Date:         Wed, 10 Dec 2008 16:25:54 -0500
Reply-To:     "Whanger, J. Mr. CTR" <James.Whanger@med.navy.mil>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         "Whanger, J. Mr. CTR" <James.Whanger@med.navy.mil>
Subject:      Re: validating a logistic regression model
Comments: To: jp7837@yahoo.com
In-Reply-To:  A<117042.20858.qm@web59909.mail.ac4.yahoo.com>
Content-Type: text/plain; charset="iso-8859-1"

John,

Before proceeding, you may want to consider the logic underlying the notion of cross-validation. If the goal is to most accurately estimate population parameters that can later be used for probabilistic prediction, then a large sample that is representative of the population is the solution rather than reducing statistical power via sample splitting or bootstrapping.  When the sample size is large enough, bootstrapped parameter estimates will be roughly equivalent to non-bootstrapped.

However, because sample splitting cross-validation & bootstrapping are considered "best practice" you will likely need to be prepared to defend why a larger sample size provides the better estimate of population parameters relative to the other two methods.

Regards,

Jim


-----Original Message-----
From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of J P
Sent: Wednesday, December 10, 2008 3:33 PM
To: SPSSX-L@LISTSERV.UGA.EDU
Subject: validating a logistic regression model

Dear Colleagues,

I am attempting to learn  how to valide a logististic regression model. I've been reading about bootstrapping and cross validation, etc. But have found no instruction on how to actually conduct the anaysis and interpret the results. Any references on this subject or advice on how to perform this with SPSS is greatly appreciated.

Here is an example of what I am talking about....http://symptomresearch.nih.gov/chapter_8/sec7/cess7pg14.htm

Thanks!
John




=======
To manage your subscription to SPSSX-L, send a message to LISTSERV@LISTSERV.UGA.EDU (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
LISTSERV@LISTSERV.UGA.EDU (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