Dear SAS users, I would like to test the trend for the severity of cancer prognosis (continuous) vs. an ordinal variable (e.g. education).  With a single dataset I would use a non parametric test such as jonkeree terpstra but having performed multiple imputation  I need also  to pool the results. I  used GLM with the estimate statement to obtain a standard error I can use with mianalyze, but I am not sure if I can do this for nonparametric data. I am also  not sure what approach would be appropriate with an ordinal variable. Could you please advise on this problem? Thank you   title 'GLM by &catvar'; proc glm data=MI_FCS2 ; by  _imputation_ ; class &catvar; model Prognosis = &catvar / solution; estimate 'edu3' intercept 1 &catvar 0 0 1; estimate 'edu2' intercept 1 &catvar 0 1 0; estimate 'edu1' intercept 1 &catvar 1 0 0; estimate 'edu1-edu2'         &catvar 1 -1 0; estimate 'edu2-edu3'         &catvar 0  1 -1; estimate '(edu1,edu2)-edu3' &catvar 0.5 0.5 -1; ods output estimates=est_ds; run; ... View more

Hi, How can I pool the results of the Jonckheere-Terpstra Test from multiply imputed datasets? Below is my code to generate a datasets with JT statistics from multiple imputations. Thank you Giampaolo   proc freq data=mydata; Table triglycerides*TumorSTAGE/JT noprint; output out=TT1 JT; by _imputation_ ; run; ... View more

Dear SAS users, After I run proc template sas keeps running and I receive the ERROR 79-322: Expecting a -. Any idea, how can I stop SAS from processing the command and fix the issue? Thank you! Proc template; define statgraph BrokenAxis1; begingraph /datacolors=(CXD05B5B CX6F7EB3) datacontrastcolors=(red blue); layout lattice / Columns=2 Rows = 2 columnweights= (.5 .5) Rows=2 rowweights= (.47 .53) rowgutter = 5 rowdatarange=UNION; /* Lattice header definitions */ column2headers ; entry textattrs=(size=9 ) "ELECTIVE"/*/pad=(left=15 px)*/; entry textattrs=(size=9 ) "EMERGENT"/*/pad=(left=15 px)*/; endcolumn2headers; /*define row 1 column 1*/ layout overlay / xaxisopts= (display= (line)) yaxisopts=(display=(line ticks tickvalues label) label="Total Cost (X$10,000)" griddisplay=on linearopts=(includeranges=(min-170000 380000-384000) tickvalueformat= bigvalues. tickvaluelist=(20000 40000 60000 80000 100000 120000 140000 160000 380000))); boxplot x=&GRP Y=eval(ifn(&strata=0,Total_cost, .))/ grouporder=ASCENDING INCLUDEMISSINGGROUP=FALSE group=&XVAR groupdisplay=cluster meanattrs = (SYMBOL = DIAMOND weight=bold ) medianattrs= (thickness = 2) name ="L" ; endlayout; /*define row 1 column 2*/ layout overlay /xaxisopts= (display= (line)) yaxisopts=(display=(line ticks tickvalues) griddisplay=on linearopts=(includeranges=(min-170000 380000-max) tickvalueformat= bigvalues. tickvaluelist=(20000 40000 60000 80000 100000 120000 140000 160000 380000))); boxplot x=&GRP Y=eval(ifn(&strata=1,Total_Cost, .))/ grouporder=ASCENDING INCLUDEMISSINGGROUP=FALSE group=&XVAR groupdisplay=cluster meanattrs = (SYMBOL = DIAMOND weight=bold ) medianattrs= (thickness = 2) name ="L" ; endlayout; /*define row 2 column 2*/ layout overlay /xaxisopts=(display=(ticks tickvalues line)) yaxisopts=(display=(ticks tickvalues line label)label="Postop LOS (days)" LABELFITPOLICY=SPLITALWAYS LABELSPLITCHAR='#' LABELSPLITCHARDROP=TRUE griddisplay=on linearopts=(tickvalueFormat= best12. includeranges=(min-42 115-118) tickvaluelist=(5 10 15 20 25 30 35 40 115))); boxplot x= &GRP Y=eval(ifn(&strata=0,PostopLOS, .)) /grouporder=ASCENDING INCLUDEMISSINGGROUP=FALSE group=&XVAR groupdisplay=cluster meanattrs = (SYMBOL = DIAMOND weight=bold ) medianattrs= (thickness = 2)name ="L" ; endlayout; /*define row 2 column 2*/ layout overlay /xaxisopts=(display=(ticks tickvalues line)) yaxisopts=(display=(ticks tickvalues line) griddisplay=on linearopts=(tickvalueFormat= best12. includeranges=(min-42 115-max) tickvaluelist=(5 10 15 20 25 30 35 40 115))); boxplot x= &GRP Y=eval(ifn(&strata=1,PostopLOS, .)) / grouporder=ASCENDING INCLUDEMISSINGGROUP=FALSE group=&XVAR groupdisplay=cluster meanattrs = (SYMBOL = DIAMOND weight=bold ) medianattrs= (thickness = 2)name ="L" ; endlayout; sidebar / align = bottom; discretelegend "L" / halign=center across= 2 border=true VALUEATTRS= (size= 9); endsidebar; endlayout; endgraph; end; run; quit; ... View more

Dear SAS users, I have divided a population of patients into quartiles of blood glucose and used a bar graph to represent the frequency of each quartiles among three groups of patients. The quartile progression from low to high is visualized by a progressively darkening color  (two color ramp). I need now to visualize quartiles from  groups of this population using a different color for each group. The different colors are to clarify that it's the group, not the population, that has been divided into quartiles.  As of now all groups have the same color progression. I posted an example of two group quintiles from white to gray. How can I apply a different color ramp to the two groups? Thank you!   My code is: proc sgplot data = rankpergroup noautolegend ; VBARPARM CATEGORY= CDM   response = PCT_ROW/ CLUSTERWIDTH= 0.7 group= q_G groupdisplay=cluster colorresponse=q_G colormodel=twocolorramp; xaxis label= 'Quartile of TWM Glucose' labelattrs= (size=14) VALUEATTRS =(size=14); yaxis label = 'Patients (%)' labelattrs= (size=14) labelpos= center VALUEATTRS =(size=14); run; ... View more