🚀 go-pugleaf

I was analyzing a large but somewhat sparse contingency
table on BMDP 4F.  I noticed, almost by accident, that the program was
not calculating the degrees-of-freedom for some log-linear models correctly.
(How many users of log-linear models routinely verify df's?  How many 
know *how*?)

A bit of playing around convinced me that the problem was due to the
sparseness of the table. If I collapsed enough categories the df were
correct.  I could find nothing in the manual about how df's are
calculated, but I had a hunch that it was assuming that some zeroes were
structural.  Finally, I came upon an almost parenthetical comment in the
1990 manual p.304:

"We recommend that you add a constant to all cells when you have empty
cells in your data that are not to be treated as structural zeros. 
Otherwise, some of the analyses ARE NOT PERFORMED CORRECTLY."

[emphasis added]

I have just told my class that BMDP has one of the best log-linear
programs around.  Now I wonder if that was bad advice.


>>>>>>>>>>>>>>>>>>>bickis@math.usask.ca<<<<<<<<<<<<<<<<<<<<<<<<<<<
Mik Bickis       \,,,       .*#*.  \    University of Saskatchewan
Department of        \,,,  ^\\|//^  ```\   Saskatoon, Saskatchewan
Mathematics & Statistics \   )|(        ```\   Canada      S7N 0W0
<<<<<<<<<<<<<<<<<<<S|A|S|K|A|T|C|H|E|W|A|N|>>>>>>>>>>>>>>>>>>>>>>>