Point 1.  When you say you have multiple data points from each experimental unit, are these related in either time or space?  If so, that might change the approach.  However, for now, I would fit the data much as you have, except to change subject=subject to subject=stream. Point 2. You can form null, reduced and full models.  Null would be model x=; Reduced would be: model x=y; Full would include the random effect as well. If that does not give you what I think you are asking for, please post more details about the macros. Steve Denham Message was edited by: Steve Denham ... View more