At 02:52 PM 2/15/01 -0600, Paul R Swank wrote:
>I remember a question from some stat book about a situation where there
>were 8 members of a group, three men and five women (or the reverse, I
>can't remember
>which) and on some issue the vote was five to three with all five women
>voting for. The question was "How likely was this event to occur by
>chance"? Can we not ask that question?
seems like we could do something like ... IF OTHER FACTORS HAVE BEEN
ACCOUNTED FOR OR CONTROLLED FOR like ... age, years in ranks, etc. ... ask
... what is the probability that ALL (or each?) male salaries were higher
than ALL (each?) female salaries ...
fishers exact test comes to mind but ... that might not be the one
but, of course, as was pointed out, no data were given about actual salaries
so the issue is moot ... from the stand point of the report ...
from what has been reported ... here ... whether one was making one case or
another ... i still stand by my earlier comment that i would HATE to have
MY name attached to the report ... unless there were many HUGE BOLD FACED
caveats ...
there are just far too many problems here ... with the dinky sized set of
data and the variables that are being used
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
