[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
P(S|~M) vs. P(S)
- To: cse471-f06@parichaalak.eas.asu.edu
- Subject: P(S|~M) vs. P(S)
- From: "Subbarao Kambhampati" <rao@asu.edu>
- Date: Mon, 16 Oct 2006 22:04:33 -0700
- Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:sender:to:subject:mime-version:content-type:x-google-sender-auth; b=Wxrtl0P0iHgOSbjQasNfFE8XPDYkk0bb7+vJJ3P7wA/3WVk/kMScza1RNboQk2vNNB/NVn9pFZY5Bn+SSk2VzGT3z8LvMyEMVFEFTR6vpt3l6NKwp0W04W9/hD1hVuDFv26ZKY9Gz4IwH1IFS6wjBE1co480UQ8TuFzZN+LWaBM=
- Sender: subbarao2z2@gmail.com
Someone
(If I remember faces right, Brandon Mechtley) asked whether it is
really easier to assess P(S|~M) compared to P(S). I tried to venture a
weak answer in the class.
In general, there don't seem to be
good and convincing arguments that it will always be easier to assess
P(S|~M) compared to P(S). (So I oversold my
case :-(
The
most reasonable explanation as to why we look at P(S|~M) type
probabilities rather than P(S) that I can offer on further reflection
is that we are interested in computing posterior probability
distribution of a variable (rather than just its maximal probable
value). If the patient's disease can be one of 7 types. There may be a
prior distribution over these diseases, and after seeing some evidence,
the doctor wants to get the posterior *distribution* on the diseases
(not just the most likely disease but the distribution). If we are
doing, we will anyway be needing
probabilities of type P(S|disease= di) (note that P(S|~M) can be seen as P(S|M=false)).
I added a slide to the class notes making this point.
cheers
Rao