home *** CD-ROM | disk | FTP | other *** search
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- Path: sparky!uunet!paladin.american.edu!auvm!UNC.BITNET!UPHILG
- Message-ID: <STAT-L%92090810132475@VM1.MCGILL.CA>
- Newsgroups: bit.listserv.stat-l
- Date: Tue, 8 Sep 1992 10:13:00 EDT
- Sender: "STATISTICAL CONSULTING" <STAT-L@MCGILL1.BITNET>
- From: "Philip Gallagher,(919)966-1065" <UPHILG@UNC.BITNET>
- Subject: Kerlinger & continuous likert scales
- Lines: 50
-
- mike, mgranaas@charlie.usd.edu, wrote, in part,
-
- > I was told a few years back that a likert scale could be made continuous
- > by using a line with anchors at each end rather than the traditional
- > 5 (or 7 or 9) point scale. Instead of picking a number between 1 and 5,
- > the respondent marks a point along the line and the researcher measures
- > the distance from the mark to one of the anchors to obtain a score.
- >
- > e.g.
- >
- > ___________________________/________________________
- > Always Never
- >
- > Does anybody know if this in fact works? References where I can learn more?
- >
-
- Try Fred Kerlinger's "Foundations of Behavioral Research".
-
- It's frightfully old (at least MY edition is!), but you should have
- mastered it before you go beating the bushes for the the newer, fancier
- materials.
-
- As an undocumented aside, my memory from courses in the late Sixties
- is that it helps people to give them some numerical hints on the
- scale (more than just the ends, but I can't remember the rules),
- along with some unequivocally forceful instructions and
- examples that show them that they need not restrict their answers
- to categorical responses, that you intend to look at their answers
- with a ruler, not just a few categories. I suspect this technique
- is still valid, but perhaps the psychometric gurus amongst us
- will know a whole lot better by now.
-
- Examples:
-
- ________________________________________________X____________
- BAD NEUTRAL GOOD
-
-
-
- _____________X_______________________________________________
- -1 0 +1
-
- Please don't forget, however, that this technique means that
- someone is going to have to go through the instrument and
- measure/score every answer. It's often worth doing it that
- way, but don't forget to budget the time and money.
-
-
- Phil Gallagher
- uphilg@unc
-