Date:         Tue, 12 Feb 2008 01:49:36 -0800
Reply-To:     chichibibi <bilbo.vador@HOTMAIL.FR>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         chichibibi <bilbo.vador@HOTMAIL.FR>
Organization: http://groups.google.com
Subject:      Re: Scheirer Ray Hare test
Comments: To: sas-l@uga.edu
Content-Type: text/plain; charset=GB2312

Hi!

and thanks a lot for informations you gave to me
Ashley, I've already compute parametric anova on rank data and this
solution looks great because of the variances. But I'm not completely
sure that it is allowed to use 2-way parametric anova with rank data.
So I take a look on your instructions for SPSS and MINITAB and I'll
post a new message later with "2-way parametric anova with rank data,
is it allowed?" in header.

And Dennis I found THE article about Scheirer Ray Hare test which is:
"The Analysis of ranked Data Derived from Completely Randomized
Factorial Designs", C. James Scheirer, William S. Ray and Nathan Hare,
Biometrics 32, 429-434, June 1976. So Art was right beacuse it's an
extension of Kruskal-Wallis test.

But if somebody knows something about how to compute scheirer ray hare
test with SAS software or something else, further information, don't
hesitate to post a message

have a good day and thanks a lot for advance


On 11 f¨¦v, 17:56, art...@NETSCAPE.NET (Arthur Tabachneck) wrote:
> Dennis,
>
> According to at least one source, it is an extension of the Kruskal-Wallis:http://xrl.us/bfz3x
>
> Art
> -----
> On Mon, 11 Feb 2008 08:12:47 -0800, Dennis G. Fisher, Ph.d.
>
>
>
>
>
> <dfis...@CSULB.EDU> wrote:
> >I am also very curious about this.  The only tests that I know of that
> >are remotely like what you are asking about
> >are the Kruskal-Wallis one-way ANOVA and the Friedman's test, but both
> >of those are not exactly what you
> >are asking about.
> >Dennis Fisher
>
> >chichibibi wrote:
> >> Sorry Peter, I made a mistake: by "ordinary" I wanted to say
> >> "ordinal"!!
> >> And you're right because ordinary means in french "ordinaire" whereas
> >> ordinal means in french "ordinal"
> >> and therefore my question is: is it possible to use 2-way parametric
> >> anova with ordinal variables?
> >> thanks a lot and again sorry for misunderstanding
>
> >> On 11 fúI 12:32, peterflomconsult...@mindspring.com (Peter Flom)
> >> wrote:
>
> >>> chichibibi <bilbo.va...@HOTMAIL.FR> wrote
>
> >>>> Hi everybody!
>
> >>>> Does anybody know something about this test?
> >>>> it's the analog of two-way parametric anova model, isn't it?
>
> >>> Never heard of it
>
> >>>> How to compute it with SAS software?
> >>>> Something else, is it possible to use 2-way anova with ordinary
> >>>> variables?
>
> >>> What do you mean by 'ordinary' variables? I notice your e-mail is from
>
> France, could this be a translation issue around 'normal variable'?
>
>
>
>
>
> >>> Peter
>
> >--
> >Dennis G. Fisher, Ph.D.
> >Professor and Director
> >Center for Behavioral Research and Services
> >California State University, Long Beach
> >1090 Atlantic Avenue
> >Long Beach, California 90813
> >562-495-2330 x121
> >562-983-1421  fax
> >www.csulb.edu/centers/cbrs- Masquer le texte des messages pr¨¦c¨¦dents -
>
> - Afficher le texte des messages pr¨¦c¨¦dents -- Masquer le texte des messages pr¨¦c¨¦dents -
>
> - Afficher le texte des messages pr¨¦c¨¦dents -