Top Gallup editor: Faulty polling led to inaccurate 2016 data models

[mystery-ak]

9/10/2018

Frank Newport, editor-in-chief at the Gallup Poll, on Monday said that data analyst websites, not national polls, were the ones incorrect in their 2016 presidential election predictions.

“The national polling was actually one of the more accurate years where they correctly predicted the popular vote,” Newport said to Hill.TV's Joe Concha, referring to national polls.

“But one of the things that happened was an overreliance on these models where various individuals and various companies put together these scientific-sounding probabilistic models,” he continued.

“When you disassemble those models, all they were were looking at state polls,” he said.

He pointed at the smaller sample sizes in toss-up states making it difficult to get accurate polling.

more
http://thehill.com/hilltv/what-americas-thinking/405942-gallup-top-editor-faulty-polling-in-2016-led-to-inaccurate-data

[cato potatoe]

Yes, I found it strange the Nate Silvers of the world gave Hillary a 72% chance of winning.  Even worse, 85% chance forecasted by NY Times??  The state polling averages only gave her a 272-266 lead on election night.  Even that hinged upon razor thin victories in NH, PA, and MI.  Months of bluster and wishcasting lead to the false impression of a huge upset that persists even still.

[bilo]

Yes, I found it strange the Nate Silvers of the world gave Hillary a 72% chance of winning.  Even worse, 85% chance forecasted by NY Times??  The state polling averages only gave her a 272-266 lead on election night.  Even that hinged upon razor thin victories in NH, PA, and MI.  Months of bluster and wishcasting lead to the false impression of a huge upset that persists even still.

Maybe there really is a silent group of voters pollsters can't reach. I know most folks don't have landlines anymore and those that do usually screen their calls. It's got to be tough to get a broad sample.

[Bigun]

Maybe there really is a silent group of voters pollsters can't reach. I know most folks don't have landlines anymore and those that do usually screen their calls. It's got to be tough to get a broad sample.

And even tougher to get an accurate one. 

[Frank Cannon]

This from the outfit that gave up polling Presidential elections because they were that bad at it.

[Wingnut]

Dude sounds like he is doing a bit of CYA.   Polling today is an unscientific method.  But they try to foist it as science upon the rubes.  Vegas has better odds. 

[bilo]

And even tougher to get an accurate one.

The left is so loud and nasty a lot of people just aren't speaking up which creates an impression that more people support the leftists then actually do. I'm sure this carries over to people that respond to polls.

[bilo]

Dude sounds like he is doing a bit of CYA.   Polling today is an unscientific method.  But they try to foist it as science upon the rubes.  Vegas has better odds.

Also, polling is now used to promote a particular view not to find out what people actually believe.

[Bigun]

Also, polling is now used to promote a particular view not to find out what people actually believe.

That's not new.  But the fact that a lot of people have caught on to it is new.

[Cyber Liberty]

Can I get a "Duh?"

[Free Vulcan]

And they're doing the same thing this time.

[truth_seeker]

I warn any pollster, against push polls. the first "push" sign, I stop, and tell them why.

When I do cooperate I might be honest, or I might not.

18-25 female minority HS dropout, very liberal democrat voter.