EcoSta 2018: Registration
View Submission - EcoSta2018
Title: Detecting time reversibility using quantile autoregressions Authors:  Li Sun - Maastricht University (Netherlands) [presenting]
Alain Hecq - Maastricht University (Netherlands)
Abstract: The aim is twofold. First we propose to detect time irreversibility in stationary time series using quantile autoregressive models (QAR). This approach provides an alternative way to look at the identification of causal from noncausal models. Although we obviously assume that non-Gaussian disturbances generate series we do not need any parametric distribution to maximize (e.g. the Student or the Cauchy) likelihood. This is very interesting for skewed distributions for instance. Secondly, we propose to extend QAR models to QMAR, namely quantile regressions in reverse time. This new modelling is appealing for investigating the presence of bubbles in economic and financial time series. We illustrate our analysis using hyperinflation episodes in Latin American countries.