topic Help understanding PROC GLIMMIX statements in Statistical Procedures

Help understanding PROC GLIMMIX statements

nlpurumi — Mon, 12 Feb 2018 18:24:37 GMT

Could anyone help me understand following two lines?

* random intercept / subject=trial1(subjectid group);

--> Does it mean to report the variance due to a variable "trial"?

--> Is there a possibility that "trial" was treated as "repeated" variable in proc glimmix through this code, because proc glimmix does not have repeated statement?

* random _residual_ / group=slc;

--> I think I have a vague sense that residuals are divided by the level of slc through this code, but I am not quite understanding why we divide them. How does it take care of heteroscedasticity problem?

Thanks in advance.

Re: Help understanding PROC GLIMMIX statements

Reeza — Mon, 12 Feb 2018 18:25:21 GMT

You need to post more code.

What PROC is this part of for starters?

@nlpurumi wrote:

Could anyone help me understand following two lines?

* random intercept / subject=trial1(subjectid group);

--> Does it mean to report the variance due to a variable "trial"?

--> Is there a possibility that "trial" was treated as "repeated" variable in proc glimmix through this code, because proc glimmix does not have repeated statement?

* random _residual_ / group=slc;

--> I think I have a vague sense that residuals are divided by the level of slc through this code, but I am not quite understanding why we divide them. How does it take care of heteroscedasticity problem?

Thanks in advance.

Re: Help understanding PROC GLIMMIX statements

nlpurumi — Mon, 12 Feb 2018 21:42:26 GMT

Because I received a help on this matter through other route, I want to ask a different question.

I want to build SAS code to test following equations:

Level 1 equation: Yij=β0j+β1j(SLC)+β2j(T)+β3j(SLC*T)+ rij(error)

(i: individual, j: each group)

Level 2 equations:

β0j= γ00+ γ01(G)+u0j

β1j= γ10+ γ11(G)+u1j

β2j= γ20+ γ21(G)+u2j

β3j= γ30+ γ31(G)+u3j

Will this be the good enough codes?

proc mixed data=dissertation1 ic;
class group slc subjectid trial1;
model ISI_Avg_sqrt= group|slc /ddfm=kr2 outp=R;
random intercept / subject=subjectid(group);
random slc / subject=subjectid(group);
random intercept / subject=trial1(subjectid group);
repeated /group=trial1;
/*repeated / group=slc;*/
run;

Thanks in advance!