[S] Box's M followup

Marc Feldesman (feldesmanm@pdx.edu)
Mon, 08 Jun 1998 10:30:40 -0700


As some of you noticed, the demo calculation I showed didn't equal the
calculated "Box's M" in my own program. I forgot to show the gamma
correction, which when applied to the data given would give the same answer
reported as "Box's M" in _my_ function. The gamma correction factor is a
function of the number of variables, the number of groups, the number of
cases, and the number of cases per group.

The calculated gamma correction factor for the data set described in my
previous post is:

g=0.9705713. If you multiply g*22.7292, you get the reported Box's M from
my function.

Dr. Marc R. Feldesman
Professor and Chairman
Anthropology Department
Portland State University
P.O. Box 751
Portland, Oregon 97207
email: feldesmanm@pdx.edu
phone: 503-725-3081
fax: 503-725-3905
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news