NetNews Usenet Archive 1992 #18/NN_1992_18.iso/spool/sci/math/stat/1709

Text File | 1992-08-20 | 1.8 KB | 36 lines

Newsgroups: sci.math.stat
Path: sparky!uunet!cs.utexas.edu!torn!cunews!nrcnet0!dgbt!ted
From: [e-mail] (Ted Grusec)
Subject: HELP - WITHIN-S ANOVA
Message-ID: <[e-mail]>
Organization: The Communications Research Centre
Date: Thu, 20 Aug 92 14:55:49 GMT
Lines: 26

My CSS:Statistica (Statsoft) program will not analyze a 2 X 10 X 13
within-subject design. It indicates a 252 dependent variable limit,
while this experiment has 260.  All of this despite a recent update
to release 3.1 which I got just days ago, the accompanying literature
to which says ridiculous things like "....the new architecture of
this module [referring to ANOVA/MANOVA] allows it to break
practically all design limitations and now supports analysis designs
which previously could not be computed on any microcomputer or
mainframe platform."!!! [Tech support at Statsoft tells me they were
really referring to Between- subjects designs!!!!]

I've had Statistica for several years and have very frequently run
into size limits which are not related to my generous-enough
computing resources (500 meg hard disk, 16 meg memory, 386, etc.) but
are strictly a function of the program. I usually wind up using the
truly marvellous |Stat program of Gary Perlman which at least gives
me a complete ANOVA table from which I can do the various internal
comparisons I need, albeit with some computational labour on my part.

Is there any commercial package that will do "large" within-subject
designs? Can someone share experiences, make recommendations?
--
==========================================================================
Ted Grusec    Communications Research Centre    (Govt. of Canada, DOC)
 3701 Carling Ave., Ottawa, Ont.K2H 8S2, CANADA  Internet: [e-mail]
  Compuserve: 73607,1576  [phone]   Fax [phone]