Mixture of chi square with NLMixed in sas

[Gilles-Protais]

Please which code can i use to test for random effects (random intercepts and random slopes) using a mixture of chi sqaures

Thanks

[Ksharp]

I am not sure if the following CHISQ option is what you are looking for ?

proc mixed data=sashelp.heart(obs=100) ;
class bp_status sex;
model weight=height sex/s chisq;
random int sex/subject=bp_status  ;
run;

or @SteveDenham  @lvm  knew it. 

[lvm]

I think you are asking about testing Ho: Variance = 0 vs Ha: Variance >0. When you use the COVTEST statement in GLIMMIX, the procedure automatically uses a mixture of chi-square statistics when appropriate (and it tells you in the results).  The mixture is typically needed when the variance parameter is on the boundary (e.g., 0). 

See 

https://support.sas.com/kb/40/724.html

to learn about COVTEST (this is different than the covtest option in MIXED).  The online documentation for GLIMMIX will explain COVTEST in more details, with simpler examples. This is a likelihood ratio test, where the ratio is compared with the chi-square statistic (mixture or otherwise, depending on the situation).  This is explained also in:

chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://support.sas.com/resources/papers/proceedings/proceedings/forum2007/177-2007.pdf