Title: Linearity testing in vector smooth transition autoregressive models when data are highly persistent
Authors: Rickard Sandberg - Stockholm School of Economics (Sweden) [presenting]
Abstract: Asymptotic distributions are derived for linearity tests in vector smooth transition autoregressive (VSTAR) type of models in the presence of a unit root. The asymptotic distributions are non-standard because of the unit root assumption, and it is shown that the linearity hypothesis is rejected far too often (already up to 60\% of the times at a 5\% nominal significance level in bivariate systems) erroneously relying upon standard critical values. These findings will have practical implications because VSTAR models often are applied to data that are highly persistent, and the outcomes of standard linearity testing procedures in these cases should be interpreted with caution.