Colleagues –
I
sincerely appreciate suggestions and references provided by Chris Baker and John
MacCuish on this issue! Looks like I have to do a little more reading on this. Any
suggestion and comment is highly appreciated.
Thanks!
Arun Bhattacharyya
AT&T Labs, Research
Florham Park, NJ 07932
(973) 236-6613
-----Original Message-----
From: s-news-owner@lists.biostat.wustl.edu
[mailto:s-news-owner@lists.biostat.wustl.edu] On
Behalf Of Bhattacharyya, Arunava, ALABS
Sent: Wednesday, May 03, 2006 8:25
PM
To: s-news@lists.biostat.wustl.edu
Subject: [S] MDS on longitudinal
data
This is not a S+ question, but I fee
this the right group to seek help form.
I am trying to find good references
- both theory and applications - on how to use MDS on longitudinal data where N
is slightly bigger than T. I a have data on 30 units over 24 time points. New
variables are entering into the dataset (which makes it richer over time) over
time as technology changes. I like to see how cluster/groups
membership of these 30 units are changing over time. I am
familiar with MDS on cross-sectional data, but in this analysis I
like to measure change in group composition over time.
Any help on this is high;y
appreciated. As I mentioned I like to get references on theory and
applied work in this area.