Ignore my first reply, please.
Prof. Cramer has explained thus:
"that's not what I meant; Boole used that phrase, referring to the
assumption that some people made about unknown probabilities ie if you
don't know it, assume it to be .5
In the semantic differential case you obviously can't assume a score of 0,
but the mid-point is questionable also.
For a set of items on a unidimensional scale under the assumption of
randomly missing scores, you would use the average of the scores you have."
He is, of course, exactly right. I apologize for misinterpretting his reply.
Grover
===========================================================================
This list is open to everyone. Occasionally, people lacking respect
for other members of the list send messages that are inappropriate
or unrelated to the list's discussion topics. Please just delete the
offensive email.
For information concerning the list, please see the following web page:
http://jse.stat.ncsu.edu/
===========================================================================
