Dear Fionnguala.
With the rectangular matrix you describe,
PREFSCAL will be your best option.
It can also handle more than one matrix,
i.e., individual differences,
although I do not think that is necessary.
Good luck.
Best regards, Frank
________________________________
From: SPSSX(r) Discussion on behalf of Fionnguala Sherry-brennan
Sent: Thu 01/02/2007 17:50
To:
[hidden email]
Subject: MDS - PROXSCAL/INDSCAL
Hello,
If anyone can help with the two related issues below I'd be very grateful.
1. Within the MDS program, PROXSCAL (in SPSS), are data that are entered as
ranks preserved within the machinations of the program so that individual
differences are taken into account? (Data are in the form of a rectangular
matrix where the variables in the columns are words (produced from word
association data) and rows are participant responses. Responses indicate
either absence (zero) or presence that reflects the order in which the words
were elicited (1 for first in the list to 7 at the end of the list.)
2. Previous research on word association data has used INDSCAL but this appears
to require the input of individual co-occurrence matrices in order to compare
differences between individuals that are subsequently reflected in the output
(creation of individual co-occurrence matrices being a very time consuming
task). Will analysis of the rank data in the rectangular matrix by PROXSCAL be
an adequate substitute?
Many thanks,
Fionnguala.
**********************************************************************
This email and any files transmitted with it are confidential and
intended solely for the use of the individual or entity to whom they
are addressed. If you have received this email in error please notify
the system manager.
**********************************************************************
Locked
