In a recent paper, Blanchard and Quah (American Economic Review, 1989,
79, 655-673) propose a set of restrictions to identify the structural
innovations from a reduced-form bivariate model of income growth and
unemployment. Given the assumptions made by Blanchard and Quah on the
time-series properties of the data, this paper demonstrates that their
bivariate model is just a special case of Stock and Watson's Journal
of the American Statistical Association, 1988, 83, 1097-1107) common t
rends representation. More importantly, this alternative representatio
n allows the econometrician to test the long-run restrictions used by
Blanchard and Quah to distinguish between demand and supply innovation
s.