Welcome to DU! The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards. Join the community: Create a free account Support DU (and get rid of ads!): Become a Star Member Latest Breaking News General Discussion The DU Lounge All Forums Issue Forums Culture Forums Alliance Forums Region Forums Support Forums Help & Search

Doctor Jack

(3,072 posts)
Fri Sep 2, 2016, 08:20 PM Sep 2016

Can We All Agree That Online Polls Are Total Bullshit?

One online poll today shows clinton up 3 in Nebraska (the entire state mind you) and another online poll shows it tied nationally? In what version of reality would that be possible? We must conclude that this is the most batshit, head spinning, illogical election in the history of the U.S. where everything we know about politics is no longer true. Or these highly experimental, never before seen "online panel polls" that everyone and their mother seems to be releasing, all showing wildly different results, might be as useful as tits on a bull.

Seriously, this dissonance between these polls should raise major red flags. We can't have one showing a tie in Wisconsin, another showing Trump up by only 2 in Utah, and a third where Clinton is ahead in Nebraska, all while nationally clinton is either up by 6 or Trump is up by 3.

I think we need to agree that these online polls are horseshit, whether they show Clinton somehow up by 16 points or down by 3. I suggest we stop touting them, stop freaking out about them, or stop celebrating them.

9 replies = new reply since forum marked as read
Highlight: NoneDon't highlight anything 5 newestHighlight 5 most recent replies

pnwmom

(108,976 posts)
2. 538 recently discussed the different outcomes. Here:
Fri Sep 2, 2016, 08:29 PM
Sep 2016
http://fivethirtyeight.com/features/live-polls-and-online-polls-tell-different-stories-about-the-election/

As of Tuesday morning, Clinton led Trump by 6 percentage points and had a 79 percent chance of winning, according to our polls-only forecast. But running our polls-only model using only live-interview surveys, Clinton leads Trump by 7 points and has an 86 percent chance of winning. Running it with only nonlive-interview polls, Clinton leads Trump by 5 points and has a 71 percent chance of winning.

That’s a pretty big gap. Interestingly, about half that gap comes from the model’s trend line adjustment, which looks for how the race is changing by comparing surveys to previous editions of the same poll (e.g.., Monmouth’s August poll to its July poll.) In other words, there’s little evidence in live-interview polls that Clinton has regressed much from her post-convention high. The forecast based on nonlive surveys, by contrast, shows her convention bounce fading by a few percentage points.

SNIP

As the cases of Utah and Kansas suggest, I’d put more faith in the live-interview polls than in other types of surveys, all else being equal. Indeed, our forecast models do just that. If the gap between live-interview polls and everything else persists, though, we’ll need to explore what might be causing the split and which is more likely to be right.

rock

(13,218 posts)
5. They are (in fact) BS
Fri Sep 2, 2016, 10:30 PM
Sep 2016

But we can't get agreement as many people don't understand the technical details of polling. By the way they could be done properly and give valid results, but the media want a horse race.

 

Lsantos04

(48 posts)
7. I concur
Sat Sep 3, 2016, 12:08 AM
Sep 2016

If I remember correctly, some polls at this point in 2012 showed that Romney was winning by several percentage points. Of course, we all know the outcome of that election, where Obama won easily.

In any case, Clinton is still outperforming Trump, and will defeat him by a landslide in November.

Monk06

(7,675 posts)
9. All you have to do is clear your internet cache and you can vote as many times as you want
Sat Sep 3, 2016, 08:23 PM
Sep 2016

That's how Freepers spam online polls They even have a name for it, Freeping the Poll

They've been doing it for years

Online polls are shit as are polls that model according to hypothical turnout by party, ethnicity or gender

The latest Monmouth poll IIRC assumed voter turnout by whites higher than it has ever historically occurred

No voting turnout should be assumed to be higher than the historical averages

That's just hynotizing chickens as Iggy says

Latest Discussions»Retired Forums»2016 Postmortem»Can We All Agree That Onl...