Date: Wed, 8 Jan 1997 16:22:37 -0500
Reply-To: "William B. Ware" <wbware@EMAIL.UNC.EDU>
Sender: "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From: "William B. Ware" <wbware@EMAIL.UNC.EDU>
Subject: Re: transforming data
In-Reply-To: <Pine.SUN.3.91.970108183312.25647D-100000@altair.herts.ac.uk>
Content-Type: TEXT/PLAIN; charset=US-ASCII
Diana,
Perhaps I made my remarks with out providing an appropriate context. I
am in my 29th year of teaching applied statistics at the university level.
During that time, I have taught using SPSS, SAS, BMDP, SYSTAT, MYSTAT, and
STATA. From the perspective of the learner, I have found over the years
that the manuals written for SPSS, especially those by Norusis, are
superior to any that accompany or that are associated with any other
system. While it is true that some of the other packages are well
documented, the technical level of documentation often appears to assume
familiarity with the system... a sort of "Catch-22" situation for the
neophyte.
WBW
______________________________________________________________________________
William B. Ware, Professor and Chair Educational Psychology
CB# 3500 EMAIL: wbware@unc.edu
University of North Carolina PHONE: (919)-966-5266
Chapel Hill, NC 27599-3500 FAX: (919)-962-1533
URL:http://www.unc.edu/~wbware/
______________________________________________________________________________
On Wed, 8 Jan 1997, Diana Kornbrot wrote:
>
> i am no neeophyte and SPSS documentation rivals MICROSOFT in its
> clumsiness and lack of crucial detail.
>
> here is a list of packages that are both easier to use and better documented:
>
> powerful general packages
> SYSTAT
> SAS
>
> good general packages covering most procedures
> STATVIEW/SUPERANOVA on MAC good grpahics but no loglinear & logistic
> regression, als has quality control
> JMP from SAS MAC or PC good graphics, excellent exploratory
> including identifying outliers & using/not outliers
> also hazards and qulaity control
> JMP IN shrink-wrapped book with discs $50 or #28 from
> Duxbury Press. as JMP but no cluster analysis
> some othe procedure v. slightly less features
> MINITAB MAC & PC good workhorse
>
> its simply NOT true that SPSS as a package or as to its docimentation is
> the best achievable.
> it is also unnecessarily fragile and meory hungry. i suspect that is
> because its basic architecture hasn't changed since its creation.
> even then some software engineers knew about modularisation!
>
> diana kornbrot
>
>
>
>
>
>
>
>
> On Wed, 8 Jan 1997, William B. Ware wrote:
>
> > On Sun, 5 Jan 1997, Kylesma wrote:
> >
> > > Ok- here is a question that probably seems rather simple for you who have
> > > much more experience with SPSS than I, but as a neophyte I am in desperate
> > > need of some of your expertise since the documentation for this package
> > > leaves something to be desired.
> >
> > Julie,
> >
> > If you think that the documentation for SPSS "leaves something to be
> > desired," then you are _truly" a neophyte! Actually, SPSS has a long
> > history of being the best documented statistics package available! You
> > need to look at some of the others!!!
> >
> > :)
> >
> >
> > > I have a distribution which is slightly, negatively skewed. How do I
> > > convert or transform the data to a normal distribution so I can then
> > > properly analyse it????
> >
> > Can you tell me more about the problem? What is the measure of skew?
> > What is the standard error? Is there only one group, or are there more?
> > What do you consider to be a "proper" analysis? In short, if you can tell
> > "us" more about your problem and its greater context, I am certain that
> > "we" can give you some more specific suggestions...
> >
> >
> > ______________________________________________________________________________
> >
> > William B. Ware, Professor and Chair Educational Psychology
> > CB# 3500 EMAIL: wbware@unc.edu
> > University of North Carolina PHONE: (919)-966-5266
> > Chapel Hill, NC 27599-3500 FAX: (919)-962-1533
> >
> > URL:http://www.unc.edu/~wbware/
> > ______________________________________________________________________________
> >
>
| 
