> -----Original Message----- > From: SAS(r) Discussion [mailto:SAS-L@LISTSERV.UGA.EDU] On Behalf Of Peter > Flom > Sent: Friday, January 21, 2011 6:41 PM > To: SAS-L@LISTSERV.UGA.EDU > Subject: Re: GLMSELECT procedure: Combination of SELECTION and STOP > options

> I usually find that the different criteria give similar > results. When they do not, then there is no clear choice as to which > model is "best", but that is usually the case anyway.

Perhaps it might be better to say, which model is the "least" bad?

I think the "clear" choice only comes through replication and refinement. In the cases the business decisions must be made, one can employ rigid protocols adhering to the "best" knowledge and still arrive at a spurious model.

Sometimes, even replication will not protect against that...

-Kevin

Kevin Viel, PhD Senior Research Statistician Patient Safety & Quality International College of Robotic Surgery Saint Joseph's Translational Research Institute

Saint Joseph's Hospital 5671 Peachtree Dunwoody Road, NE, Suite 330 Atlanta, GA 30342

(678) 843-6076: Direct Phone (678) 843-6153: Facsimile (404) 558-1364: Mobile kviel@sjha.org Confidentiality Notice: This e-mail, including any attachments is the property of Catholic Health East and is intended for the sole use of the intended recipient(s). It may contain information that is privileged and confidential. Any unauthorized review, use, disclosure, or distribution is prohibited. If you are not the intended recipient, please delete this message, and reply to the sender regarding the error in a separate email.