topic How to run diagnostics for logistic regression in SAS Procedures https://communities.sas.com/t5/SAS-Procedures/How-to-run-diagnostics-for-logistic-regression/m-p/106566#M29692 <HTML><HEAD></HEAD><BODY><P>Proc glimmix data = cool plots=all;</P><P>Class a1 a2 a3 a4;</P><P>Model a1 = a2/ dist = binomial&nbsp; s ddfm = kr;</P><P>Random a3/ subject = a4 residual type = cs;</P><P>run;</P><P></P><P>Is there a way you can get the deviance and goodness of fit from proc glimmix?</P></BODY></HTML> Fri, 12 Apr 2013 16:58:01 GMT coollord 2013-04-12T16:58:01Z How to run diagnostics for logistic regression https://communities.sas.com/t5/SAS-Procedures/How-to-run-diagnostics-for-logistic-regression/m-p/106566#M29692 <HTML><HEAD></HEAD><BODY><P>Proc glimmix data = cool plots=all;</P><P>Class a1 a2 a3 a4;</P><P>Model a1 = a2/ dist = binomial&nbsp; s ddfm = kr;</P><P>Random a3/ subject = a4 residual type = cs;</P><P>run;</P><P></P><P>Is there a way you can get the deviance and goodness of fit from proc glimmix?</P></BODY></HTML> Fri, 12 Apr 2013 16:58:01 GMT https://communities.sas.com/t5/SAS-Procedures/How-to-run-diagnostics-for-logistic-regression/m-p/106566#M29692 coollord 2013-04-12T16:58:01Z Re: How to run diagnostics for logistic regression https://communities.sas.com/t5/SAS-Procedures/How-to-run-diagnostics-for-logistic-regression/m-p/106567#M29693 <HTML><HEAD></HEAD><BODY><P>Try with Proc Logistic as follow...</P><P></P><P>Proc Logistic data = cool descending;</P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; model a1 = a2 / DEVIANCE LACKFIT;</P><P>quit;</P><P></P><P>If you want to predict the probability of success based on catogrical response variable then i think Proc Logistic is best to use, you dont need to specify BINOMIAL option on MODEL statement...</P><P></P><P>-Urvish</P></BODY></HTML> Sat, 13 Apr 2013 12:30:31 GMT https://communities.sas.com/t5/SAS-Procedures/How-to-run-diagnostics-for-logistic-regression/m-p/106567#M29693 UrvishShah 2013-04-13T12:30:31Z