Date: Tue, 4 Nov 2003 14:09:59 -0600
Reply-To: Thompson Bill T Contr USAFSAM/FEC <Bill.Thompson@BROOKS.AF.MIL>
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: Thompson Bill T Contr USAFSAM/FEC <Bill.Thompson@BROOKS.AF.MIL>
Subject: Re: Transforming data
Content-Type: text/plain; charset="iso-8859-1"
Peter,
These 36 variables are actually part of a 3x3x2x2 repeated measures design.
time x light x screen x eye
These variables represent "contrast sensitivity" values taken at baseline,
and then 12 months and 24 months post refractive surgery. The issue has
been raised as to wether or not we should analyze the "contrast sensitivity"
values or the "log contrast sensitivity" values. These are continuous data.
The data was analyzed as a repeated measures design described above using
the "raw" contrast sensitivity data.
Thanks for your help and I hope this further explains the data.
Bill
-----Original Message-----
From: Peter Flom [mailto:flom@NDRI.ORG]
Sent: Tuesday, November 04, 2003 1:56 PM
To: SAS-L@LISTSERV.UGA.EDU
Subject: Re: Transforming data
The first question is what you are going to do with these 36 variables.
e.g. are
they going to be independent variables in a regression? Are they of
interest in themselves?
Are they going to be a part of a factor analysis? Or what?
The second question is what these variables ARE. Are they counts?
Scores on
something? Continuous? Discrete? or what?
Without knowing this, it's hard to recommend anything.
HTH
Peter
Peter L. Flom, PhD
Assistant Director, Statistics and Data Analysis Core
Center for Drug Use and HIV Research
National Development and Research Institutes
71 W. 23rd St
www.peterflom.com
New York, NY 10010
(212) 845-4485 (voice)
(917) 438-0894 (fax)
>>> Thompson Bill T Contr USAFSAM/FEC <Bill.Thompson@BROOKS.AF.MIL>
11/4/2003 2:24:08 PM >>>
I have 36 variables of which I perfromed Shapio-Wilks normality test
on. Of
those 36 variables there were 5 that were "not" normally distributed
and
when log transformed they became normally distributed. There were 3
that
remained "not" normally distributed, however, there were alos 2
variables
that "were" normally distributed that when transformed became "not"
normally
distributed.
My question is as follows: What considerations should be addressed
when
this situation happens. Do I transform all the data even if a couple
of
variables become non-normal or do I just leave the data as is and
analyze.
This is my first encounter with this situation so forgive my
ignorance.
Bill Thompson
