Hi all,    Is there a way to pick out certain parts of your results and send to a new table? for example, in the solution for fixed effects below, I want just the estimate p- value and confidence interval in a new table but want to exclude the rest of the results :  what i want:  estimate p value lower upper -2.598 <.0001 -2.95 -2.2   I appreciate the help! ... View more

Hi all,     I have data where in some records visit 1 is missing, meaning I need SAS to set the baseline value to the first observation that has an actual value. Here is my data +code: data WORK.test; input record visit orange apple; CARDS; 1 1 1 . 1 2 1 1 1 3 1 1 1 4 0 1 1 5 0 3 1 6 0 0 1 7 0 0 2 1 2 . 2 2 0 . 2 3 0 1 2 4 0 0 ; run; data test2; set test; by record visit; retain baseline_apple; if (first.record) and apple ne . then baseline_apple=apple; When I run this, it only sets baseline when the value isn't missing which is good, but I can't figure out how to tell it to use the next observation (if also not missing ) as the baseline and retain that baseline value for the rest of the visits.  (baseline gets set for each record ). output:  What I want is this:  record visit apple baseline 1 1 . . 1 2 1 1 1 3 1 1 1 4 1 1 1 5 3 1 2 1 . . 2 2 . . 2 3 1 1 if I use "else baseline=apple" it won't retain the value across visits.   I dont wan't to use a statement like where apple ne . because it will delete the entire row and I could lose data for other variables in my data set. Thank you!! ... View more