Breaks or long memory behaviour : an empirical investigation

Are structural breaks models true switching models or long memory processes? The answer to this question remain ambiguous. A lot of papers, in recent years, have dealt with this problem. For instance, Diebold and Inoue (2001) and Granger and Hyung (2004) show, under speci c conditions, that switching models and long memory processes can be easily confused. In this paper, using several generating models like the mean-plus-noise model, the STOchastic Permanent BREAK model, the Markov switching model, The TAR model, the sign model and the Structural CHange model (SCH) and several estimation techniques like the the GPH technique, the Exact Local Whittle (ELW) and the Wavelet methods, we show that, if the answer is quite simple in some cases, it can be mitigate in other cases. Using French and American in ation rates we show that these series cannot be characterized by the same class of models. The main result of this study suggests that estimating the long memory parameter without taking account existence of breaks in the data sets may lead to misspeci cation and to overestimate the true parameter. JEL classi cation: C13 C32 E3