A case is a row of data, and respondents are just those that responded to
the event. In the data I am looking at here, we have about a 2% response
rate, so 2 in 100 cases are flagged as having responded.
It looks like the tree procedure can control for minimum row cardinality,
but I am looking to control for minimum response count.
Thanks in advance.
Scott Carl, Principal
Tricision, Inc.
P.O. Box 2147
Granite Bay, CA 95746
(916) 652-9317 Work
(916) 759-6910 Mobile
[hidden email]
-----Original Message-----
From: Oliver, Richard [mailto:
[hidden email]]
Sent: Monday, October 20, 2008 12:04 PM
To: Scott Carl;
[hidden email]
Subject: RE: Decision Tree Question
I'm not sure I understand the distinction in this context. What is the
difference between a "case" and a "respondent" in your data?
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of
Scott Carl
Sent: Saturday, October 18, 2008 5:49 PM
To:
[hidden email]
Subject: Decision Tree Question
Hello,
In looking into the tree procedure, I see where we can control for minimum
cases within each node using the growthlimit subcommand. I am looking for
minimum respondents within each node, rather than minimum cases. Does
anyone know how to accomplish this? Thanks in advance.
=====================
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
Locked
