Without knowing what type of model you want to fit, it will be difficult to privide an informative answer (or whether it can even be done).  In any event, I am going to privide possible places (in SAS) you could look for the solution to your problem.   Suppose y_ijt is the response variable associated with i-th source and j-th destination, at time t.  Similarly, X_ijkt denotes k-th predictor variable (for i-th source and j-th destination, at time t).  You want to model y_ijt and the model could have regression terms associated with X_ijkt, various fixed and random effects associated with i, j, t, and a variety of error terms.  You might also have lagged y_ijt (and or X_ijkt).  These types of models can be handled by a few different procedures in SAS.  Three of these are: PANEL (in SAS/ETS), MIXED (in SAS/STAT) and SSM (in SAS/ETS).  Each of these will have some advantages and some disadvantages.    PROC PANEL is specially designed for panel data types.    PROC MIXED can also fit a variaty of mixed effects models.  You can create different interaction variables (by DATA step and by the use of CLASS variables).  PROC SSM can also be used for such models but you must first formulate your model as a state space model.  Please consult the documentation (and solved examples in the doc) for additional information. ... View more