Re: Gallup organization on polling methods

[Dennis Roberts]

At 04:58 PM 12/4/02 -0700, Paul Bernhardt wrote:

dennis roberts said on 12/4/02 8:56 AM:

>So, we really have no idea of whether they are "typical" of the "population
>of likely voters" or not. It was NOT a SRS of Americans who were "likely
>voters".

while I appreciate the perspective you are bringing to this question, and
certainly the process you describe is probably a closer approximation of
what actually occured than is related in the article, we still have to
come up with a rationale for deciding that the sample actually attained
is not equivalent to a true SRS....

in the article by the chief of the gallup poll, he clearly says several times that the method they used was simple random sampling ... he stressed that over and over ... in fact, that was THE main point of the paper ... SRS is what made their results so close to what actually happened he said

he did not say or suggest that their methods, though NOT really SRS, produce results like SRS ... he said they were SRS

i dispute that claim

i think the prudent course of assumption action is to never assume one does SRS ... UNless we have pretty clear procedural evidence that they did

if you look at what he said, it is pretty clear that they did not take a SRS of "likely voters"

there is no way to prove one way or the other that they did or did not use SRS ...
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================