Range unit root testsReport as inadecuate




Range unit root tests - Download this document for free, or read online. Document in PDF available to download.

Issued date: 2003-02

Serie-No.: UC3M Working Papers. Statistics and Econometrics;2003-26

Abstract:Since the seminal paper by Dickey and Fuller in 1979, unit-root tests have conditioned the standard approaches to analyse time series with strong serial dependence, the focus being placed in the detection of eventual unit roots in an autorregresive model fitteSince the seminal paper by Dickey and Fuller in 1979, unit-root tests have conditioned the standard approaches to analyse time series with strong serial dependence, the focus being placed in the detection of eventual unit roots in an autorregresive model fitted to the series. In this paper we propose a completely different method to test for the type of -long-wave- patterns observed not only in unit root time series but also in series following more complex data generating mechanism. To this end, our testing device analyses the trend exhibit by the data, without imposing any constraint on the generating mechanism. We call our device the Range Unit Root (RUR) Test since it is constructed from running ranges of the series. These statistics allow a more general characterization of a strong serial dependence in the mean behavior, thus endowing our test with a number of desirable properties. Among these properties are the invariance to nonlinear monotonic transformations of the series and the robustness to the presence of level shifts and additive outliers. In addition, the RUR test outperforms the power of standard unit root tests on near-unit-root stationary time series.+-





Author: Aparicio, Felipe M.; Escribano, Álvaro; García, Ana

Source: http://e-archivo.uc3m.es


Teaser



Universidad Carlos III de Madrid Repositorio institucional e-Archivo http:--e-archivo.uc3m.es Departamento de Estadística DES - Working Papers.
Statistics and Econometrics.
WS 2003-02 Range unit root tests Aparicio, Felipe M. http:--hdl.handle.net-10016-190 Descargado de e-Archivo, repositorio institucional de la Universidad Carlos III de Madrid Working Paper 03-11 Statistics and Econometrics Series 26 February 2003 Departamento de Estadística y Econometría Universidad Carlos III de Madrid Calle Madrid, 126 28903 Getafe (Spain) Fax (34) 91 624-98-49 RANGE UNIT ROOT TESTS Felipe M.
Aparicio, Alvaro Escribano and Ana García* Abstract Since the seminal paper by Dickey and Fuller in 1979, unit-root tests have conditioned the standard approaches to analyse time series with strong serial dependence, the focus being placed in the detection of eventual unit roots in an autorregresive model fitted to the series.
In this paper we propose a completely different method to test for the type of “long-wave” patterns observed not only in unit root time series but also in series following more complex data generating mechanism.
To this end, our testing device analyses the trend exhibit by the data, without imposing any constraint on the generating mechanism.
We call our device the Range Unit Root (RUR) Test since it is constructed from running ranges of the series.
These statistics allow a more general characterization of a strong serial dependence in the mean behavior, thus endowing our test with a number of desirable properties.
Among these properties are the invariance to nonlinear monotonic transformations of the series and the robustness to the presence of level shifts and additive outliers.
In addition, the RUR test outperforms the power of standard unit root tests on near-unit-root stationary time series. Keywords: Unit roots tests, Strong serial dependence; Structural breaks; Nonlinearity; Additive outliers, Near-unit root time series; Invariance; Robustnes...





Related documents