https://communities.sas.com/t5/Statistical-Procedures/Can-you-do-Alternating-Logistic-Regression-with-Glimmix-or-just/m-p/69353#M3355 Sorry I was not clear, but you interpreted me correctly. Thanks. Message was edited by: proctice Thu, 10 Feb 2011 17:05:12 GMT proctice 2011-02-10T17:05:12Z https://communities.sas.com/t5/Statistical-Procedures/Can-you-do-Alternating-Logistic-Regression-with-Glimmix-or-just/m-p/69351#M3353 Is there a command like logor= that makes glimmix give odds ratios instead of variance covariance? Fri, 04 Feb 2011 22:08:43 GMT https://communities.sas.com/t5/Statistical-Procedures/Can-you-do-Alternating-Logistic-Regression-with-Glimmix-or-just/m-p/69351#M3353 proctice 2011-02-04T22:08:43Z https://communities.sas.com/t5/Statistical-Procedures/Can-you-do-Alternating-Logistic-Regression-with-Glimmix-or-just/m-p/69352#M3354 It is not clear what you are asking.I think you are asking if you can specify the covariance matrix for subjects in terms of the Carey/Zeger/Diggle ALR method (strictly for binary data). As far as I know, GLIMMIX does not have this capability, although GLIMMIX does have many possible covariance structures, specified with type= option on a random statement. Thu, 10 Feb 2011 16:59:37 GMT https://communities.sas.com/t5/Statistical-Procedures/Can-you-do-Alternating-Logistic-Regression-with-Glimmix-or-just/m-p/69352#M3354 lvm 2011-02-10T16:59:37Z https://communities.sas.com/t5/Statistical-Procedures/Can-you-do-Alternating-Logistic-Regression-with-Glimmix-or-just/m-p/69353#M3355 Sorry I was not clear, but you interpreted me correctly. Thanks. Message was edited by: proctice Thu, 10 Feb 2011 17:05:12 GMT https://communities.sas.com/t5/Statistical-Procedures/Can-you-do-Alternating-Logistic-Regression-with-Glimmix-or-just/m-p/69353#M3355 proctice 2011-02-10T17:05:12Z