Published
COMPARACIÓN ENTRE DOS MÉTODOS DE REDUCCIÓN DE DIMENSIONALIDAD EN SERIES DE TIEMPO
COMPARISON BETWEEN TWO DIMENSIONALITY REDUCTION METHODS IN TIME SERIES
Keywords:
series de tiempo multivariadas, reducción de dimensionalidad, dominio del tiempo, dominio de las frecuencias (es)Multivariate time series, Reduction of dimensionality, Time domain, Frequency domain (en)
Downloads
1Universidad Santo Tomás, Facultad de Estadística, Centro de Investigaciones y Estudios Estadísticos (CIEES), Bogotá, Colombia. Docente investigadora. Email: hanwenzhang@usantotomas.edu.co
En este trabajo se analizan dos métodos de reducción de dimensionalidad en series de tiempo multivariadas estacionarias: el método de Peña y Box, basado en el dominio del tiempo, y el método de Brillinger, basado en el dominio de las frecuencias. Se encontraron dos fallas en el método de Peña y Box, y se propusieron correcciones a estas. También se compararon los dos métodos con respecto a la capacidad para identificar el número de factores latentes mediante simulaciones y se realizó una aplicación empírica.
Palabras clave: series de tiempo multivariadas, reducción de dimensionalidad, dominio del tiempo, dominio de las frecuencias.
Two methods of dimensionality reduction of multivariate stationary time series are analyzed: Peña-Boxs methodology in the time domain and Brillingers methodology in the frequency domain. Two failures of Peña-Boxs methodology were found, and their corrections are given. Also the two methods are compared regarding to their capacities to identify the number of latent factors by simulations and an empirical application.
Key words: Multivariate time series, Reduction of dimensionality, Time domain, Frequency domain.
Texto completo disponible en PDF
Referencias
1. Ahn, S. K. & Reinsel, G. C. (1988), 'Nested Reduced-Rank Autoregressive Models for Multiple Time Series',Journal of the American Statistical Association 83, 849-856.
2. Brillinger, D. R. (1981), Time Series: Data Analysis and Theory, Holden-Day, San Francisco, United States.
3. Brockwell, P. J. & Davis, R. A. (1991), Time Series: Theory and Methods, 2 edn, Springer, New York, United States.
4. Brockwell, P. J. & Davis, R. A. (1996), Introduction to Time Series and Forecasting, 1 edn, Springer, New York, United States.
5. Correal, M. E. & Peña, D. (2008), 'Modelo factorial dinámico threshold', Revista Colombiana de Estadística31(2), 183-192.
6. Jiménez, J. A. (2004), Álgebra Lineal II, con aplicaciones en estadística, 1 edn, Unibiblos, Bogotá, Colombia.
7. Johansen, S. (1991), 'Estimation and Hypothesis Testing of Cointegration Vectors in Gaussian Vector Autoregressive Models', Econometrica 59(6), 1551-1580.
8. Li, W. K. (2004), Diagnostic Checks in Time Series, 1 edn, Chapman & Hall/CRC.
9. Martínez, W. (2007), Uso de tendencias comunes en la construcción de índices coincidentes, Tesis de maestría, Departamento de Estadística, Facultad de Ciencias, Universidad Nacional de Colombia, Bogotá, Colombia.
10. Melo, L. F., Nieto, F., Posada, C. E., Betancourt, Y. R. & Barón, J. D. (2001), 'Un índice coincidente para la actividad económica de Colombia', Ensayos Sobre Política Económica 40, 46-88.
11. Peña, D. & Box, G. B. P. (1987), 'Identifying a Simplifying Structure in Time Series', Journal of the American Statistical Association 82(399), 836-843.
12. Peña, D. & Poncela, P. (2006), 'Nonstationary Dynamic Factor Analysis', Journal of Statistical Planning and Inference 136(4), 1237-1257.
13. Reinsel, G. C. (1983), 'Some Results on Multivariate Autoregressive Index Models', Biometrika 70, 145-156.
14. Stoffer, D. S. (1999), 'Detecting Common Signals in Multiple Time Series using the Spectral Envelope', Journal of the American Statistical Association 94(448), 1341-1356.
15. Tiao, G. C. & Box, G. E. P. (1981), 'Modelling Multiple Time Series with Applications', Journal of the American Statistical Association 76(376), 802-816.
16. Tiao, G. C. & Tsay, R. S. (1989), 'Model Specification in Multivariate Time Series', Journal of the Royal Statistical Society, B 51(2), 157-213.
17. Wei, W. S. (2006), Time Series Analysis: Univariate and Multivariate Methods, 1 edn, Pearson, Boston, United States.
Este artículo se puede citar en LaTeX utilizando la siguiente referencia bibliográfica de BibTeX:
@ARTICLE{RCEv32n2a02,AUTHOR = {Zhang, Hanwen},
TITLE = {{Comparación entre dos métodos de reducción de dimensionalidad en series de tiempo}},
JOURNAL = {Revista Colombiana de Estadística},
YEAR = {2009},
volume = {32},
number = {2},
pages = {189-212}
}
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
Article abstract page views
Downloads
License
Copyright (c) 2009 Revista Colombiana de Estadística
![Creative Commons License](http://i.creativecommons.org/l/by/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution 4.0 International License.
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).