home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!spool.mu.edu!howland.reston.ans.net!paladin.american.edu!auvm!WATSON.BITNET!FOLGER
- Return-Path: <Folger@OLIVAW.watson.ibm.com>
- X-External-Networks: yes
- Message-ID: <9301282225.AA2409@OLIVAW.watson.ibm.com>
- Newsgroups: bit.listserv.stat-l
- Date: Thu, 28 Jan 1993 17:16:00 EST
- Reply-To: "Davis A. Foulger (914) 945-2077 (t. 862-2077)"
- <Foulger@WATSON.BITNET>
- Sender: STATISTICAL CONSULTING <STAT-L@MCGILL1.BITNET>
- From: FOLGER@WATSON.BITNET
- Subject: Re: Interactions
- In-Reply-To: <9301281536.AG0109@OLIVAW.watson.ibm.com>
- Lines: 25
-
- >Well, it seems to me that when you use an ANOVA, you engage in classic
- >ANOVA interaction thinking, otherwise you would use another technique.
-
- I wish that was true. Unfortunately, I don't think it is. I have seen far
- too many graduate programs whose idea of teaching statistical analysis and
- experimental design is to roll out, in order, Chi Squares, T-tests, and
- ANOVA. Occasionally folks graduate to MANOVA. Rarely is much more than
- handwaving done over regression. Most people don't engage in class ANOVA
- interaction thinking because they have selected it. They select it because
- its all they know.
-
- >The whole point to the ANOVA is the conditionality of the statement. If
- >you have an interaction, you can't make an unconditional statement.
-
- I don't agree. Interactions are not subsidiary effects. They are effects
- in and of themselves which, when shaped correctly, can be interpreted
- independently of the main effects. If all one does with an interaction is
- to say that you can no longer make an unconditional statement about
- the main effects, one probably hasn't done a complete analysis.
-
- Davis
-
- Snailmail..........................Davis A. Foulger
- Internet: FOLGER@WATSON.IBM.COM IBM T.J. Watson Research Center
- Prodigy: XFRR20A P O Box 218, Yorktown Ht, NY 10598
-