Unit roots in the presence of abrupt governmental interventions with an application to Brazilian data

This paper considers econometric issues related to time-series data that ha ve been subject to abrupt governmental interventions, The motivating exampl e for this study is the Brazilian monthly inflation rate (1974: 1-1993:6) w hich we use throughout for illustration. This series has been heavily influ enced by the effect of so-called shock plans implemented by various governm ents starting in the mid-1980s. The plans act as 'inliers' in the sense tha t the series is temporarily brought down to low levels before returning to its previous trend path. We analyse the effects on standard unit root tests and measures of persistence caused by the presence of these 'inliers'. We show a substantial bias in flavour of concluding that the series is station ary and that shocks have temporary effects. We then construct appropriately corrected statistics which take into account the presence of the plans. Th ese show, unlike the standard tests. that the stochastic behaviour of the i nflation rate was indeed unstable over this period. Simulation results are presented to support the adequacy of our corrected statistics. Copyright (C ) 1999 John Wiley & Sons, Ltd.