If you can read this, either the style sheet didn't load or you have an older browser that doesn't support style sheets. Try clearing your browser cache and refreshing the page.

(Talking Points Memo)   Gallup admits mistakes in 2012 polling. Promises to unskew the polls for 2016, study it out   (tpmdc.talkingpointsmemo.com) divider line 15
    More: Amusing  
•       •       •

942 clicks; posted to Politics » on 14 May 2013 at 9:56 AM (1 year ago)   |  Favorite    |   share:  Share on Twitter share via Email Share on Facebook   more»



15 Comments   (+0 »)
   
View Voting Results: Smartest and Funniest

Archived thread
 
2013-05-14 09:54:57 AM
It sounds like their likely voter model is ten years out of date. Young people and minorities vote now, too.
 
2013-05-14 10:02:59 AM
Did they really quote the tragedy of the commons for an explanation for the failing of their polling models?
 
2013-05-14 10:16:22 AM
They should hire this guy:
talkingpointsmemo.com
 
2013-05-14 10:22:36 AM
Yes, I'm sure the skewed Gallup polling results that pushed the same horse-race narrative in all branches of corporate media was a mistake.  Yeah, that's it.  A mistake.

I think I'll just listen to Nate Silver from now on, but thanks anyway.
 
2013-05-14 10:39:12 AM

LouDobbsAwaaaay: Yes, I'm sure the skewed Gallup polling results that pushed the same horse-race narrative in all branches of corporate media was a mistake.  Yeah, that's it.  A mistake.

I think I'll just listen to Nate Silver from now on, but thanks anyway.


I like Nate Silver, too, and he was my first resource for numbers during the election. But Silver can't do his job without other people taking polls. The better the numbers Silver has to work with, the smaller his margin of error. If Gallop fixes its model, that's a good thing for all of us.
 
2013-05-14 10:48:39 AM

MindStalker: Did they really quote the tragedy of the commons for an explanation for the failing of their polling models?


Yes. Yes they did. I came here to say, basically, this. WTF.
 
2013-05-14 10:53:01 AM

DeaH: LouDobbsAwaaaay: Yes, I'm sure the skewed Gallup polling results that pushed the same horse-race narrative in all branches of corporate media was a mistake.  Yeah, that's it.  A mistake.

I think I'll just listen to Nate Silver from now on, but thanks anyway.

I like Nate Silver, too, and he was my first resource for numbers during the election. But Silver can't do his job without other people taking polls. The better the numbers Silver has to work with, the smaller his margin of error. If Gallop fixes its model, that's a good thing for all of us.


No, the sooner Gallup goes out of business, the better off we'll be.
 
2013-05-14 11:00:27 AM

DeaH: The better the numbers Silver has to work with, the smaller his margin of error.


I don't trust Gallup to correct their polls.  If the bias in Gallup's system is identified, it can be corrected for in-post.  I'd imagine all we're going to get out of this is some ham-fisted approach on Gallup's part to reclaim some sense of authenticity, which will just inflate the uncertainty surrounding their numbers, until enough election cycles have taken place to discover what their new bias is.
 
2013-05-14 11:04:56 AM
FTA: The findings will be unveiled during an event on June 4 at Gallup's Washington, D.C. office.

Looking forward to reading that autopsy report.

LouDobbsAwaaaay: Yes, I'm sure the skewed Gallup polling results that pushed the same horse-race narrative in all branches of corporate media was a mistake.


Actually, that's not completely implausible. The poll shift on evolution from 2012 also looks wonky, and isn't readily explain by "horse-race narrative" motivation. Now, a partisan motivation (hoping to influence social lemmings) might work; but it's hard to distinguish whether a sample that skews to the right results from malice or from mere incompetence.

DeaH: I like Nate Silver, too, and he was my first resource for numbers during the election. But Silver can't do his job without other people taking polls. The better the numbers Silver has to work with, the smaller his margin of error. If Gallop fixes its model, that's a good thing for all of us.


If Gallup isn't completely incompetent, that "blue ribbon group of outside experts" might well include Nate Silver and Sam Wang.
 
2013-05-14 03:20:29 PM
Was the "mistake" that their polls showed what they wanted to see, or that Gallup isn't influential enough to make what they wanted to see a reality?
 
2013-05-14 03:59:42 PM
I want a photoshop contest on this....ppplllleeeeeeeeeeeezzzzzz?
 
2013-05-14 05:56:26 PM
I'm so pleased that "study it out" has become a watch-word for dumbfarkery. I hope that crazy woman is, too.
 
2013-05-14 11:53:05 PM

theorellior: I'm so pleased that "study it out" has become a watch-word for dumbfarkery. I hope that crazy woman is, too.


Me too. The second I heard it, I knew it was going to catch on.

Fuggin's Paradox of Memes: Memes can't be created intentionally.
 
2013-05-15 12:33:21 AM

DeaH: LouDobbsAwaaaay: Yes, I'm sure the skewed Gallup polling results that pushed the same horse-race narrative in all branches of corporate media was a mistake.  Yeah, that's it.  A mistake.

I think I'll just listen to Nate Silver from now on, but thanks anyway.

I like Nate Silver, too, and he was my first resource for numbers during the election. But Silver can't do his job without other people taking polls. The better the numbers Silver has to work with, the smaller his margin of error. If Gallop fixes its model, that's a good thing for all of us.


Exactly.  Nobody in the media actually learned the real lesson from Silver's work: The more data, the better.
 
2013-05-15 08:09:49 PM
Hello, Dave...
 
Displayed 15 of 15 comments

View Voting Results: Smartest and Funniest


This thread is archived, and closed to new comments.

Continue Farking
Submit a Link »






Report