My apologies if I don't understand, but ranks/counts would strike me as
being quantitative (i.e., differing in amount) as opposed to qualitative
(i.e., differening in kind). If so, there would be no particular problem
presented with the data set.
Jeff Rasmussen, PhD
The Art of The Experiment:
experimental design and statistics tutorial cd-rom
http://symynet.com/educational_software
----- Original Message -----
From: "Anputhas, Markandu (IWMI-HQ)" <[log in to unmask]>
To: <[log in to unmask]>
Sent: Thursday, August 15, 2002 2:37 AM
Subject: cluster analysis
> Dear all,
>
> I am currently dealing with a Socio-economic study data where i wnat to do
> cluter analysis to make diffrent groups based on the data what i have.The
> problem in my mind is the data set containing both qulitative (ranks /
> counts) as well as quantitative (conituous variable or measures) can be
used
> to this purpose.Please forard your suggestion.It would be greatful if you
> code some refrence for this.
>
> Thanks in advance.
>
> M.Anputhas
> International Water Management Institute,
> 127,Sunil Mawatha,Pelawatta,
> Battaramulla,Sri Lanka.
> TP.94-1-787404
> Fax:-94-1-786854
> Website: www.iwmi.org <http://www.iwmi.org/>
>
|