Time series discrimination using likelihood function of discrete wavelet coefficients

Document Type : Original Paper

Authors

Department of Statistics, Shahid Chamran University, Ahvaz, Iran

Abstract

In this paper, the likelihood ratio of two normal density functions are approximated using discrete wavelet transform and a nonparametric criteria for discrimination of a stationary time series models in the wavelet domain are obtained. The performance of discriminant rule is shown in ARMA models using simulation techniques. In addition to do not requiring to parametric model, speed calculations for large time series and very low error rate are two characteristics of wavelet discriminate criteria.

In this paper, the likelihood ratio of two normal density functions are approximated using discrete wavelet transform and a nonparametric criteria for discrimination of a stationary time series models in the wavelet domain are obtained. The performance of discriminant rule is shown in ARMA models using simulation techniques. In addition to do not requiring to parametric model, speed calculations for large time series and very low error rate are two characteristics of wavelet discriminate criteria.

Keywords

Main Subjects

Full Text

Download Fulltext

References

[1] Shumway, R.H. and Stoffer, D.S. (2011). Time Series Analysis and Applications, Second Edition, Springer, New York. [2] Chan, H.T. (1991). Discriminant analysis of Time Series. Ph.D. Thesis, Newcastle University. [3] Chan, H.T., Chinipardaz, R. and
Cox, T.F. (1996). Discrimination of AR, MA and ARMA time series models, Comm. Stat. Theory and Method, 25(6), 1247-1260. [4] Chinipardaz, R. (2000). Discrimination analysis in AR(1) plus noise processes, Iranian Journal of Science & Technology, Trans.
, 24(2), 165-172. [5] Mansouri, B., Chinipardaz, R. and Parham, G. A. (2011). Discrimination analysis in AR(p) plus different noises processes. Iranian Journal of Since and Technology Transaction A: Since. 35. [6] Chinipardaz, R. and Cox, T.F. (2004).
Nonparametric discrimination of time series, Metrika, 59(1), 13-20. [7] Liget, W.S. (1971). On the asymptotic optimality of spectral analysis for testing hypotheses about time series, Annals of Math Stat, 42, 1348- 1358. [8] Shumway, R.H. and Unger, A.N. (1974). Linear discriminant function for stationary time series, J. Amer. Stat. Assoc., 69, 948-956

Files

History

  • Receive Date: 03 July 2013
  • Revise Date: 17 April 2014
  • Accept Date: 30 April 2014

Share

How to cite

Statistics