home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!gatech!paladin.american.edu!auvm!UGA.BITNET!FDANE
- Message-ID: <STAT-L%92090916175805@VM1.MCGILL.CA>
- Newsgroups: bit.listserv.stat-l
- Date: Wed, 9 Sep 1992 14:39:55 EDT
- Sender: "STATISTICAL CONSULTING" <STAT-L@MCGILL1.BITNET>
- From: Frank Dane <FDANE@UGA.BITNET>
- Subject: Re: likert scales and ordinal and interval measurement
- In-Reply-To: Message of Tue, 8 Sep 1992 17:02:11 EDT from <ELLEN@PACEVM>
- Lines: 18
-
- Art Ellen asksif it makes sense to sum two apparently different items,
- e.g. I am sometimes blue and I am depressed daily, to arrive at a
- total score. IF the correlation is high enough, then it does make sense.
- Given thesetwo sample items, one would not expect the correlation between
- them to be very high. But the point of scaling is to determine what
- consistencies lie in the subjects' responses to the items. If a
- sufficient number of subjects see these two items as related, then
- one's own expectations about the items must bechalked up to differing
- phenomenological outlooks. Perhaps the subjects think being "blue"
- and being "depressed" are very different things, and that things are
- very bad if they are feeling both.
-
- Dr. Francis C. Dane, Associate Professor and Chair
- Department of Psychology, Mercer University
- Macon, GA 31207-0001 USA
- Bitnet: FDANE@UGA Internet: FDANE@UGA.CC.UGA.EDU
- Tel: (912) 752-2972
- Fax: (912) 752-2108
-