Possibly, Jeroen Weesie's -linest- maybe of use:
TITLE
linest. Two-stage linear-constrained estimation.
DESCRIPTION/AUTHOR(S)
linest imposed linear constraints on the last estimation
results. This two-stage estimator is asymptotically equivalent
to the "true" one-stage constrained estimator.
Yes! That looks very promising. The help even says it is written for
dummies like me, i.e. "for user-written command for which the trouble to
add code to deal with constraints may be excessive, we supply a
solution." It sounds like it may not be quite as good as a one-stage
estimation procedure, but until I learn how to write my own this may be
good enough. Thanks much!
