SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Politics : I Will Continue to Continue, to Pretend....
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: Sully- who wrote (22430)10/19/2006 7:17:34 PM
From: Sully-  Read Replies (1) of 35834
 
I'd forgotten this

Betsy's Page

Riehl World looks back on polls from just before the 2002 election. And finds a pattern (link below).

I remember a study done by Gerald S. Wasserman of Purdue of the polls in 1996, that found that all the polls predicted a much bigger win for Clinton than there actually was. Wasserman calculated the chances that there would be such an overall overprediction for one candidate by chance and found this result: 
    Most of the final 1996 presidential polls predicted that 
    Clinton's margin over Dole would be greater than it 
    actually was. The present document presents the results of
    a meta-analysis of this pattern; this calculation 
    indicates that chance alone would produce such a failure 
    pattern only once in 4,900 elections.
Meanwhile, Jim Geraghty is having fun just contrasting what two polls over the same time period say about the same races. There are wild swings (link below).

As I wrote earlier, I'm more and more convinced that pollsters really have some problems that may indeed be insurmountable in using their polls to predict election outcomes. The more and more we are using polls, the more we should be aware of all their weaknesses and past failures. I used to think that, perhaps the polls couldn't get the margin correct, but they could get the general trend. But, there are too many counter examples.

I would love to know if the accuracy rate of the polls that the parties themselves use. You would think that they would have the most interest in getting a correct analysis since they're committing money and resources on the basis of those polls. Do their polls have as poor a history as the public ones do? I don't know if the partisan pollsters make their data public, but I sure would be interested in finding out if they have the same problems.

Examining entrails is beginning to seem like as if it would be just as predicative as some of these polls.

betsyspage.blogspot.com

www2.psych.purdue.edu

tks.nationalreview.com

riehlworldview.com
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  

HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2025 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News