topic Re: SAS/IML and SAS/STAT in SAS/IML Software and Matrix Computations https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161738#M1536 <HTML><HEAD></HEAD><BODY><P>If you have already done the calculation of coefficients in PROC IML, then you could easily compute residuals in PROC IML as well. Using SAS/STAT in this situation only complicates things, in my opinion.</P></BODY></HTML> Fri, 26 Sep 2014 13:32:26 GMT PaigeMiller 2014-09-26T13:32:26Z SAS/IML and SAS/STAT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161737#M1535 <HTML><HEAD></HEAD><BODY><P>Dear all, </P><P>I wrote a sas/iml code which compute a coefficients matrix of three OLS regressions. (VAR model)</P><P>Is it possible to plug in this matrix in VAR model at SAS/STAT in order to calculate the residuals? (residual=y-yhat)</P><P>and then the covariance matrix between the residuals?</P><P></P><P>Usually the SAS regression procedures compute the matrix of the coefficients. </P><P>Here I want to give the X, coefficient's matrix and then to compute the residuals.</P><P>I'll appreciate any information,</P><P>Thanks,</P><P>Orit</P></BODY></HTML> Fri, 26 Sep 2014 13:27:35 GMT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161737#M1535 oriti 2014-09-26T13:27:35Z Re: SAS/IML and SAS/STAT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161738#M1536 <HTML><HEAD></HEAD><BODY><P>If you have already done the calculation of coefficients in PROC IML, then you could easily compute residuals in PROC IML as well. Using SAS/STAT in this situation only complicates things, in my opinion.</P></BODY></HTML> Fri, 26 Sep 2014 13:32:26 GMT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161738#M1536 PaigeMiller 2014-09-26T13:32:26Z Re: SAS/IML and SAS/STAT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161739#M1537 <HTML><HEAD></HEAD><BODY><P>You right in general.</P><P>But I have a VAR model which is in my case three equation and can be more.</P><P>So it will be really efficient if it is possible to plug in the coefficient matrix into SAS/STAT.</P><P>Is it possible?</P></BODY></HTML> Fri, 26 Sep 2014 13:49:57 GMT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161739#M1537 oriti 2014-09-26T13:49:57Z Re: SAS/IML and SAS/STAT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161740#M1538 <HTML><HEAD></HEAD><BODY><P>Without knowing the details of what you are doing, I can't see how it would be more efficient to compute coefficients in IML and then move the coefficients somewhere else for calculation of residuals. You have everything you need already in IML.</P><P></P><P>But if you must use SAS/STAT, use PROC SCORE.</P></BODY></HTML> Fri, 26 Sep 2014 14:15:25 GMT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161740#M1538 PaigeMiller 2014-09-26T14:15:25Z Re: SAS/IML and SAS/STAT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161741#M1539 <HTML><HEAD></HEAD><BODY><P>Being possible and being a good idea are two different things. Yes, it is possible. However, I agree with <A __default_attr="71595" __jive_macro_name="user" class="jive_macro jive_macro_user" data-objecttype="3" href="https://communities.sas.com/"></A> that evaluating (scoring) the model in SAS/IML will probably be simpler, since evaluating a model is just matrix multiplication.</P><P></P><P>If you decide to go the SAS/STAT route, look into PROC SCORE. You would have to write the coefficients to a data set in the form that PROC SCORE could consume, as described here: <A href="http://support.sas.com/documentation/cdl/en/statug/66859/HTML/default/viewer.htm#statug_score_overview02.htm" title="http://support.sas.com/documentation/cdl/en/statug/66859/HTML/default/viewer.htm#statug_score_overview02.htm">SAS/STAT(R) 13.1 User's Guide</A> </P></BODY></HTML> Fri, 26 Sep 2014 14:20:53 GMT https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/SAS-IML-and-SAS-STAT/m-p/161741#M1539 Rick_SAS 2014-09-26T14:20:53Z