Poll Averaging

Poll Averaging Critique

Submitted by Blue Leader on Fri, 12/05/2008 - 16:03

Matt Yglesias made a good point recently: for all the additional complexity that 538's prediction model brought to the table, it didn't add a whole ton of accuracy.  Yglesias goes into more detail, but the nut is here:

Read more...

»

The Poll-of-Polls Problem

Submitted by Student Redux on Tue, 10/28/2008 - 15:35

Last week, I discussed some of the sampling problems that can crop up in pollsters' work.  My first article showed how the problem of bias is intrinsic to stratified sampling.  My second article expanded the discussion to demographic weighting and cluster sampling.

Today, I'm going to resume the discussion of polling problems by looking at the media's new tactic of using polls-of-polls to resolve the sometimes conflicting information from polls that get reported on an hourly basis.

There's more... 

»

Snark from Chris Bowers

Submitted by Blue Leader on Mon, 07/28/2008 - 18:06

We are back from our hiatus and getting into the thick of things.  There will be more substantive content tomorrow, but for now, content yourself with this entertaining post on Open Left, about the media's seemingly bottomless desire for a close election.  A taste:

If you are trying to win an election, is it better to be ahead, or behind, in the polls? This question has haunted philosophers since Kirkegaard.

»
Syndicate content