Automatic Scaling for Cluster Analysis

[dinom]

I am trying to run clustering on a 10 column, 10 case dataset. Two columns in the set are numerically much larger than the rest. Do I need to manually scale these columns or does SPSS do this automatically if I run the  Automatic Cluster Detection (From Direct Marketing Option)?


Thanks in advance,
Dino

[Art Kendall]

I do not have that module.  However, clustering is in the base module of SPSS.  Do you have that?

If you do, please describe you data. What is the nature of the cases?
What is the nature of the variables?  Level of measurement? Are they pretty much uncorrelated?

What are you asking for? A tree?  A single new nominal level variable?

Art Kendall
Social Research Consultants

On 11/23/2011 1:14 PM, dinom wrote:

I am trying to run clustering on a 10 column, 10 case dataset. Two columns in
the set are numerically much larger than the rest. Do I need to manually
scale these columns or does SPSS do this automatically if I run the
Automatic Cluster Detection (From Direct Marketing Option)?


Thanks in advance,
Dino

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Automatic-Scaling-for-Cluster-Analysis-tp5017546p5017546.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD