Forward regression in SPSS

I am trying to predict some missing values in a dataset by doing a stepwise forward regression procedure, I was succesfull in producing an output telling me the weights (beta) of each predictor when correlated and ofcourse the collective r.
I know I am supposed to use the weights of the predictors together with the individuals scores these predictors to be able to predict the missing scores (criteria) but how do I go about doing this with this knowledge? I am mainly interested in how it is done in SPSS, but if someone could tell me how it is done manually as well that would be good for my overall understanding.
Hey can noone help me? Can someone at least tell me how I normally would go about predicting scores in spss when I made a normal regressino analysis and got the weights and everything?