1Banco de la República. E-mail: egonzamo@banrep.gov.co
2Universidad Nacional de Colombia. E-mail:fhnietos@unal.edu.co
Testing for unit roots is a common practice in observable stochastic processes and there is abundant literature on this topic. However, sometimes, one is faced with the same problem but in the case where the processes of inter est are latent or unobservable. In this paper, empirical distributions of the usual unit-root test statistics are obtained for the trend component of some particular structural models, which are based on optimal predictions (as the observed data) of the trend stochastic process. It is found that these statis tical tests tend to be most powerful than the usual Dickey-Fuller tests.
]]> Keywords: Structural models, Unit roots, Unobservable process.
Las pruebas de raíces unitarias son una práctica común en procesos estocásti cos observables y se encuentra literatura abundante sobre este tema. Sin embargo, en ocasiones, aunque el problema es el mismo, los procesos de interés son latentes o no observables. En este artículo se obtienen distribu ciones empíricas de las estadísticas de prueba usuales de raíces unitarias para el componente de tendencia de algunos modelos estructurales particulares, basadas en predicciones óptimas (como los datos observados) del proceso es tocástico de tendencia. Se encuentra que estas pruebas estadísticas tienden a ser más potentes que las pruebas usuales de Dickey-Fuller.
Palabras Clave: Modelos estructurales, raíces unitarias, procesos no obser- vables.
Texto completo disponible en PDF
References
1. Bell, W. R. (1984), "Signal extraction for nonstationary time series", The Annals of Statistics 12, 646- 664. [ Links ]
2. Dickey, D. & Fuller, W. (1979), "Distributions of the estimators for autoregressive time series with a unit root", Journal of the American Statistical Association 74, 427- 431. [ Links ]
3. Fuller, W. (1996), Introduction to Statistical Time Series, 2 edn, John Wiley & Sons, New York. [ Links ]
4. Harvey, A. (1989), Forecasting, Structural Time Series Models and the Kalman Filter, Cambridge University Press, Cambridge. [ Links ]
5. Harvey, A. (2001), "Testing in unobserved components models", Journal of Forecasting 20, 1- 19. [ Links ]
6. Kaiser, R. & Maravall, A. (2001), Measuring business cycles in economic time series, in "Lecture Notes in Statistics", Springer-Verlag, New York. [ Links ]
7. Koopman, S., Harvey, A. C., Doornik, J. & Shephard, N. (1995), STAMP 5.0 Structural Time Series Analyzer, Modeler and Predictor, Chapman and Hall, London. [ Links ]
8. Kwiatkowski, D., Phillips, P. S. & Shin, Y. (1992), "Testing the null hypothesis of stationarity against the alternative of a unit root: Economic time series have a unit root?", Journal of Econometrics 54, 159- 178. [ Links ]
9. Nyblom, J. & Makelainen, T. (1983), "Comparisons of tests for the presence of random walk coefficients in a simple linear model", Journal of the American Statistical Association 78(384). [ Links ]
10. Phillips, P. & Perron, P. (1988), "Testing for a unit root in time series regression", Biometrika 75, 335- 346. [ Links ]
11. Schmidt, P. & Phillips, P. C. B. (1992), "LM test for a unit root in the presence of deterministic trends", Oxford Bulletin of Economics and Statistics 54, 257- 287. [ Links ] ]]>