topic Second order autoregressive covariance structure in multilevel model in Statistical Procedures https://communities.sas.com/t5/Statistical-Procedures/Second-order-autoregressive-covariance-structure-in-multilevel/m-p/138701#M7234 <HTML><HEAD></HEAD><BODY><P>Does SAS have the native ability to implement a second order autoregressive covariance structure within either PROC MIXED or PROC GLIMMIX?&nbsp; I am aware that I can specify a first order autoregressive structure with TYPE = AR(1) on either the RANDOM or REPEATED statement line.&nbsp; However, using AR(2) returns and error of <SPAN style="color: #222222; font-family: arial, sans-serif; background-color: #ffffff;">"Invalid order specification"</SPAN>.</P><P></P><P>I am surprised that AR(2) does not appear to be a valid function.</P><P></P><P>Thanks,</P><P>Matt</P></BODY></HTML> Wed, 30 Apr 2014 02:08:35 GMT mtaetntan 2014-04-30T02:08:35Z Second order autoregressive covariance structure in multilevel model https://communities.sas.com/t5/Statistical-Procedures/Second-order-autoregressive-covariance-structure-in-multilevel/m-p/138701#M7234 <HTML><HEAD></HEAD><BODY><P>Does SAS have the native ability to implement a second order autoregressive covariance structure within either PROC MIXED or PROC GLIMMIX?&nbsp; I am aware that I can specify a first order autoregressive structure with TYPE = AR(1) on either the RANDOM or REPEATED statement line.&nbsp; However, using AR(2) returns and error of <SPAN style="color: #222222; font-family: arial, sans-serif; background-color: #ffffff;">"Invalid order specification"</SPAN>.</P><P></P><P>I am surprised that AR(2) does not appear to be a valid function.</P><P></P><P>Thanks,</P><P>Matt</P></BODY></HTML> Wed, 30 Apr 2014 02:08:35 GMT https://communities.sas.com/t5/Statistical-Procedures/Second-order-autoregressive-covariance-structure-in-multilevel/m-p/138701#M7234 mtaetntan 2014-04-30T02:08:35Z Re: Second order autoregressive covariance structure in multilevel model https://communities.sas.com/t5/Statistical-Procedures/Second-order-autoregressive-covariance-structure-in-multilevel/m-p/138702#M7235 <HTML><HEAD></HEAD><BODY><P>Not available.&nbsp; Do you think you could approximate it with either ANTE(1) or TOEPH?&nbsp; Those look like they could be AR(2) under the right parameterization.&nbsp; However, this really falls into the wild a&amp;&amp;ed guess category.</P><P></P><P>Steve Denham</P></BODY></HTML> Wed, 30 Apr 2014 16:54:25 GMT https://communities.sas.com/t5/Statistical-Procedures/Second-order-autoregressive-covariance-structure-in-multilevel/m-p/138702#M7235 SteveDenham 2014-04-30T16:54:25Z Re: Second order autoregressive covariance structure in multilevel model https://communities.sas.com/t5/Statistical-Procedures/Second-order-autoregressive-covariance-structure-in-multilevel/m-p/138703#M7236 <HTML><HEAD></HEAD><BODY><P>Thanks, Steve.&nbsp; I appreciate you confirming my suspicions.&nbsp; </P></BODY></HTML> Wed, 30 Apr 2014 18:27:46 GMT https://communities.sas.com/t5/Statistical-Procedures/Second-order-autoregressive-covariance-structure-in-multilevel/m-p/138703#M7236 mtaetntan 2014-04-30T18:27:46Z