Date: Fri, 7 Mar 2008 12:22:47 -0600
Reply-To: "data _null_," <datanull@GMAIL.COM>
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: "data _null_," <datanull@GMAIL.COM>
Subject: Re: Principal Component Analysis on Mixed data
Content-Type: text/plain; charset=ISO-8859-1
It looks like they made a procedure...
The PRINQUAL (principal components of qualitative data) procedure is a
data transformation procedure that is based on the work of Kruskal and
Shepard (1974); Young, Takane, and de Leeuw (1978); Young (1981); and
Winsberg and Ramsay (1983). You can use PROC PRINQUAL to
generalize ordinary principal component analysis to a method capable
of analyzing data that are not quantitative
perform metric and nonmetric multidimensional preference (MDPREF)
analyses (Carroll 1972)
preprocess data, transforming variables prior to their use in other
summarize mixed quantitative and qualitative data and detect nonlinear
reduce the number of variables for subsequent use in regression
analyses, cluster analyses, and other analyses
On Fri, Mar 7, 2008 at 10:07 AM, Dennis G. Fisher, Ph.d.
> I remember that there used to be a PRINQUAL macro that might be of some
> value here
> if you can find it.
> Dennis Fisher
> cat.. wrote:
> > Hi there,
> > I need to represent graphically a set of patients characterized by
> > both continuous and categorical variables. Ordinal categorical
> > variables such as scales can be processed as continuous ones but for
> > other types of categorical variables, I should normally not include
> > them in a PCA.
> > I was wondering what would be the results if I just transform each
> > categorical ones into several indicators (ex Sex Male/Female by Male
> > Yes/No) and include them as any continuous character in the PCA.
> > Has one ever tried that ?
> > What do you think ?
> > Cheers,
> > Catherine.
> 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