I am overlaying some plots (vbar and 2 scatters) on an sgplot statement but each overlay adds extra space between the 0 mark on the y axis and my x axis. How can I prevent this?     proc sgplot data=dat noautolegend noborder;     vbarparm category=sex response=median;     scatter x=sex y=median/ yerrorupper=quartile3 markerattrs=(size=0);     scatter x=sex y=mylabel / markerattrs=(symbol=asterisk);     yaxis values=(0 to 100 by 10);     xaxis display=(nolabel) valueattrs=(size=12pt); run; ... View more

I am running a vertical bar chart for stat=median and would like an upper error bar to represent the 3rd quartile of the IQR. Is there a way to do this? I think error bars are only displayed when stat = mean?   proc sgplot data=dat;     vbar x/ response=y stat=median; run;     ... View more

I have some data I am creating vbars for as such:   Y             TIME             GROUP           GENDER 1.1              0                    A                      F 1.5              1                    A                      F 1.3              0                    B                      F 1.4              1                    B                      F 1.5              0                    A                      M 1.7              1                    A                      M     There are no males in group b, but when I run the below code, I get a blank area for group B under the male panel. There was actually never supposed to be males in group b, so I dont want this to display at all. I just want one panel that is for females that displays groups a and b, and then one panel for males that only displays group A. Any way to do this?   proc sgpanel data=x;      panelby gender / novarname;      vbar group / response=y group=time  groupdisplay=cluster stat=mean; run; ... View more

I am running a proc hpgenselect logistic model using lasso selection. I understand hpgenselect already uses group lasso methods for class variables. However, I additionally have 2 variables (part of a spline - 1 represents continuous variable less than X and the other represents continuous variable greater than X) that I want to keep together. How can I do this as they are not part of the same class variable? ... View more

I am using hpgenselect to run a logistic model with a lasso selection method and I want to force 2 variables in the model. Is there a method equivalent to "include = 2" from a logistic model I could use? ... View more