[extropy-chat] what is probability?
russell.wallace at gmail.com
Mon Jan 15 17:56:38 UTC 2007
On 1/15/07, gts <gts_2000 at yahoo.com> wrote:
> Not sure what you're getting at here, but assume you are political
> pollster commissioned by a politician wanting to know the political
> make-up of some newly districted congressional district about which there
> is no reliable prior data, and at a time in which the entire country is in
> political turmoil such that not even national statistics can be relied
> upon for priors. Assume also that you don't care about third parties.
Okay that's a reasonably practical example, thanks. (Like Jef said, context
In that situation, if you are using bayesian methods, you might use the PI
> and set your prior judgemental probability to .5 of finding, among those
> voters in the district who say they belong to one of the two major
> parties, someone who professes to be a democrat.
Not if you wanted an answer that reflected reality, you wouldn't. Rather
than just make up a number like .5 for no reason, at the very least you can
start with the results of the last election, which give actual data on the
probability of a randomly selected person being a member of party A vs B.
Maybe said data is no longer very reliable, but if you just make things up
the reliability is zero, so better to use what you have. Then you probably
have some sort of data on how this varies with social groups or whatever,
that lets you narrow it down a bit. If that's still not enough for a
reliable answer, you go out and gather data by polling substantial numbers
of people, and use the result of that as your prior for further
investigation. You'd never actually rely on the principle of indifference.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the extropy-chat