Leaving the community

Matt Whiting writes:
Exactly what is "useful" about exit polls taken on election day?

One use of exit polls is to check the accuracy of the election. As a
pilot, you probably appreciate the value of redundant systems. The
exit poll data can give you an indication of a problem in the
electoral polling process.

If the election result and the polling data radically disagree, it is
probably worthwhile to look closely at both the election and the exit
poll to figure out the source of error...

Chris
--
Chris Colohan Email: PGP: finger
Web: www.colohan.com Phone: (412)268-4751

Christopher Brian Colohan wrote:
Matt Whiting writes:

Exactly what is "useful" about exit polls taken on election day?


One use of exit polls is to check the accuracy of the election. As a
pilot, you probably appreciate the value of redundant systems. The
exit poll data can give you an indication of a problem in the
electoral polling process.

If the election result and the polling data radically disagree, it is
probably worthwhile to look closely at both the election and the exit
poll to figure out the source of error...

Chris


I disagree with this. Exit polls are not taken by every person that
votes. I don't participate in them for instance. They only exist so
that the media has something to report throughout the day instead of
just reminding everyone when the polls close and watching the clock in
anticipation. I for one believe the media should keeps its mouth shut
and not even talk about the election other than reminding everyone it is
election day until states are finalized.

Brooks Hagenow writes:

Christopher Brian Colohan wrote:
Matt Whiting writes:
Exactly what is "useful" about exit polls taken on election day?

One use of exit polls is to check the accuracy of the election.
As a pilot, you probably appreciate the value of redundant
systems. The exit poll data can give you an indication of a
problem in the electoral polling process.

If the election result and the polling data radically disagree, it
is probably worthwhile to look closely at both the election and
the exit poll to figure out the source of error...

I disagree with this. Exit polls are not taken by every person that
votes. I don't participate in them for instance.

I'm confused -- what are you disagreeing with? Are you arguing that
any source of inaccuracy (no matter how small) in the polls
invalidates their usefulness as an indicator? Why?

If you can estimate or measure the potential error from people
refusing to participate then you can adjust your error bounds on the
polling data.

For example, lets say that the exit polls at my local firehouse showed
that 90% of folks voted for Joe the garbageman, and only 10% voted for
Bob the fireman for our new position of block captain. If the
election results showed that Bob the fireman won by a landslide, I
would want to know why! It may be a problem in the polls, but perhaps
something fishy was going on at the firehouse... Are you arguing that
when it looks like there may be a problem it is better to look the
other way?

They only exist so that the media has something to report throughout
the day instead of just reminding everyone when the polls close and
watching the clock in anticipation. I for one believe the media
should keeps its mouth shut and not even talk about the election
other than reminding everyone it is election day until states are
finalized.

I strongly agree that the media should not report any election results
(from polls or otherwise) until the election is complete. It is not
fair to the candidates if their reporting influences people's voting
decision.

Chris
--
Chris Colohan Email: PGP: finger
Web: www.colohan.com Phone: (412)268-4751

In article ,
Christopher Brian Colohan wrote:

If you can estimate or measure the potential error from people
refusing to participate then you can adjust your error bounds on the
polling data.

and there is the problem - can you really estimate or bound the error
from all the error sources (e.g., people not participating or
deliberately lying to the poll)?

--
Bob Noel

and there is the problem - can you really estimate or bound the error
from all the error sources (e.g., people not participating or
deliberately lying to the poll)?

Yes.

You cannot "bound" the error in an absolute sense, except to say that it's no bigger than the total population, which is useless. However, if a poll is done right, you can estimate the likely error. For example, "95% of the time, the error will be
less than 1%. 98% of the time, the error will be less than 5%" (I'm making these numbers up since they depend on how well the poll is conducted, and how big the sample size is, etc). This is where the standard deviation of the mean comes in as an
estimate of how good your measurement is.

Of course it cannot be used as a "backup" to voting. However, it can (and should) be used as a screening to indicate whether this particular situation warrents closer investigation. IF the actual voting disagrees with the exit poll by enough
(depending on how the poll is conducted), then there is a good chance (though not a certanty) that there is funny business going on somewhere. It could be that the poll is incorrectly reflecting the actual intended (by the voters) results. However,
it could also be that the election incorrectly reports the voters' choices.

Jose
--
Freedom. It seemed like a good idea at the time.
for Email, make the obvious change in the address.

In article ,
Jose wrote:

and there is the problem - can you really estimate or bound the error
from all the error sources (e.g., people not participating or
deliberately lying to the poll)?

Yes.

You cannot "bound" the error in an absolute sense, except to say that it's no
bigger than the total population, which is useless. However, if a poll is
done right, you can estimate the likely error. For example, "95% of the
time, the error will be
less than 1%. 98% of the time, the error will be less than 5%" (I'm making
these numbers up since they depend on how well the poll is conducted, and how
big the sample size is, etc). This is where the standard deviation of the
mean comes in as an
estimate of how good your measurement is.

This is true only if you know the distribution function.

--
Bob Noel

This [putting a bound on the likely error] is true
only if you know the distribution function.

One of course never =knows= the distribution function. However, one can make reasonable estimates ("guesses", if you will) based on ones sampling methods and experience with previous polls (comparing past polls with elections for example). True,
your guess of the distribution function might be off, but if you do things right, it's probably close. How close? Well, there's a distribution function to describe that too.

One doesn't even know the sun will come up the next day, but as a working theory it seems to be more than satisfactory. Statistics is not mumbo jumbo, although it is true that real mumbo jumbo can be disguised as statistics.

Jose
--
Freedom. It seemed like a good idea at the time.
for Email, make the obvious change in the address.
(note to r.a.student: I only follow r.a.piloting and r.a.ifr, to which this is also posted)

On Mon, 08 Nov 2004 01:48:42 GMT, Jose
wrote:

and there is the problem - can you really estimate or bound the error
from all the error sources (e.g., people not participating or
deliberately lying to the poll)?

Yes.

You cannot "bound" the error in an absolute sense, except to say that it's no bigger than the total population, which is useless. However, if a poll is done right, you can estimate the likely error. For example, "95% of the time, the error will be


Ahhhh... How about setting your line wrap to about 70 characters?

Roger Halstead (K8RI & ARRL life member)
(N833R, S# CD-2 Worlds oldest Debonair)
www.rogerhalstead.com

Ahhhh... How about setting your line wrap to about 70 characters?

Well, that's double edged. Wide line wrap (200 char or so) lets newsreaders that autowrap text do their thing gracefully while preventing buffer overruns, but are a pain for those that don't. Line wrapping at (say) 70 defeats autowrap, but ensures
that older newsreaders (I'd presume very old) handle the post gracefully (unless it's quoted too much).

What's a poster to do?

Jose
(note - I don't follow r.a.student)
--
Freedom. It seemed like a good idea at the time.
for Email, make the obvious change in the address.

Christopher Brian Colohan wrote:

Matt Whiting writes:

Exactly what is "useful" about exit polls taken on election day?


One use of exit polls is to check the accuracy of the election. As a
pilot, you probably appreciate the value of redundant systems. The
exit poll data can give you an indication of a problem in the
electoral polling process.

If the election result and the polling data radically disagree, it is
probably worthwhile to look closely at both the election and the exit
poll to figure out the source of error...

I absolutely believe in redundant systems, but only if each system is
itself reliable. Exit polls simply aren't reliable enough for me to
consider them a redundant system.


Matt