody who is out there, wants to work but doesn't have the skill set to do it. When you look, a lot of those communities are communities of color and we're going to be putting in resources to make sure that we are training those folks up. And, by the way, that's good for America generally. If we don't have black and Hispanic kids who can compete, you know that's the fastest growing population, and that's our future workforce and America will decline economically unless everybody is able to get the opportunities that they deserve."

Link to comment
Share on other sites

http://washingtonexa...96#.UI7KkkLdI20

 

 

Ryan, a long-time White House correspondent known for her news-making interviews, also pressed the president on the high joblessness among blacks and Hispanics. The president responded by saying he would focus on "communities of color" in his second term because those two groups are the "future workforce" of America.

But as he has throughout his four years in office, the president said that would be part of a larger effort to put all Americans back to work. He told Ryan: "My target is anybody who is out there, wants to work but doesn't have the skill set to do it. When you look, a lot of those communities are communities of color and we're going to be putting in resources to make sure that we are training those folks up. And, by the way, that's good for America generally. If we don't have black and Hispanic kids who can compete, you know that's the fastest growing population, and that's our future workforce and America will decline economically unless everybody is able to get the opportunities that they deserve."

See? They are trying to make Latino = Black...when there's no way they have the same history, motivations, or values. Economic status is the only thing the latino community has in common...and not for long if they can get legal.

 

If we can get comprehensive immigration policy done, then, that removes a massive assimilation hindrance from Latinos. There's no reason to believe that they won't follow the path of the Irish, Italians, Polish, Germans, etc. In 2 generations they will have their Ryans, Gulianis....and...oh wait: don't they already have Marco Rubio and Susana Martinez?

 

:lol: It's hysterical that this occupant of the office tries to lump these 2 groups together...it basically tells you all you need to know.

Link to comment
Share on other sites

 

The raw data for 2012, the makeup of the electorate, is not going to be what it was in 2008. However, OFA is feeding Nate Silver the idiocy that it will be, and demanding that he, and others(Gallup) agree with them...about things like "whites will make up 68%, not 74%, of the overall electorate". :blink:

 

 

Nice analysis on the 'whole' issue. I bolded the above sentence as the crux of the matter. In all the 'polling' threads/comments in the last few months.... the issue always seems to boil down to this. Is the bold statement correct or incorrect? I agree with your take but we'll see. Regardless, there is no question that some of the polling has been bizarre.

Link to comment
Share on other sites

I've never been polled by phone before, then today twice within an hour. In one poll I was an elderly Latina voting for Romney and the other a middle aged white guy who has already voted for Obama

All of these nonsense polls, with internals that show a Romney blowout, but with top line Obama leading, are due to trolls like you? Thanks a lot. I've been doing all this analysis since August...and was trolled. :wallbash::lol:

 

Just in case it isn't trolling, and since this thread has "definitive" in the title, here is the definitive work on why Axlerod, and therefore, Nate Silver, who gets all his modeling from Axelrod, is full of it: http://battlegroundw...-turnout-model/

 

My "Nate Silver is full of schit" mendoza line was 68% white voter turnout. Turns out, it should have been at 72%:

National polls often use 74% as the representative White vote in this election, but from a historic stand-point 75% is the more reasonable level which would be a -1.3% decline from 2008. With polls today consistently showing Obama’s support between 36-38% with this segment of the electorate comprising 75% of voters, it is easy to see how a tight race can turn into a blowout rather quickly. As for David Axelrod’s turnout model, he is talking his book when every ounce of data says he blowing smoke. If Axelrod is right on the racial make-up of the electorate, President Obama probably wins re-election in a close race. But there is little evidence that the 76.3% of White voters in 2008 when combined with a probable return of the missing 1.7 million whites will make up only 72% of the electorate Team Obama needs to avoid a sizable Romney win on November 6.

