Readers of this mailing list may be interested in the following article just
published by JAIR:
Grunwald, P.D. and Halpern, J.Y. (2003)
"Updating Probabilities", Journal of Artificial Intelligence Research
(JAIR),
Volume 19, pages 243-278.
For quick access via your WWW browser, use this URL:
http://www.jair.org/abstracts/grunwald03a.html
Abstract:
As examples such as the Monty Hall puzzle show, applying conditioning
to update a probability distribution on a ``naive space'', which does
not take into account the protocol used, can often lead to
counterintuitive results. Here we examine why. A criterion known as
CAR (``coarsening at random'') in the statistical literature
characterizes when ``naive'' conditioning in a naive space works. We
show that the CAR condition holds rather infrequently, and we provide
a procedural characterization of it, by giving a randomized algorithm
that generates all and only distributions for which CAR holds. This
substantially extends previous characterizations of CAR. We also
consider more generalized notions of update such as Jeffrey
conditioning and minimizing relative entropy (MRE). We give a
generalization of the CAR condition that characterizes when Jeffrey
conditioning leads to appropriate answers, and show that there exist
some very simple settings in which MRE essentially never gives the
right results. This generalizes and interconnects previous results
obtained in the literature on CAR and MRE.
The article is available via:
-- comp.ai.jair.papers (also see comp.ai.jair.announce)
-- World Wide Web: The URL for our World Wide Web server is
http://www.jair.org/
For direct access to this article and related files try:
http://www.jair.org/abstracts/grunwald03a.html
-- Anonymous FTP from Carnegie-Mellon University (USA):
ftp://ftp.cs.cmu.edu/project/jair/volume19/grunwald03a.ps
The compressed PostScript file is named grunwald03a.ps.Z
For more information about JAIR, visit our WWW or FTP sites, or
contact [EMAIL PROTECTED]
