topic Re: Problems to determine the best model in Statistical Procedures https://communities.sas.com/t5/Statistical-Procedures/Problems-to-determine-the-best-model/m-p/206449#M11090 <HTML><HEAD></HEAD><BODY><P>The magnitude of AIC is not meaningful, just the difference in AIC between different models. 0 has no particular meaning. You want the smallest AIC. -75.8 is much smaller than 8.8</P></BODY></HTML> Mon, 20 Jul 2015 14:53:02 GMT lvm 2015-07-20T14:53:02Z Problems to determine the best model https://communities.sas.com/t5/Statistical-Procedures/Problems-to-determine-the-best-model/m-p/206448#M11089 <HTML><HEAD></HEAD><BODY><P>Hello everybody,</P><P></P><P> I'm using mixed with repeated measurement, and I want to choose the best model, when I compared the different possibilities of the stamen type (ante(1), ar(1), un, cs...) I have some AIC values negatives and positives.</P><P>So my question is smaller is better, but smaller means near to 0 or more negative.</P><P>One example I have for ante(1) an AIC of -75.8 and for ar(1) 8.8 so which one is the preferred model??</P><P>Thank you for the help!</P></BODY></HTML> Mon, 20 Jul 2015 14:17:29 GMT https://communities.sas.com/t5/Statistical-Procedures/Problems-to-determine-the-best-model/m-p/206448#M11089 aral 2015-07-20T14:17:29Z Re: Problems to determine the best model https://communities.sas.com/t5/Statistical-Procedures/Problems-to-determine-the-best-model/m-p/206449#M11090 <HTML><HEAD></HEAD><BODY><P>The magnitude of AIC is not meaningful, just the difference in AIC between different models. 0 has no particular meaning. You want the smallest AIC. -75.8 is much smaller than 8.8</P></BODY></HTML> Mon, 20 Jul 2015 14:53:02 GMT https://communities.sas.com/t5/Statistical-Procedures/Problems-to-determine-the-best-model/m-p/206449#M11090 lvm 2015-07-20T14:53:02Z Re: Problems to determine the best model https://communities.sas.com/t5/Statistical-Procedures/Problems-to-determine-the-best-model/m-p/206450#M11091 <HTML><HEAD></HEAD><BODY><P><SPAN style="font-size: 9.5pt; font-family: 'Arial','sans-serif';">It is very important to explore different variance-covariance structures when using proc mixed because the output contains fit statistics indicating which clearly indicate how well each model fits the data compared to other models.</SPAN> You need select the model that has the smallest AIC value.&nbsp; </P></BODY></HTML> Wed, 22 Jul 2015 04:07:48 GMT https://communities.sas.com/t5/Statistical-Procedures/Problems-to-determine-the-best-model/m-p/206450#M11091 HarryLiu 2015-07-22T04:07:48Z