hi Anthony,

Look at RESTRICT statement in PROC REG; It allows you to specify linear constraints on your model parameters; I do not think it allows inequality statements, but it does allow specific values;

If RESTRICT does not help, look at PROC MODEL in SAS/ETS, which has "bounds" statement; Using this you can certainly specify inequalities;

But do tell us more about your model; Restricting parameters might not give you a very good model, so you might want to explore alternatives;

From what you stated, looks like your inputs will always be positive; Is that the only reason why you want model parameters to be positive?..

Thanks, Shankar

On Apr 17, 2:57 am, Pact.Capacity.Managem...@UK.FUJITSU.COM (Anthony Steel) wrote: > Good-day all, > I was hoping someone may have a solution to a minor modelling issue we > are encountering. > > Our aim is to produce "best-fit" analysis of response-variables against > multiple regressors (for which PROC REG is currently used), but as we are > dealing with sets of real positive numbers (>=0) we wish to restrict the > range of possible parameter value outputs to also be in the same range > (i.e. >=0). > > So in summary is there anyway of ensuring the multivariate linear > regression analysis provides the "best-fit" that can be achieved with the > calculated paramaters being greater than or equal to zero? > > Regards, and thanks in advance, > Anthony Steel.