Hi SAS Community! I have done a fair bit of macro programming with SAS and lots of straight-forward analyses, but nothing complex and now I am a overwhelmed. Perhaps you can help? I have an experimental design: * Treatments: A, B, Sham * Parameters: just one * Measurements: baseline, T1 - T4 -> so one parameter measured before and then four times after each intervention Each subject was exposed to all three treatments (different days) so the treatments and the measurements are repeated. (If that's the correct way to say it). I want to know whether treatment modulates the parameter and how it relates to time, so I thought a two-way repeated measures ANOVA would do be a nice start, followed by Tukey post-hoc test to see if A and B are dif from each other, or just sham. I suppose I could use Dennet post hoc test instead since sham is involved. I may also want to do a separate model with an interaction term. What would be the complete SAS syntax for this? I can structure the data as needed (e.g. wide or stacked) but right now I have it like this: SubjectID Intervention Timepoint Value =============================== 1 A Base 8 1 A T1 19 1 A T2 12 1 A T3 19 1 A T4 13 1 B Base 13 1 B T1 19 1 B T2 11 1 B T3 10 1 B T4 9 1 Sham Base 2 1 Sham T1 3 1 Sham T2 5 1 Sham T3 3 1 Sham T4 4 2 A Base ... etc. I was thinking something like proc glm class intervention timepoint; model value = intervention timepoint; means group / cldiff tukey; run; But this is not repeated measures. And I don't even know if this is right. Can you please advise? I can restructure the data however needed, the main thing is I need to do two-way repeated measure anova on the given experiment design. Thanks! -Bob Message was edited by: Bob291032 ... View more

I have a set of cases and a set of controls. For each possible case-control pair, there is a cost associated with the pairing. Sometimes the pair is not allowed (e.g. cost is too high) so the cost is set to missing. The dataset then has one observation per case, with one variable per control, with the value of each variable either missing or set to the cost of matching the case to that particular control. i.e. it's an N x M matrix of N cases (observations) and M controls (variables). Because this is a large dataset with missing costs, PROC ASSIGN errors out and reports that the problem is infeasible, though it does provide a reasonable solution. I would like to reformulate this as a linear program so I can solve this optimization problem using PROC OPTMODEL and get the optimal solution. I'm reading the PROC OPTMODEL docs and looking at SAS white papers, but this stuff gets pretty complicated to a newbie like me and my problem is probably one of the easiest types of problems you can solve with PROC OPTMODEL so I was wondering if anyone on this forum can help me reformulate the problem. I do know how to manipulate/transform/restructure datasets in SAS, write macros, etc. but the theoretical component of OPTMODEL is a over my head right now. Please advise. Thanks! -Bob ... View more

I am using PROC ASSIGN to perform optimal matching on a set of cases and a set of controls using a simple distance measure between cases and controls. I am unwilling to accept a match if the distance is greater than X, where X is between 0 and 1. Thus, if a cell in the distance matrix I am sending to PROC ASSIGN has a node with a distance greater than X, I set that node to missing (.). This prevents PROC ASSIGN from matching that case/control combination thereby ensuring no matches with a distance greater than X. If I set X very high, PROC ASSIGN succeeds in matching all of my cases to their optimal controls. If I set X a bit lower, PROC ASSSIGN succeeds in matching most of my cases to their optimal control and some cases just don't get matched (which is what I want). However, If I set X too low, PROC ASSIGN fails with the error, "The problem is infeasible. The output data set shows the assignments made before the infeasibility was found." I've reviewed the relevant SAS docs and the only information they have about infeasibility is for a given case-control where with a missing distance. But in my case, that's not what's triggering the error (I don't think) as having a missing distance for some cases and controls only gives off the infeasibility error when the ratio of missing cases is beyond some threshold (or something like that). So what does "The problem is infeasible. The output data set shows the assignments made before the infeasibility was found." mean? Is the resulting match non-optimal? Is the resulting match valid? I can accept if it is less than optimal, but does SAS just error out and stop trying at the point of the error, and if so, how early is this triggered? If it's after most of the good matches have been made, again, I can accept that. Please advise. Thanks! -Bob ... View more