Hi Folks, I've created a scatter plot in SGPLOT with the GROUP= option and overlaid it with a regression also with the GROUP= option. Because of the density of the data points in the scatter plot, I want to specify a contrasting colors for the regression lines that are different from the scatter plot marker colors and thus improves readability but I cannot find a way to do this, even with an ATTRID= specification. Adjusting the transparency of the markers for the scatter plot does not help. The overlaid regression lines cannot be the same color. Many thanks for all suggestions. Code below, example attached.   data attrmap; set &library..tablvars_labs_evnts_phz&phz.(keep=CIRRHOSIS); if CIRRHOSIS='Y' then linecolor='Blue'; else if CIRRHOSIS='N' then linecolor='Red'; id='myid'; run; proc sort data=&library..tablvars_labs_evnts_phz&phz.; by TESTCD CIRRHOSIS EOTWKS; run; proc sgplot data=&library..tablvars_labs_evnts_phz&phz. noautolegend; by TESTCD; where BINSVR='SVR' and TESTCD in ('PLAT'); styleattrs datacontrastcolors=(salmon bigb green) datasymbols=(plus circle square); scatter y=NUMRSLT x=EOTWKS / group=CIRRHOSIS splitcharnodrop splitchar='*' markerattrs=(size=8) transparency=0.7; reg y=NUMRSLT x=EOTWKS / degree=3 group=CIRRHOSIS lineattrs=(thickness=8 pattern=4) attrid=myid; refline -24 -12 -8 0 12 52 78 104 / axis=x lineattrs=(pattern=shortdash) transparency=0.2 label=("TXST-24wk" "TXST-12wk" "TXST-8wk" "EOT" "SVR" "1 yr. PTX" "1.5 yr. PTX" "2 yr. PTX") labelattrs=(Color=green Family=Arial Size=8 Weight=Bold) lineattrs=(Color=green thickness=3) labelpos=auto labelloc=outside ; xaxis type=linear /*offsetmin=0 offsetmax=0.35 min=-0.5 max=0.5*/ values=(-120 to 180 by 24) minor valueattrs=(Family=Arial Size=10 Weight=bold) label="WEEKS" labelattrs=(Color=black Family=Arial Size=10 Weight=Bold) labelpos=datacenter; * format TESTCD $lbtst.; label MEANDIFF="MEAN DIFFERENCE" LCL="Lower 95%CL" UCL="Upper 95%CL" NOBSUSED='NOBS' NUMRSLT='PLATELET MEASURMENT' DYSPSTEOT='WEEKS FOLLOWING EOT'; yaxis type=linear valueattrs=(Family=Arial Size=11 Weight=bold) labelpos=top fitpolicy=splitalways splitchar='*' values=(0 to 800 by 100) valueattrs=(Family=Arial Size=10 Weight=bold) label="MEASURMENT" labelattrs=(Color=black Family=Arial Size=10 Weight=Bold) labelpos=datacenter; keylegend / title="GROUP" titleattrs=(Color=black Family=Arial Size=10 Weight=Bold) across=2 location=outside valueattrs=(Color=black Family=Arial Size=10 Weight=Bold); run;   ... View more

I'm running a repeated measures analysis with GENMOD with a binary outcome and want to specify the best correlation matrix. The following code is used but changing the TYPE does not change the parameter estimates or the predicted probabilities. This seems somewhere between ridiculous and impossible. LINK=IDENTITY produces the predicted probability differences from the LSMEANS in the correct scale but the TYPE still has no impact on the output. All clues gratefully embraced.   proc genmod data=&library..qstrans_dm descending; where RANDREG in ('SOF/LDV' 'EBR/GZR') and HCVGT2 in ('1A' '1B'); class USUBJID RANDREG (ref='SOF/LDV') HCVGT2 (ref='1B') CIRRHOSIS (ref='N') EVENT (ref='T2') / param=ref; model ADHERENT = RANDREG HCVGT2 CIRRHOSIS EVENT / dist=binomial link=logit; repeated subject=USUBJID / corrb covb type=CS; contrast 'Regimen' RANDREG 1; lsmeans RANDREG / ilink exp diff cl; lsmestimate RANDREG 'HVN vs ZEP' 11 / exp cl; run; ... View more

I want to compute differences in proportions for a two-level outcome using the logistic procedure with contrasts, according to:   proc logistic data=&library..SVR_GP_mITT; class ACTARMCD HCVGTCAT; model SVR12= TREATMENT HCVGTCAT LOGHCVBASE; contrast 'a - b' HCVGTCAT. 1 / estimate=parm; contrast 'Treatment A vs B' TREATMENT 1; run;   TREATMENT is a two-level predictor (A/B); HCVGTCAT is also two-level (a/b); LOGHCVBASE is continuous. Unless I’m missing something, the contrast estimates do not, themselves, provide the differences in proportions between treatment arms directly. Is it legitimate to use the contrast (treatment arm, HCV sub-genotype) and parameter estimates (LogHCVBASE) obtained from the logistic model to compute predicted SVR12 proportions for each subject, controlling for all predictors in the model, with the difference in mean proportions (and confidence intervals) subsequently computed by arm group (A vs. B )?   Many thanks for all insights. ... View more

Hi Folks, I want to compute the overall stratum-adjusted difference in proportions (SVR12*TRTWKS) and confidence limits for the variable SVR12 in the following tables statement in a frequency procedure. I need the overall difference (and C.I.) in SVR12, controlling for CIRRHOSIS (Y/N) and HCVGTCAT (A/B) simultaneously but the following code is producing individual differences controlling independently for each pair of strata (e.g., CIRRHOSIS='Y', HCVGTCAT='A') and not controlling for all levels of both covariates simulateously. Many thanks for all insights.   proc freq data=&library..SVR_GP_mITT nlevels order=data; tables CIRRHOSIS*HCVGTCAT*TRTWKS*SVR12 / riskdiff (column=both CL=(WALD WILSON)) chisq fisher cmh cl agree alpha=0.05; format SVR12 svrfmt.; where FIRSTREC=1; ods output CrossTabFreqs=crstabfrq RiskDiffCol1=rskdfcol1 PearsonChiSq=pearchisq PdiffCLs=PdiffCLs ; run; ... View more

I need to report confidence intervals for proportions and proportion differences using the Wilson-score (also called Newcombe) method but I cannot use PROC FREQ because the proportions are output as predicted values from a logistic model. The algebraic algorithm could be incorporated into a data step but it's pretty messy - has anyone already created code to do this. Many thanks. ... View more