ABSTRACT
It is often difficult to justify a maintained hy
pothesis that the regression c o e f f i c i e n t s are
stable over a sample interval. Stability(of esti
mated functional form)of economic relations is
largely an empirical question. Stability is also
closely connected with the e m p i r i c a l issue of
choosing among appropriate definitions of the de
pendent and independent variables in the model.
