st: develop outcome risk stratification scale

[Haluk Vahaboglu <vahabo@hotmail.com>]

P { margin-bottom: 0.21cm; }


Hi all,
I am using stata 12.1 and
currently working on a database of 500 patients. My principle purpose
is to develop an “outcome risk stratification scale”. The outcome
is dichotomous; “1” assigned to died patients and “0” to
survived. I picked up 450 patients randomly for the developing stage
and left 50 for validation.
I am planning to get
independent predictors from a logistic model and assign scores to
these variables according to their coefficients.
My questions are:
1. Is this a valid
strategy to develop an outcome scale?
2. Is there a practical 
way (using statistics-mathematics) to assign scores to variables
(translate coefficients to scores)?
Any help will be highly
appreciated.



p.s. I would like to kindly remind that
I do not have a background in statistics/mathematics (could not found an expert around here so have to do it myself) 




Haluk Vahaboglu, MD
Prof in Inf Dis & Clin Micro 		 	   		  

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/