Skip to Content.
Sympa Menu

internetworkers - RE: [internetworkers] 50/50/50 clue-by-four request

internetworkers AT lists.ibiblio.org

Subject: Internetworkers: http://www.ibiblio.org/internetworkers/

List archive

Chronological Thread  
  • From: Michael <michael AT metalab.unc.edu>
  • To: "Internetworkers: http://www.ibiblio.org/internetworkers/" <internetworkers AT lists.ibiblio.org>
  • Subject: RE: [internetworkers] 50/50/50 clue-by-four request
  • Date: Fri, 30 Jul 2004 17:31:00 -0400 (EDT)


On Fri, 30 Jul 2004, Michael D. Thomas wrote:

> Moore also believes that the polls that we see are flawed b/c they poll
> people with a history of voting. (I don't know enough about polling to
> agree or disagree.)

Something I've wondered about - but can't answer, as I'm not even remotely
a pollster or statistician - is whether polls are becoming decreasingly
accurate due to sample creep. By that I mean more and more people have
cellphones as their primary phones, and they're not in the phonebook, thus
they don't get polled. I'd also gamble that the percentage of people who
don't have a landline is heavily skewed towards younger voters.

Ignoring the issue of voter turnout across demographics, I wonder if that
means polls are, in general, sampling only older generations. If so,
will that increase over time, as the younger demographics who now are
partially unavailable for polling grow into older demographics with
similar cell-users back-fill the younger demographics and as fewer people
keep a landline in the first place - ie, will more demographics have a
percentage of people who are unavailable for polling, and will the
percentage within any given demographic go up over time?

I'm just talking through my hat here, but it's something that had
occurred to me and I sincerely have no idea if it's at all an issue,
accurate or worth thinking about. If subjects are being harvested from
voter rolls, for example, and those people are using their cell #'s as
the # they list when they register, then it's a non-issue. But if fewer
and fewer people outside of my parents' voting bloc become available to be
polled, eventually my parents' voting bloc are going to be the /only/ ones
effectively being polled, and that's going to give us some screwy answers.
If my parents are eventually the only subjects left we're going to have an
awful lot of McGovern-Nixon rematches, I'm just sayin'.

--
www.robustmcmanlypants.org/blog "Get off my desk
Michael Williams before you get them
http://www.ibiblio.org/michael demonic spirits on me!"
michael AT ibiblio.org --co-worker





Archive powered by MHonArc 2.6.24.

Top of Page