Posted on 10/19/2016 6:04:52 PM PDT by 2ndDivisionVet
Over the last decade we’ve witnessed big data tackle issues such as crime, health care, climate change, and even how to select a movie.
So, with the availability of ever-growing collections of political data, more sophisticated statistical analysis techniques, and the ubiquitous presence of social media, it is tempting to think that big data should be able to give us a completely accurate prediction of major votes likes Brexit or the American presidential election.
After all, statistical error decreases with sample size, so with unbounded data at our fingertips, it’s easy to imagine that measurement error will also vanish. Indeed, being overconfident of large sample sizes is one of the most common statistical blunders we see as a big data training company.
History, however, is replete with cautionary tales of being lulled into complacency by the sweet siren call of misapplied statistics. These warnings are not just scattered anecdotes but coalesce into a pattern that reveals both the promise and potential peril of big data.
In 1936, Literary Digest’s poll predicted Republican Governor Alfred Landon of Kansas would win the upcoming presidential election by a landslide. The magazine believed in the irrefutability of its sample size: It had polled 10 million individuals — an astronomical number for any poll. Which made it all the more surprising when the Democratic incumbent, President Franklin Delano Roosevelt, defeated Landon in one of the most lopsided electoral victories in modern American history....
(Excerpt) Read more at techcrunch.com ...
I cannot prove this but I believe there is an additional 3% to 5% of support for The Donald. First, the polls are using a “likely voter” model which excludes those who did not vote in previous elections. Mr Trump has energized a lot of previous apathetic voters who would be excluded by most polling companies as people that won’t vote. I think this effect is particularly strong in the mid-West and places like Pennsylvania. There are a lot of early middle-aged people that have seen their jobs disappear who might not have normally voted. Second I believe the article is right in postulating a sort of “Shy Tory” syndrome. There are a lot of people that support Mr Trump but don’t talk about it because they are afraid of the violence that the democrats visit upon those who offer dissent. Third, an unfocused issue in this campaign is the absolute revulsion many people have for the PC speech codes. Mr Trump’s casual vulgarity is, in many ways refreshing rather than shocking.
Like I said I can’t prove any of what I just wrote. I hope it is not just wishfull thinking.
I cannot prove this but I believe there is an additional 3% to 5% of support for The Donald. First, the polls are using a “likely voter” model which excludes those who did not vote in previous elections. Mr Trump has energized a lot of previous apathetic voters who would be excluded by most polling companies as people that won’t vote. I think this effect is particularly strong in the mid-West and places like Pennsylvania. There are a lot of early middle-aged people that have seen their jobs disappear who might not have normally voted. Second I believe the article is right in postulating a sort of “Shy Tory” syndrome. There are a lot of people that support Mr Trump but don’t talk about it because they are afraid of the violence that the democrats visit upon those who offer dissent. Third, an unfocused issue in this campaign is the absolute revulsion many people have for the PC speech codes. Mr Trump’s casual vulgarity is, in many ways refreshing rather than shocking.
Like I said I can’t prove any of what I just wrote. I hope it is not just wishfull thinking.
I’m seeing three factors that will tend to throw off polls, two of which would suggest that Mr. Trump will do better in the actual election.
First, a blinding flash of the obvious: Donald Trump is not playing the usual game. He demonstrated during the primary season that he can make the approach he is using, work for him, at least some of the time. How well this will translate into the general election, I don’t know. Regardless, it does mean that predictions that are based on the election going as they historically do, are weaker. This one is not going to be orthodox.
Second, given the assaults against people publicly supporting Mr. Trump (both physical and screaming fits directed at their employers), and the vandalism that’s been targeted at anyone supporting him, I consider it a certainty that some of his support has been driven underground. Whenever any poll says that his support is X, it is really (X + (people who don’t want to be mugged)). One problem with this: When someone’s support has been driven partially underground, how do you tell how much there is? I consider it a certainty that Mr. Trump’s support is greater than his supporters are willing to state, but I don’t see any way of telling how much greater.
A third factor making predictions difficult, is the presence of the minor party candidates. In general, as the election nears, some people will change their support from a minor party candidate to someone who might actually win. How much transfer there will be, and to who, I don’t know. I will say that someone who supports a minor candidate will tend not to be someone who likes the political establishment. In this election, Secretary Clinton is running as almost the ultimate establishment candidate, and Mr. Trump is running as close to the ultimate iconoclast. He’s very much the candidate of people who hate the Washington establishment. That suggests that people who support minor candidates are more likely to find him congenial, than to support someone who is that Washington Big-Shot Club’s candidate. But I don’t know how this will break.
