Jh. Stock et Mw. Watson, EVIDENCE ON STRUCTURAL INSTABILITY IN MACROECONOMIC TIME-SERIES RELATIONS, Journal of business & economic statistics, 14(1), 1996, pp. 11-30
An experiment is performed to assess the prevalence of instability in
univariate and bivariate macroeconomic time series relations and to as
certain whether various adaptive forecasting techniques successfully h
andle any such instability. Formal tests for instability and out-of-sa
mple forecasts from 16 different models are computed using a sample of
76 representative U.S. monthly postwar macroeconomic time series, con
stituting 5,700 bivariate forecasting relations. The tests for instabi
lity and the forecast comparisons suggest that there is substantial in
stability in a significant fraction of the univariate and bivariate au
toregressive models.