Robert J. MacG. Dawson ([EMAIL PROTECTED]) wrote:
: I would argue that for _most_ questions it is _a_priori_ plausible that
: the outcome correlates significantly with the probability of response.
: Recall the famous self-selected survey done by (Ann Landers/Dear Abby)
: in which readers with children were asked whether they would make the
: same decision again WRT having children. Something like half the
: respondents said "no", they would not have kids if they had a second
: chance. Somebody (sorry, no reference) checked this with a randomized
: phone survey and concluded that the true incidence was much lower
: (around 10%?).
And don't forget that if the survey involves something controversial, it
will be subject to campaigning, and different sides of the controversy
are unlikely to campaign equally hard. At the end of 1998,
random-selection telephone polls were finding most of the American public
opposed to Clinton being removed from office, while "click-in" Web polls
were finding a better-than-75% majority in favor of his removal. Many
conservatives were arguing on Usenet that this meant that traditional
statistical inference was an invention of liberals. Ah,
anti-intellectualism.
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================