The media's biggest 2016 mistake: over-certainty about the data.
Excellent Nate Silver piece on the media's (and my personal) biggest 2016 mistake: over-certainty about the data.
Link to tweet
The Media Has A Probability Problem
The medias demand for certainty and its lack of statistical rigor is a bad match for our complex world.
By Nate Silver
Filed under The Real Story Of 2016
This is the 11th and final article in a series that reviews news coverage of the 2016 general election, explores how Donald Trump won and why his chances were underrated by most of the American media.
....
The media keeps misinterpreting data and then blaming the data
You wont be surprised to learn that I see a lot of similarities between hurricane forecasting and election forecasting and between the medias coverage of Irma and its coverage of the 2016 campaign. In recent elections, the media has often overestimated the precision of polling, cherry-picked data and portrayed elections as sure things when that conclusion very much wasnt supported by polls or other empirical evidence.
As Ive documented throughout this series, polls and other data did not support the exceptionally high degree of confidence that news organizations such as The New York Times regularly expressed about Hillary Clintons chances. (Weve been using the Times as our case study throughout this series, both because theyre such an important journalistic institution and because their 2016 coverage had so many problems.) On the contrary, the more carefully one looked at the polling, the more reason there was to think that Clinton might not close the deal. In contrast to President Obama, who overperformed in the Electoral College relative to the popular vote in 2012, Clintons coalition (which relied heavily on urban, college-educated voters) was poorly configured for the Electoral College. In contrast to 2012, when hardly any voters were undecided between Obama and Mitt Romney, about 14 percent of voters went into the final week of the 2016 campaign undecided about their vote or saying they planned to vote for a third-party candidate. And in contrast to 2012, when polls were exceptionally stable, they were fairly volatile in 2016, with several swings back and forth between Clinton and Trump including the final major swing of the campaign (after former FBI Director James Comeys letter to Congress), which favored Trump.
By Election Day, Clinton simply wasnt all that much of a favorite; she had about a 70 percent chance of winning according to FiveThirtyEights forecast, as compared to 30 percent for Trump. Even a 2- or 3-point polling error in Trumps favor about as much as polls had missed on average, historically would likely be enough to tip the Electoral College to him. While many things about the 2016 election were surprising, the fact that Trump narrowly won (1) when polls had him narrowly trailing was an utterly routine and unremarkable occurrence. The outcome was well within the cone of uncertainty, so to speak.
....
(1) https://fivethirtyeight.com/features/the-media-has-a-probability-problem/amp/
Skittles
(153,169 posts)and the media's skewed attention to that orange buffoon was unprecedented in a presidential election
zipplewrath
(16,646 posts)People don't really understand probability or percentages. Even a 70% chance of winning an election means roughly speaking that you win 2 out of 3 times. The third time you lose. There aren't many things that you would bet on if the stakes were high when you could lose 2 out of 3 times. But yet people interpret 70% as "near certain". Furthermore, there's something known as "statistically significant" which for simple systems is a sample size of like 35 or so. Probability means nothing for an individual event, and very little for samples of 3, 4, 5, etc. What Nate is trying to explain is that there is WAY more to his analysis than one number. Most people don't know there is a difference between precision and accuracy. Precision is getting the SAME answer. Accuracy is getting the RIGHT number. His polls, while precise, don't have nearly the same level of accuracy.
He was trying to explain too, right up until the end, that the magnitude of the "undecided" was so large, that depending upon how they "split", it could make the difference in the whole election. And that's exactly what happened. In the right 4 states, JUST enough people voted the "wrong" way to result in a shift in the outcome. They do analysis at 538 where they change the polling data just a "little" and see what difference it makes (it's sometimes called a "Monte Carlo" analysis). And as he tries to present, small changes in the polling data resulted in huge changes in outcome. Think about a marble on a "flat" table. Any small imperfection in the table is going to determine if the marble is going to roll, and in what direction. Stick a matchbook under a leg and the imperfections won't matter. But on a table that is truly "level", the small imperfections will decide everything. After the Comey letters, and the fake news the table was VERY level. Rain, a traffic jam, an election day sales at Sears on Play Stations could shift an election.
Hortensis
(58,785 posts)MSM media corruption is homogeneous only in its bias toward sensationalization, especially overstating problems, to maximize profits. Not to minimize that, though, as it's been very destructive.
On individual subjects, coverage can be honorable and excellent on most and still be corrupt on others. Hillary is one of the others -- almost every story was given the negative spin required of all who wanted to attain and keep prestigious jobs.
Another, ultimately far more monumental corruption, though, is not reporting on the degree of control and diversion to the far right of the Republican Party achieved by ultraconservative anti-government donors. That failure, including the reasons behind it are, is frightening.
The media most people watch cover issues and events without ever mentioning this huge factor. They now routinely refer to the Kochs' extremist "Freedom Caucus" as congress's conservatives and people like Graham and McCain as "moderates," as if by far most genuinely moderate conservatives hadn't been purged and replaced with strong and extreme conservatives long ago. A huge warping of and veil over political reality embedded in everyday language of reporting.