Sun September 09, 2018 2:39 am
Sun September 09, 2018 7:17 pm
washing machine wrote:He's showing the fuck up!
Wed September 12, 2018 12:36 pm
Wed September 12, 2018 12:44 pm
Wed September 12, 2018 1:40 pm
Wed September 12, 2018 1:51 pm
Wed September 12, 2018 3:56 pm
McParadigm wrote:I don’t think that’s an accurate summary at all. Polls in 2016 never had Clinton at much more than a 9 point lead, and the final week of calling showed her at around a +3. She ended up coming out 2.1% ahead. That seems pretty predictive.
Thu September 13, 2018 11:43 pm
4/5 wrote:McParadigm wrote:I don’t think that’s an accurate summary at all. Polls in 2016 never had Clinton at much more than a 9 point lead, and the final week of calling showed her at around a +3. She ended up coming out 2.1% ahead. That seems pretty predictive.
Yeah, this.
I also wouldn't underestimate the effect of the exact timing of the polls and the election. That cycle featured some pretty major polling swings following the news cycle and of course the last news that affected voters was that Comey bit which sent Clinton's numbers into a nosedive. I think it's very possible that Hillary would have won if the election were the day before Comey's attention grab (or barring new news maybe a week or so after the election once that proclamation became old news), and I think it's also likely that polls didn't have adequate time to fully include the full adjustment caused by that news.
Another major mistake a lot of people made in their prediction models based on the polls was that they viewed the result in individual states as uncorrelated events. Therefore if they gave Hillary a 75% chance of winning in each of, let's say Pennsylvania, Michigan, Wisconsin, and Minnesota they viewed Trump as having a 0.39% chance of winning all four. Silver's model wisely viewed the results in similar states as being correlated, suggesting that if Hillary had a 75% chance of winning in each of them, an upset in one could be predictive of an upset in the others, so his model gave Trump a better chance than most, e.g. the NYT one that had her with an absurd 99% chance of victory.
Fri September 14, 2018 12:03 am
Simple Torture wrote:4/5 wrote:McParadigm wrote:I don’t think that’s an accurate summary at all. Polls in 2016 never had Clinton at much more than a 9 point lead, and the final week of calling showed her at around a +3. She ended up coming out 2.1% ahead. That seems pretty predictive.
Yeah, this.
Another major mistake a lot of people made in their prediction models based on the polls was that they viewed the result in individual states as uncorrelated events. Therefore if they gave Hillary a 75% chance of winning in each of, let's say Pennsylvania, Michigan, Wisconsin, and Minnesota they viewed Trump as having a 0.39% chance of winning all four. Silver's model wisely viewed the results in similar states as being correlated, suggesting that if Hillary had a 75% chance of winning in each of them, an upset in one could be predictive of an upset in the others, so his model gave Trump a better chance than most, e.g. the NYT one that had her with an absurd 99% chance of victory.
There was an article on 538 about a week before the election that laid this out pretty clearly (i.e., it described exactly what happened), and I've been trying to find it for a while now but it keeps slipping through my fingers.
In 2012, Obama beat his polling by 2 or 3 percentage points in almost every swing state. The same was true in 1980 when Ronald Reagan won in a landslide — instead of the modest lead that polls showed a few days before the election — and claimed 489 electoral votes by winning almost every competitive state. You also frequently see this in midterms — Republicans beat their polling in almost every key Senate and gubernatorial race in 2014, for example.
Basically, this means that you shouldn’t count on states to behave independently of one another, especially if they’re demographically similar. If Clinton loses Pennsylvania despite having a big lead in the polls there, for instance, she might also have problems in Michigan, North Carolina and other swing states. What seems like an impregnable firewall in the Electoral College may begin to collapse.
It’s true that Trump would have to make a breakthrough somewhere, by winning at least one state in Clinton’s firewall. But that’s why it’s not only reasonable but 100 percent strategically correct for Trump to be campaigning in states such as Michigan and Wisconsin. (I’ll grant that New Mexico is more of a stretch.) Sure, Trump’s behind in these states, but he has to win somewhere where he’s behind — or he’s consigning himself to four more years in Trump Tower instead of the White House. Michigan and Wisconsin are as reasonable as any other targets: Trump isn’t any further behind in them than he is in higher-profile battleground states such as Pennsylvania, and the demographics are potentially more favorable for him.
If you want to debate a campaign’s geographic planning, Hillary Clinton spending time in Arizona is a much worse decision than Trump hanging out in Michigan or Wisconsin. Sure, she could win the state — but probably only if she’s having a strong night nationally. If the results are tight next Tuesday instead, Michigan and Wisconsin are much more likely to swing the election.
Fri September 14, 2018 5:44 pm
Fri September 14, 2018 10:30 pm
4/5 wrote:Yup. I remember telling my classes that in the days right before the election. I also recall that about a week out 538 had Clinton with a 75% chance of victory so I reminded students what that actual means: Trump had the same chance of winning the presidency as you have of flipping heads twice in a row. I decided to demonstrate and promptly flipped heads twice in a row to the great delight of a depressingly large contingent of my p.2 class.
Fri September 14, 2018 10:34 pm
Sun September 16, 2018 2:47 am
Sun September 16, 2018 3:09 am
Wexner had a close relationship with Jeffrey Epstein, who managed Wexner's money. Wexner and Epstein parted when Epstein went to prison.[25]
Trump said of Epstein in 2002: "I've known Jeff for fifteen years. Terrific guy. He's a lot of fun to be with. It is even said that he likes beautiful women as much as I do, and many of them are on the younger side."[61]
Mon September 17, 2018 3:12 pm
Tue September 18, 2018 1:42 pm
Tue September 18, 2018 2:59 pm
Tue September 18, 2018 3:11 pm
Tue September 18, 2018 3:26 pm
Tue September 18, 2018 7:50 pm