https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35057#M1467 I had only looked some on the SAS software help. I looked at the SAS website just now and it says the output from the two PROCs should be the same, which is what I originally thought. So I'll have to check the code again but I could've sworn it's the same with both GENMOD and GLM.<BR /> <BR /> Actually it's not the regular GENMOD and GLM output that was different (I diidn't even check that actually) but rather the results from the ESTIMATE statements that were different. So maybe even though the procs give the same output in general they give different output on identical ESTIMATE statements, perhaps because different paramaterizations are used. I'll check into it but if anyone has any idea off the top of their heads please pipe up. Wed, 06 Jan 2010 04:24:03 GMT n6 2010-01-06T04:24:03Z https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35055#M1465 Hi,<BR /> I have a binary response data.Is it possible for me to use Proc Loess for fitting those Binary Response? If so, do I need to specify some where that response is binary? Mon, 28 Dec 2009 17:30:23 GMT https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35055#M1465 deleted_user 2009-12-28T17:30:23Z https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35056#M1466 TEchnically, it is possible to do by just scoring the dependent variable 0-1. However, it is not recommended, see<BR /> <A href="http://www.gotstat.com/category/SAS.aspx" target="_blank">http://www.gotstat.com/category/SAS.aspx</A> Tue, 05 Jan 2010 16:06:45 GMT https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35056#M1466 Doc_Duke 2010-01-05T16:06:45Z https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35057#M1467 I had only looked some on the SAS software help. I looked at the SAS website just now and it says the output from the two PROCs should be the same, which is what I originally thought. So I'll have to check the code again but I could've sworn it's the same with both GENMOD and GLM.<BR /> <BR /> Actually it's not the regular GENMOD and GLM output that was different (I diidn't even check that actually) but rather the results from the ESTIMATE statements that were different. So maybe even though the procs give the same output in general they give different output on identical ESTIMATE statements, perhaps because different paramaterizations are used. I'll check into it but if anyone has any idea off the top of their heads please pipe up. Wed, 06 Jan 2010 04:24:03 GMT https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35057#M1467 n6 2010-01-06T04:24:03Z https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35058#M1468 Oops, my response was meant to go in the GENMOD / GLM thread. I've copied it there. Please ignore it here. Sorry about that. Wed, 06 Jan 2010 04:50:57 GMT https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35058#M1468 n6 2010-01-06T04:50:57Z https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35059#M1469 You can use PROC GAM, rather than PROC LOESS, to fit a model to a logistic model to a binary response that includes loess- or spline-smoothed predictors. For details and examples, see the GAM documentation:<BR /> <BR /> <A href="http://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/gam_toc.htm" target="_blank">http://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/gam_toc.htm</A> Fri, 15 Jan 2010 19:03:19 GMT https://communities.sas.com/t5/Statistical-Procedures/Peoc-Loess-for-Binary-Response/m-p/35059#M1469 StatDave 2010-01-15T19:03:19Z