https://communities.sas.com/t5/Statistical-Procedures/Fit-a-Multinomial-Mixed-Model-by-Proc-GLIMMIX/m-p/491013#M25508 <P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="dimention of G matrix.png" style="width: 278px;"><img src="https://communities.sas.com/t5/image/serverpage/image-id/22863i95A2459075798AC5/image-size/large?v=v2&amp;px=999" role="button" title="dimention of G matrix.png" alt="dimention of G matrix.png" /></span><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="covariance estimate of G matrix.png" style="width: 588px;"><img src="https://communities.sas.com/t5/image/serverpage/image-id/22864iFD955E60671AFB4F/image-size/large?v=v2&amp;px=999" role="button" title="covariance estimate of G matrix.png" alt="covariance estimate of G matrix.png" /></span>&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;</P><P>&nbsp;</P><P>Above is what the G matrix dimension and G matrix estimate is. But there is something wrong as I mentioned in the first post.</P> Wed, 29 Aug 2018 21:57:30 GMT binfang 2018-08-29T21:57:30Z https://communities.sas.com/t5/Statistical-Procedures/Fit-a-Multinomial-Mixed-Model-by-Proc-GLIMMIX/m-p/491004#M25505 <DIV>I am trying to fit a multinomial mixed model.&nbsp;The outcome is a categorical variables with 4 levels and the predictors are continuous. The random intercept effect come from one variable "case" in which subjects are pairs or unmatched.</DIV><DIV>&nbsp;</DIV><DIV>The code,&nbsp;<SPAN>log, output and data set are all attached</SPAN> in this post.&nbsp;</DIV><DIV>&nbsp;</DIV><DIV><STRONG>A very serious problem in the output comes from the dimension of estimated G matrix: in the output 4 parameters are estimated in the G matrix, whereas there are supposed to be only 3.<SPAN>&nbsp;</SPAN></STRONG>As comparison, when a logistic mixed model is fitted, in which the outcome is 2-level categorical, only one parameter in the G matrix is estimated.</DIV><DIV>&nbsp;</DIV><DIV>I guess there is something wrong with the model fitting.</DIV> Wed, 29 Aug 2018 21:50:17 GMT https://communities.sas.com/t5/Statistical-Procedures/Fit-a-Multinomial-Mixed-Model-by-Proc-GLIMMIX/m-p/491004#M25505 binfang 2018-08-29T21:50:17Z https://communities.sas.com/t5/Statistical-Procedures/Fit-a-Multinomial-Mixed-Model-by-Proc-GLIMMIX/m-p/491013#M25508 <P><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="dimention of G matrix.png" style="width: 278px;"><img src="https://communities.sas.com/t5/image/serverpage/image-id/22863i95A2459075798AC5/image-size/large?v=v2&amp;px=999" role="button" title="dimention of G matrix.png" alt="dimention of G matrix.png" /></span><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="covariance estimate of G matrix.png" style="width: 588px;"><img src="https://communities.sas.com/t5/image/serverpage/image-id/22864iFD955E60671AFB4F/image-size/large?v=v2&amp;px=999" role="button" title="covariance estimate of G matrix.png" alt="covariance estimate of G matrix.png" /></span>&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;</P><P>&nbsp;</P><P>Above is what the G matrix dimension and G matrix estimate is. But there is something wrong as I mentioned in the first post.</P> Wed, 29 Aug 2018 21:57:30 GMT https://communities.sas.com/t5/Statistical-Procedures/Fit-a-Multinomial-Mixed-Model-by-Proc-GLIMMIX/m-p/491013#M25508 binfang 2018-08-29T21:57:30Z