Can I change line thickness different for the variables in my group based on pvalues for LOESS?

[bchronister]

Hello, 

I am using sgplot to create a loess graph of grouped data. I have created an indicator variable that determines whether the association is above or below a pvalue of 0.05. I saw that there is a way to create a thickness response when making a series plot. However, I haven't gotten it to work when I am using a LOESS graph. Is there any way to do that? I have copied one of my attempts below. 

proc sgplot data=compiled aspect=1 ;
where &rank. & &hormone.;
loess y=lsmean x=LSMeanNumber/group=metabolite markerattrs=(size=0) lineattrs=( thickresp= thickmax=7px)
;
xaxis grid label="Rank" LABELATTRS=(family='Times New Roman' size=10) LABELATTRS=(family='Times New Roman' size=12) valueattrs=(family='Times New Roman' size=12pt); 
YAXIS grid label="ln(hormone) concentration" LABELATTRS=(family='Times New Roman' size=10)  LABELATTRS=(family='Times New Roman' size=12 ) valueattrs=( family='Times New Roman' size=12pt) min=3.5 max=4.5;
format metabolite summaryscore. hormone hormoneln.;
styleattrs datacontrastcolors=(BIGB  VIPB  DELG VIRO STPPK VIYPK );

title " ";
run;

[Jay54]

You may be able to save the data output of the LOESS function from your code to an ODS output data set, and then use it for a SERIES plot with the THICKRESP=numeric-variable option to set line thickness by the p-value variable column.  See other related options in doc to customize the output.

https://documentation.sas.com/?cdcId=pgmsascdc&cdcVersion=9.4_3.5&docsetId=grstatproc&docsetTarget=n...