Hi all! Please help! I am using proc glm and mianalyze to generate simple intercepts and slopes. I get results like the picture below. The problem is, rather than generating this output, which says that the intercepts and slopes are significantly different from zero, I want to generate specific points for the average diagnostic age for each possible category (for example, male Hispanic, male non-Hispanic, female Hispanic, and female non-Hispanic) and see if they significantly differ from each other. see plot below: Does anyone know how to generate these points and see if they significantly differ? Essentially comparing simple slopes and intercepts. I'm stumped!! Here's my code if it helps: title "probing 3 way intx in model 4, subsetting by non- multi children, with multi var out of model"; odsselectnone; proc glm data=NotMult; model AgeDxASD = SC_AGE_YEARS CurrID NewLang Educ_1 Educ_2 Educ_3 Unemployed NoInsur povcat_1 povcat_2 povcat_3 Female black Asian Hispanic BlaFemIntx AsiaFemIntx BlaHispIntx FemHispIntx / solution; estimate 'intnotHisp' intercept 1 sc_age_years 5 currid .2 newlang .2 educ_1 .15 educ_2 .15 educ_3 .15 unemployed .2 noinsur .3 povcat_1 .15 povcat_2 .15 povcat_3 .15 Asian 0 black 0 BlaFemIntx 0 AsiaFemIntx 0 BlaHispIntx 0 FemHispIntx 0 ; estimate 'SlopeNotHisp' Female 1 FemHispIntx 0; estimate 'IntHisp' intercept 1 Hispanic 1 sc_age_years 5 currid .2 newlang .2 educ_1 .15 educ_2 .15 educ_3 .15 unemployed .2 noinsur .3 povcat_1 .15 povcat_2 .15 povcat_3 .15 Asian 0 black 0 BlaFemIntx 0 AsiaFemIntx 0 BlaHispIntx 0 FemHispIntx 0 ; estimate 'SlopeHisp' Female 1 FemHispIntx 1; weight FWC ; by _imputation_ ; ods output estimates = femhisp; run; quit; odsselectall; proc print data = femhisp (obs=6); run; proc sort data = femhisp out = femhisp; by _imputation_ parameter; run; proc transpose data = femhisp out=femhisp2 ; by _imputation_ parameter ; var Estimate stderr ; run; proc print data = femhisp2 (obs=20); run; proc transpose data = femhisp2 out=femhisp3 ; by _imputation_ ; id parameter _name_ ; var COL1 ; run; proc print data = femhisp3 (obs=20); run; proc mianalyze data=femhisp3 ; modeleffects IntHispEstimate SlopeHispEstimate SlopenotHispEstimate intnotHispEstimate ; stderr IntHispStdErr SlopeHispStdErr SlopenotHispStdErr intnotHispStdErr ; ods output parameterestimates=_parms_; run; proc transpose data=_parms_ out=_parms_; id parm; var estimate; run; data probe1; set _parms_; do female=0 to 1; hispanic=inthispestimate+slopehispestimate*female; nonhispanic=intnothispestimate+slopenothispestimate*female; output; end; run; proc print data=probe1; run;
... View more