I do think that standard methods of predicting election outcomes are weaker in this election, than for any since 1860.
Another possible wild card, but not as disruptive, is that Mr. Trump is actively campaigning, while Secretary Clinton has been avoiding press conferences, and most campaign events, except fund-raisers. I don’t know what effect this will have, but it’s unusual.
I’m seeing three factors that will tend to throw off polls, two of which would suggest that Mr. Trump will do better in the actual election.
First, a blinding flash of the obvious: Donald Trump is not playing the usual game. He demonstrated during the primary season that he can make the approach he is using, work for him, at least some of the time. How well this will translate into the general election, I don’t know. Regardless, it does mean that predictions that are based on the election going as they historically do, are weaker. This one is not going to be orthodox.
Second, given the assaults against people publicly supporting Mr. Trump (both physical and screaming fits directed at their employers), and the vandalism that’s been targeted at anyone supporting him, I consider it a certainty that some of his support has been driven underground. Whenever any poll says that his support is X, it is really (X + (people who don’t want to be mugged)). One problem with this: When someone’s support has been driven partially underground, how do you tell how much there is? I consider it a certainty that Mr. Trump’s support is greater than his supporters are willing to state, but I don’t see any way of telling how much greater.
A third factor making predictions difficult, is the presence of the minor party candidates. In general, as the election nears, some people will change their support from a minor party candidate to someone who might actually win. How much transfer there will be, and to who, I don’t know. I will say that someone who supports a minor candidate will tend not to be someone who likes the political establishment. In this election, Secretary Clinton is running as almost the ultimate establishment candidate, and Mr. Trump is running as close to the ultimate iconoclast. He’s very much the candidate of people who hate the Washington establishment. That suggests that people who support minor candidates are more likely to find him congenial, than to support someone who is that Washington Big-Shot Club’s candidate. But I don’t know how this will break.
I do think that standard methods of predicting election outcomes are weaker in this election, than for any since 1860.
Another possible wild card, but not as disruptive, is that Mr. Trump is actively campaigning, while Secretary Clinton has been avoiding press conferences, and most campaign events, except fund-raisers. I don’t know what effect this will have, but it’s unusual.
A part of the equation is fear. People are fearful of expressing their opinions these days, if their opinions are not left wing and anti-American.
I, too, suspect that Mr. Trump will do better than the polls indicate, for the reasons stated above - he has energized many people that are not on the “likely voter” lists, and many people keep their support of him quiet because of the negative retribution from various libtards. I also believe that it is virtually impossible to obtain a valid statistical sample by telephone polling - you are actually sampling the subset of likely voters that still have landlines and are willing to answer the phone when caller ID indicates it’s nobody they know. Don’t know how this affects the results but I’m guessing that polling companies assume no effect. I know I am not in that subset.
Then there’s the fact that the biased media are skewing the reported polling results to spin a certain Jezebel victory, in an effort to suppress turnout of Trump voters (these are the same corrupt toads that say voter ID suppresses minority voting). So not only is it impossible to get a valid sample, the polling companies in cahoots with the media don’t want one. Our local See-BS station is going with the laughable NBC polls which show Jezebel comfortably in front and almost sure to win a landslide. Anyone who doesn’t read Drudge might conclude that it is indeed over so may as well stay home. I’m hoping that Mr. Trump’s base is smarter than that. I’m also hoping that there is a large group of minority voters that want off the rat plantation and are willing to vote for change.
A part of the equation is fear. People are fearful of expressing their opinions these days, if their opinions are not left wing and anti-American.>>> and fear for family safety and survival is a very strong motivator.
JERUSALEM — “The last polls just days before Israel’s election show Prime Minister Benjamin Netanyahu’s Likud party trailing behind the center-left opposition.”
(Polls taken ahead of the Israeli election mostly agreed with CBS/AP poll on March 13, 2015)
Headline in the NY Times three days later, “Netanyahu Soundly Defeats Chief Rival in Israeli Elections By JODI RUDORENMARCH 17, 2015.
The liberal media pushed, “the polls” to the last minute.
Does anyone see friends/family who are typically Republican saying they will vote for Hillary? I hear a number of elected and formerly elected Republicans saying that, but not normal, everyday people.
Didn’t Hillz have a meltdown backstage after debate #2 wherein she screamed,”If that fascist _____ gets it we all hang!”
There’s plenty of guilt to go around in both parties in or out of office.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.