home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!stanford.edu!bu.edu!wupost!gumby!yale!yale.edu!news.yale.edu!mars.caps.maine.edu!maine.maine.edu!cunyvm!psuvm!auvm!UNCVM1.BITNET!WDAVIS
- From: WDAVIS@UNCVM1.BITNET (Walter Davis)
- Newsgroups: bit.listserv.stat-l
- Subject: Re: Normal probability plots
- Message-ID: <STAT-L%92111717023867@VM1.MCGILL.CA>
- Date: 17 Nov 92 21:53:10 GMT
- Sender: "STATISTICAL CONSULTING" <STAT-L@MCGILL1.BITNET>
- Lines: 28
- Comments: Gated by NETNEWS@AUVM.AMERICAN.EDU
- In-Reply-To: Message of Tue,
- 17 Nov 1992 09:40:00 PST from <CHAMBERLINC@AXE.HUMBOLDT.EDU>
-
- On Tue, 17 Nov 1992 09:40:00 PST Charles Chamberlin said:
- >Shapiro,Wilk,and Chen(1968) JASA 63:1343-1372 report an empirical
- >comparison of alternative methods for testing for normality. The
- >methods they compare include the chi-squared test, the Kolmogorov-
- >Smirnov test, as well as the Shapiro-Wilk test. 45 alternative
- >distributions in 12 families and five sample sizes were studied.
- >Overall, the S-W test was most powerful.
- >It also can be applied to small sample sizes.
- >
-
- There is a chapter by D'Agostino in a book by D'Agostino and
- Stephens titled _Goodness of Fit Techniques_ - the chapter is
- all about tests for the normal distribution and includes tests
- for univariate and multivariate normality. Bollen _Structural
- Equations with Latent Variables_ has a brief section on
- tests of univariate and multivariate normality and presents
- the tests which D'Agostino found worked best. I have written
- a SAS macro which uses SAS/IML to perform the tests presented
- in Bollen. If you'd like a copy, drop me a note (for those
- of you who have already dropped me a note, everything will
- be on the way soon).
-
- hope this helps,
-
- Walter Davis <WDAVIS@UNCVM1>
- Department of Sociology
- Institute for Research in Social Science
- UNC - Chapel Hill
-