home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!gatech!destroyer!gumby!wupost!spool.mu.edu!uwm.edu!ogicse!mimbres.cs.unm.edu!constellation!kittyhawk.ecn.uoknor.edu!prasundi
- From: prasundi@kittyhawk.ecn.uoknor.edu (Pankaj Raghavendra Asundi)
- Newsgroups: sci.math.stat
- Subject: SPLIT-SPLIT-PLOT LATIN SQUARE CODE NEEDED
- Message-ID: <Bz7n6C.9y@constellation.ecn.uoknor.edu>
- Date: 13 Dec 92 18:25:24 GMT
- Article-I.D.: constell.Bz7n6C.9y
- Sender: usenet@constellation.ecn.uoknor.edu (Usenet Administrator)
- Distribution: na
- Organization: Engineering Computer Network, University of Oklahoma, Norman, OK, USA
- Lines: 40
- Nntp-Posting-Host: kittyhawk.ecn.uoknor.edu
-
- Hi Netters;
- I have a design that looks like this and belongs to
- the category of " SPLIT-SPLIT-PLOT LATIN SQUARE DESIGN".
-
-
-
- Bo B1 B2
- ---------------
- C0 C1 C2
-
- S0 3 4 6
- A0 S1 1 4 6
- ---------------------------
- C2 C0 C1
-
- S0 3 4 6
- A1 S1 1 4 6
- --------------------------
- C1 C2 C0
-
- S0 3 4 6
- A2 S1 1 4 6
- ---------------------------
-
-
-
- I would like some help on coding this for SAS. Unfortunately the SAS manuals
- do not have an example that is similar do this.
- Please post on the net or e-mail to my address.
-
- Also can somebody help me with this question
- " why do we initially assume that the null is true rather than
- the alternative? what is the mathematical reason for this?
-
- Thanks in advance
-
- my e-mail address : prasundi@uokmax.ecn.uoknor.edu
-
-
-
-