Well, no more polls, and as much as I like figuring out what things really mean, even I’m more than a little tired of it all. The last couple surveys came in this morning, both tracking polls that have always favored Trump (remember the LA Times tracker that is wildly
Posts in Category: polling
Plus ça ne change point….
More polls, no change, so the decline of the last week appears to have flattened out, though I won’t call it a trough unless it starts to climb again.
Read More
Into–Deo Gratias–The Homestretch…
OK, OK, so the polls have tightened, but the polls always tighten in the last couple weeks. I’d thought that Comeymania would filter through for a few days, if at all, and then things would stabilize. If they’re going to stabilize, it’s today and tomorrow that it will happen. On
Not Saying Much Because There Ain’t Much To Say Dept.
Courtesy, as ever, Princeton Election Consortium
Sam Wang’s right. This really is a remarkably stable race. Even Obama/Romney ’12 had more variability, and that one seemed like the
PEC Clinton meta-margin closes up another 0.3%. Needs to start widening again by Monday.
As I’d been suggesting, the early response that Trump did well in the debate should show up in the first few days’ polling done afterwards, but if that glow really did fade quickly, by the time we got to polls that were taken entirely after Sunday night, we’d probably see
tl;dr Dept., Or How PEC Does What It Does And Why Mathier Is Better When You’re Doing, Y’Know, Math
The linked post is pretty heavy stuff, but at least look at the first couple paragraphs before Sam Wang gets all mathy with it. He also does a good job of explaining why PEC is different, by design, from 538—that the goals are different, and perhaps the motivations as well.
Not Quite A Polling Update, But Close. Because Nothing’s Changed, That’s Why.
So Sam Wang has a theory about why 538 is so much more indecisive than people who know how to use math. He thinks that in addition to using means instead of medians (which in itself adds volatility due to the effect of single outlying results), they may be double-counting
So, is ANYthing happening? Umm, well….
So since there’s nothing new to talk about again, but I’m trying to do something every day, let’s go to the videotape. In the last three presidential elections, and you may not know this, but the Democratic candidate has actually outperformed the polls, after previous underperformance.
Poll Aggregation 1, People Who Think Poll Aggregation Misses The Point 0
Source: All The Reasons You Doubt Polls: Motivated Reasoning Strikes Again
Sam Wang’s new take on people’s take, courtesy Princeton Election Consortium.
This, this, a thousand million kaskillion times