This announcement is a call for "beta testers" of
an S function/C engine that has recently been
revised.  Persons interested in testing the code,
which is supplied as source code in C and S, with
installation tools for UNIX platforms,
can e-mail carey@hsph.harvard.edu.  The code will
be supplied as a uuencoded gzipped shar.

The aim of beta testing is to trap problems before
the code is submitted to statlib, and to observe
the behavior of the programs on platforms other than
those on which it was developed.  Comments on 
other aspects of program functionality will also
be considered.  The function is discussed below.

New Features of 4.x: better memory management
(thanks to Bill Dunlap), cloglog link (thanks to
John Maindonald)

--------------------------------------------------

The "gee" S function/C engine for solving Generalized
Estimating Equations (Liang and Zeger, 1986) has been
revised.

NEW FEATURES: 1) support of model formulae with glm
family objects; 2) elimination of many redundant
computations in the cgee engine; 3) initialization
of regression parameter estimates via glm(); improved
output summary format; 4) installation governed by
CHAPTER utilities; 5) errorbranching handled by longjmp
back to S so that if the model fit fails, control
is handed back to S; the previous version would exit(1)
from C back to UNIX; 6) scale parameter estimation
improved for compatibility with glm(); scale parameter
may be given a fixed value.
 
NOTE: glm()-Family functionality is not fully supported.
The family objects are searched for names of component
functions, but the functions themselves are not
used by the gee engine.  Full use of family objects
is planned in a future rewrite of the code.
 
TEST BEDS: Splus 3.1 under SunOS 4.1.3 with gcc 2.3.3;
Splus 3.1 under ULTRIX 4.3A with gcc 2.5.7.  Loading
problems have been reported with HP workstations.

COPYING: The software is distributed under the terms of
the GNU general public license.  No warranty on software
performance or support, but we attempt to seek out
unknown problems, and solve or notify users about known 
problems.

DISTRIBUTION: After a testing period, the software
will be made available through STATLIB (lib.stat.cmu.edu).
