I've been too busy to participate in this heated, but interesting
discussion.
Not to sound naive, but isn't the group of 11 MIT Biologists supposed to be
a sample, because we are extrapolating to all science faculty at MIT? If we
are not extrapolating, then why all the debate. Proving that discrimination
exists/does not exist ONLY in a single small department seems like a waste
of effort to all except those 11 folks. Actually, even this is not true.
Those 11 are a subset of the entire Biology department, are they not?
Clearly I can understand the characterization that these 11 folks are a
non-random sample, but claiming that they are a population would seem to
imply to me that there was no interest in generalizing beyond this group.
Everybody seems to be generalizing to all MIT science faculty if not to an
even larger group.
Maybe I don't understand what a sample truly is. To me, it just makes no
sense to act as if the 11 faculty are a population. Rich Ulrich in a
different series of posts argues that you should consider a population to be
such only in "warehouse" type applications. This does not strike me as a
"warehouse" sort of problem.
Also, has anyone looked at a log transformation of the data? The "huge"
difference doesn't look so huge on a log scale.
Finally, who is this guy "ad hominem" and why is he attacking everybody?
<grin>
Steve Simon, [EMAIL PROTECTED], Standard Disclaimer.
STATS: STeve's Attempt to Teach Statistics. http://www.cmh.edu/stats
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