 

:wacko:

 

See? It all goes back to his f'ing book. This entire campaign is based on it. I've never heard of political campaign, whose central thrust is based on: faulty demographic assumptions and political science, and not ideas, achievements, ideology, or vision for the future.

 

It's confounding, really. How pissed are Ds going to be, if they lose/lose big, can lucidly analyze it, and realize that this was never as much about getting Obama re-elected, as it was about trying to twist the facts to suit bad conclusions in a book? :blink: If it ends up being basically Axelrod telling them: "F your ideas, and your guy, this is about me and my book!" Yikes. :o

 

Obama himself has stated it: "Should I win a second term, a big reason I will win a second term is because the Republican nominee and the Republican Party have so alienated the fastest-growing demographic group in the country, the Latino community."

 

So, now we know that Obama has bought Axelrod's model, and Axerod wrote a book, so, of course it's right. :wacko:

Edited by OCinBuffalo
Link to comment
Share on other sites

http://www.cjr.org/swing_states_project/pundits_versus_probabilities.php

 

I guess everyone is wrong...

 

The FiveThirtyEight forecast is not an outlier. Silver’s estimates are generally somewhatmore conservative than the other statistical forecasting models and only moderately more confident in an Obama victory than the betting markets. Whatever objection pundits or conservatives may have is with the state of the publicly available evidence or the way in which forecasters and bettors translate that evidence into probabilities, not with Silver or his methods.
Link to comment
Share on other sites

http://www.redstate....obama-is-toast/

 

This is interesting....as "smaller" samples implies meddling, to me

 

This is fact-based, and extensive analysis. If you want to be critical of it, point out where it goes wrong with your own fact-based, extensive analysis. Go ahead and say Nate Silver...and see what I post.

 

Otherwise, accept that I have been right about the oversampling of the polls/idiocy of using 2008 as a model. (Suggestion: you might want to get that out of the way now, rather than waiting for Nov. 7th) The question of turnout reality vs. fantasy is now resolved. (With the caveat that Nevada...is Nevada...so who the F knows?)

 

Next question: what is the O/U on days until Nate Silver's 538 prediction models move away from this D+7 fantasy? Or, when he stops over-weighting polls from 4 weeks ago, and under-weighting polls from yesterday? :rolleyes:

 

And, yes, I know that 538 is the only thing keeping you Ds from a meltdown...but...you might as well disabuse yourselves from Nate now, rather than later, as well.

 

Just sayin'

 

Nate Silver is first and foremost a statistical analyst. He happens to be a damn good one at that. This means that he goes very far out his way to avoid any sort of "bias" and simply analyze the numbers to the best of his ability. You can disagree with his analysis if you want, you are welcome to. There is a reason so many people trust him though, he's shown to be very accurate in the past elections.

Link to comment
Share on other sites

Look up Silver on the Mass special election for Ted Kennedy's replacement polling. He's a hack that falls in line at the last minute to get his predictions right. He's got one election that my 7 year old grandson could have predicted all 57 states correctly and he missed one.

Link to comment
Share on other sites

Nate Silver is first and foremost a statistical analyst.

 

Karl Rove is first and foremost one of the better political organizers of this generation. Granted he's also a hyper partisan and viewed as the Son of Satan by some. But dude knows how the ground game operates.

 

Silver can work wonders with a sample to derive numbers. But Rove understands where those samples derive from

 

http://online.wsj.com/article/SB10001424052970204846304578090820229096046.html?mod=WSJ_Opinion_LEADTop

Link to comment
Share on other sites

Look up Silver on the Mass special election for Ted Kennedy's replacement polling. He's a hack that falls in line at the last minute to get his predictions right. He's got one election that my 7 year old grandson could have predicted all 57 states correctly and he missed one.

 

His predictions in 2010 were great as well.

 

http://en.wikipedia.org/wiki/FiveThirtyEight#2010_U.S._mid-term_elections

Edited by fjl2nd
Link to comment
Share on other sites

×
×
  • Create New...