06-22-2012 06:21 AM
I'm trying to assess model calibration using modified H–L χ2 statistic according to equation (3.2) or (3.50) written in the following reference:
Now I 'm writing a sas macro to estimate the modified H–L statistic .
And I want to check my sas code if there any other sas macros available or published.
I would be very grateful if someone would give me information about this.
Thanks in advance,
06-22-2012 11:22 AM
Since most of use aren't going to $30 to read the text of the article you might need to find another reference.
What does the H-L stand for? We may be able to find another source.
06-22-2012 10:21 PM
Thank you for your reply and I apologize my explanation was not enough.
The H-L statistic stands for the Hosmer-Lemeshow statistic and you can view the reference article at the following link (though it might be the draft version):
Your continued support will be greatly appreciated.
06-27-2012 01:28 PM
Does http://www.ats.ucla.edu/stat/sas/seminars/sas_logistic/logistic1.htm help at all? This page has an example with PROC LOGISTIC.
06-28-2012 12:32 AM
Than you for your continued help.
Yes, I know the conventional Hosmer-Lomeshow test for binary data can be conducted with lackfit specification in Proc Logistic.
But I want to conduct the modified one for survival data. D'Agostino and Nam introduced it and a lot of authers have been refering to this article. So I think SAS macro code can be available or published.
06-28-2012 12:19 AM
Thank you for your reply.
I'm sorry for trouble you.
Could you refer to the following article?
06-28-2012 12:39 PM