Score contribution per author:
α: calibrated so average coauthorship-adjusted count equals average raw count
In this paper, we investigate the small-sample performance of LR tests on long-run coefficients in the <italic>I</italic>(2) model; we focus on a comparison between <italic>I</italic>(2) and near-<italic>I</italic>(2) data, i.e. <italic>I</italic>(1) data with a second root very close to unity, and report the results of some Monte Carlo experiments. With near-<italic>I</italic>(2) data, the finite-sample properties of the tests are (i) similar to those found with genuine <italic>I</italic>(2) data, (ii) systematically superior to those of the analogous tests constructed in the <italic>I</italic>(1) model, even if the latter is, in principle, correctly specified and the former is not. Therefore, there seems to be strong support to the idea that, in practice, modelling near-<italic>I</italic>(2) data using the <italic>I</italic>(2) model may be a good idea, despite the inherent misspecification.