Has Zogby's methodology completely self destructed? (user search)
       |           

Welcome, Guest. Please login or register.
Did you miss your activation email?
April 27, 2024, 07:54:28 PM
News: Election Simulator 2.0 Released. Senate/Gubernatorial maps, proportional electoral votes, and more - Read more

  Talk Elections
  Election Archive
  Election Archive
  2004 U.S. Presidential Election
  2004 U.S. Presidential Election Polls
  Has Zogby's methodology completely self destructed? (search mode)
Pages: [1]
Author Topic: Has Zogby's methodology completely self destructed?  (Read 3392 times)
The Vorlon
Vorlon
YaBB God
*****
Posts: 4,660


Political Matrix
E: 8.00, S: -4.21

« on: June 02, 2004, 12:56:08 AM »
« edited: June 02, 2004, 11:36:19 AM by The Vorlon »

These are the results of Zogby's 2002 tracking polls + the 2004 South Dakota House race.

http://www.zogby.com/news/ReadNews.dbm?ID=648

This is how Zogby has done over his last 14 polls.

Has the Zogby Methodological house of cards come tumbling down?



Logged
The Vorlon
Vorlon
YaBB God
*****
Posts: 4,660


Political Matrix
E: 8.00, S: -4.21

« Reply #1 on: June 02, 2004, 11:08:49 AM »


How do you figure an error of 9 in the Georgia race?   This looks like he was off by 5 to me.

Sorry, it is 9% - I just reversed the two candidates Chambliss did win! - Corrected now and thanks for noticing !
Logged
The Vorlon
Vorlon
YaBB God
*****
Posts: 4,660


Political Matrix
E: 8.00, S: -4.21

« Reply #2 on: June 02, 2004, 11:25:15 AM »

"Zogby is the Drudge Report of pollsters."  -The Vorlon

Couldn't have said it better myself.. Cheesy
Logged
The Vorlon
Vorlon
YaBB God
*****
Posts: 4,660


Political Matrix
E: 8.00, S: -4.21

« Reply #3 on: June 04, 2004, 11:36:16 AM »

This analysis may actually understate Zogby's inaccuracy.   For those who were following Zogby's polls on his website during the Democratic primaries, he was notorious for having "off-the-wall" results for a long period of time, and then suddenly having a massive shift of his results closer to the "consensus" of other polls the day before the election.

Thus, any results looking at his last-day tracking polls will often understate just how far out in left-field his polls really were.

TheOldLine

Zogby has always cut just a stunning array of corners on his polls.  He breaks a very large numbers for faily fundemental rules, but has always, generally speaking, been able to compensate by adding a variety of weights and adjustments to his raw data.

In 2000 he did "ok" - not great but OK.  His National poll was only 2% off, but about 40% of his state by state results were just totally screwed, (He had Gore and Bush TIED in California at the end)

I expect he had made some adjustments for 2004, or at least I hope he has.  He is a businessman, and a smart one, at the end of the day his "product" (accurate results) have to be there or he will go under.
Logged
Pages: [1]  
Jump to:  


Login with username, password and session length

Terms of Service - DMCA Agent and Policy - Privacy Policy and Cookies

Powered by SMF 1.1.21 | SMF © 2015, Simple Machines

Page created in 0.02 seconds with 14 queries.