Theory: In finite samples, near-integrated data, widely thought to be stationary, mimic the same nonstationary data properties as integrated data. Hypothesis: Regressing two independent and near-integrated series results in high false rejection rates of the null hypothesis (spurious regressions). Method: Analytical derivations and numerical (Monte Carlo) analysis. We also extend the spurious regression test to actual data used in political science-macropartisanship-and a simulated near-integrated series. Results: False rejection of the null hypothesis is comparable to the integrated case (Granger and Newbold 1974). In addition, solutions to the spurious regression problem apply with equal force to the near-integrated situation.
No takes yet. Share an insight, caveat, or question.
DeBoef et al. (1997) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: