Nader Wins the Debate

[Michael Hoover]

> Marco Anglesio wrote:
> >That's true, but you would expect the same sample bias in each tracking
> >poll, unless they modified the criteria for likely voters over the course
> >of the tracking poll. I suspect that it's merely sample error, accounted
> >for in the confidence interval. One should expect the poll numbers to rise
> >and fall even if support within the sampled population is stable.
> 
> Each pollster uses different techniques to project likely voters, 
> which may account for the diff between Zogby & Gallup. The time 
> trends within each poll are probably the joint product of noise and 
> real volatility.
> Doug

what is it with lbo-ster public opinion poll fetish...

as number of polls has increased, number of folks willing to answer
questions has declined (correlation doesn't mean causation but in
this instance...).  Pollsters find it increasingly difficult to 
get "correct" mix of respondents.  Falling response rates (measuring
number of people who say they will participate) has led pollsters
to "cook up" ways to secure respondents.  Some polling firms now
pay cash ($10 is going rate, I think) and others offer gifts [[I've
long held that if left would offer people Mr. Coffee Makers...]]
If memory serves, University of Michigan Institute for Social Research
(which conducts national election studies) offers respondents a "Go
Blue" desk clock.

We've all been malled, er, I mean polled...  Michael Hoover

btw: my favorite internet poll (in all its self-selected glory) indicates
following:

Buchanan 38%
Bush 24%
Gore 19%
Browne 12%
Nader 5%

btw2: N' Sync has picked up a percentage point since last week in
favorite "boy band" poll.  Back Street Boys not yet a lock...