home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!paladin.american.edu!auvm!WUBIOS.WUSTL.EDU!PHIL
- Return-Path: <@OHSTVMA.ACS.OHIO-STATE.EDU:phil@wubios.wustl.edu>
- Return-Path: <phil@wubios>
- X-Mailer: ELM [version 2.4 PL20A]
- Mime-Version: 1.0
- Content-Type: text/plain; charset=US-ASCII
- Content-Transfer-Encoding: 7bit
- Content-Length: 990
- Message-ID: <9301221956.AA22652@wubios>
- Newsgroups: bit.listserv.sas-l
- Date: Fri, 22 Jan 1993 13:56:26 -0600
- Reply-To: "J. Philip Miller" <phil@WUBIOS.WUSTL.EDU>
- Sender: "SAS(r) Discussion" <SAS-L@UGA.BITNET>
- From: "J. Philip Miller" <phil@WUBIOS.WUSTL.EDU>
- Subject: Performance of Proc MIXED
- Comments: To: SAS Mailing List <SAS-L@ohstvma.ircc.ohio-state.edu>
- Lines: 26
-
- While doin some analyses using the Beta OS/2 version of PROC MIXED, we noted
- that
-
-
- > The program * sample sizes: *
- > PROC MIXED METHOD=REML; * BELT n *
- > CLASS BELT STATION; * . 7249 *
- > MODEL MAP = BELT/ SOLUTION; * 0 2093 *
- > RANDOM STATION(BELT); * 1 2594 *
- > FORMAT BELT BLT. *******************
- > RUN;
- > took 26 minutes to run. The same program with the addition of
- > WHERE BELT IN (0 1);
- > took 6 minutes. The results were the same.
- >
-
- Now this is wall time and we know that disk i/o can have a major effect, but
- this seems a little strange. Anyone else noticed similar results?
-
- -phil
-
-
- --
- J. Philip Miller, Professor, Division of Biostatistics, Box 8067
- Washington University Medical School, St. Louis MO 63110
- phil@wubios.WUstl.edu - (314) 362-3617 [362-2694(FAX)]
-