output regression coefficients from proc glm
in [SAS]
|
From: Takatsugu on 11 Dec 2009 14:49 Hi, This should be a very simple stuff. I am trying to spit out a list of regression coefficients and R- squares computed by segments. It seems that the output option in proc glm does not have coeff or r-square... I appreciate it if anyone could help me! Thanks
From: Dominic Mitchell on 11 Dec 2009 16:36 Hi, You can use "ODS output" to get the information you need: ods output "Solution"=parameters "Fit Statistics"=fit; proc glm data=hers; model glucose = exercise ; quit; run; As you will see, the "Solution" and "Fit Statistics" are found in your results tab. You can get a listing of all the tables created by ODS by using "ods trace on" and then running proc glm. The tables will get listed in you log: ods trace on; proc glm data=hers; model glucose = exercise ; quit; run; ods trace off; In this case, the trace option yields the following output: Output Added: ------------- Name: NObs Label: Number of Observations Template: STAT.GLM.NObsNotitle Path: GLM.Data.NObs ------------- Output Added: ------------- Name: OverallANOVA Label: Overall ANOVA Template: stat.GLM.OverallANOVA Path: GLM.ANOVA.GLUCOSE.OverallANOVA ------------- Output Added: ------------- Name: FitStatistics Label: Fit Statistics Template: stat.GLM.FitStatistics Path: GLM.ANOVA.GLUCOSE.FitStatistics ------------- Output Added: ------------- Name: ModelANOVA Label: Type I Model ANOVA Template: stat.GLM.Tests Path: GLM.ANOVA.GLUCOSE.ModelANOVA ------------- Output Added: ------------- Name: ModelANOVA Label: Type III Model ANOVA Template: stat.GLM.Tests Path: GLM.ANOVA.GLUCOSE.ModelANOVA ------------- Output Added: ------------- Name: ParameterEstimates Label: Solution Template: stat.GLM.Estimates Path: GLM.ANOVA.GLUCOSE.ParameterEstimates The other option is just to go straight to the results tab and get either the label or the name of the table needed. Note that when you use a label you need to quote the table name: ods output "Label of the table"=Data_set_name_you_want; Regards, Dominic. -----Original Message----- From: SAS(r) Discussion [mailto:SAS-L(a)LISTSERV.UGA.EDU] On Behalf Of Takatsugu Sent: Friday, December 11, 2009 2:49 PM To: SAS-L(a)LISTSERV.UGA.EDU Subject: output regression coefficients from proc glm Hi, This should be a very simple stuff. I am trying to spit out a list of regression coefficients and R- squares computed by segments. It seems that the output option in proc glm does not have coeff or r-square... I appreciate it if anyone could help me! Thanks
From: Sierra Information Services on 13 Dec 2009 19:44 Dominic has already suggested the ODS TRACE ON; statement to write the names of ODS output tables generated by a PROC step to the SASLOG. If you use the LISTING option to this statement (e.g., ODS TRACE ON / LISTING; then the names of the output tables are written to the output window (i.e., the LISTING destination) just before the output itself. In my experience, using the LISTING option makes it easier to figure out what's in which table rather than having to flip back and forth between the LOG and OUTPUT windows. Hope this helps... Andrew Karp Sierra Information Services http://www.sierrainformation.com On Dec 11, 1:36�pm, mitchel...(a)VIDEOTRON.CA (Dominic Mitchell) wrote: > Hi, > > You can use "ODS output" to get the information you need: > > ods output "Solution"=parameters "Fit Statistics"=fit; > proc glm data=hers; > model glucose = exercise ; > quit; > run; > > As you will see, the "Solution" and "Fit Statistics" are found in your > results tab. > > You can get a listing of all the tables created by ODS by using "ods trace > on" and then running proc glm. �The tables will get listed in you log: > > ods trace on; > proc glm data=hers; > model glucose = exercise ; > quit; > run; > ods trace off; > > In this case, the trace option yields the following output: > > Output Added: > ------------- > Name: � � � NObs > Label: � � �Number of Observations > Template: � STAT.GLM.NObsNotitle > Path: � � � GLM.Data.NObs > ------------- > > Output Added: > ------------- > Name: � � � OverallANOVA > Label: � � �Overall ANOVA > Template: � stat.GLM.OverallANOVA > Path: � � � GLM.ANOVA.GLUCOSE.OverallANOVA > ------------- > > Output Added: > ------------- > Name: � � � FitStatistics > Label: � � �Fit Statistics > Template: � stat.GLM.FitStatistics > Path: � � � GLM.ANOVA.GLUCOSE.FitStatistics > ------------- > > Output Added: > ------------- > Name: � � � ModelANOVA > Label: � � �Type I Model ANOVA > Template: � stat.GLM.Tests > Path: � � � GLM.ANOVA.GLUCOSE.ModelANOVA > ------------- > > Output Added: > ------------- > Name: � � � ModelANOVA > Label: � � �Type III Model ANOVA > Template: � stat.GLM.Tests > Path: � � � GLM.ANOVA.GLUCOSE.ModelANOVA > ------------- > > Output Added: > ------------- > Name: � � � ParameterEstimates > Label: � � �Solution > Template: � stat.GLM.Estimates > Path: � � � GLM.ANOVA.GLUCOSE.ParameterEstimates > > The other option is just to go straight to the results tab and get either > the label or the name of the table needed. �Note that when you use a label > you need to quote the table name: > > ods output "Label of the table"=Data_set_name_you_want; > > Regards, > > Dominic. > > > > -----Original Message----- > From: SAS(r) Discussion [mailto:SA...(a)LISTSERV.UGA.EDU] On Behalf Of > > Takatsugu > Sent: Friday, December 11, 2009 2:49 PM > To: SA...(a)LISTSERV.UGA.EDU > Subject: output regression coefficients from proc glm > > Hi, > > This should be a very simple stuff. > > I am trying to spit out a list of regression coefficients and R- > squares computed by segments. It seems that the output option in proc > glm does not have coeff or r-square... �I appreciate it if anyone > could help me! > > Thanks- Hide quoted text - > > - Show quoted text -
|
Pages: 1 Prev: transport format catalog from sas v6 to v9 Next: SAS vs. SPLUS vs. SAS |