Hi Lilly, A couple places to look.  If you are doing VCE corrections, many of those are available in PANEL using these HCCME options SAS/ETS(R) 13.1 User's Guide If you are looking to use GLS then I would suggest PROC MIXED as the likely place as it will have longitudinal model options that you would likely want. Good luck-Ken ... View more

The transpose is the first idea. Perhaps more easy to do some datasetcoding. The thoughts: - Define two array-s for all the company 1/ date vars 2/ tobinsq. Pehaps the naming is helping.   SAS(R) 9.4 Statements: Reference (array) - the in a do loop for all variables write to a SAS new dataset:   company-id , date(i),tobinq(i) - let te datastep proceed for all  records. The result will be a dataset with the columns you need, just the order is different. Ordering the data can be done by creating indexes. Base SAS(R) 9.4 Procedures Guide Or by sorting. Proc sort (company/date) As the dataset is that small it could easily be fit in memory or being buffered. Unless there are many timemoments (10 minute snap-shots for over many years.)   ... View more