Wavelet Thresholding Methods Applied to Testing Significance Differences Between Autoregressive Hilbertian Processes
The philosophy of Fan (1996) and Fan and Lin (1998) is adopted in the formulation of significance tests for comparing autoregressive Hilbertian processes. The discrete wavelet domain is considered to derive the test statistic based on thresholding rules. The results derived are applied to the statistical analysis of spatial functional data (SFD) sequences.
KeywordsAmerican Statistical Association Wavelet Domain Functional Data Analysis Hard Thresholding Thresholding Rule
Unable to display preview. Download preview PDF.
- Abramovich, F., Antoniadis, A., Sapatinas, T. and Vidakovic, B.: Optimal testing in functional analysis of variance models. Int. J. Wavelets Multiresolution Inform. Process. 2, 323-349.Google Scholar
- Bosq, D.: Linear processes in function spaces. Springer-Verlag. (2000).Google Scholar
- Brillinger, D. R.: The analysis of time series collected in an experiment design. In Multivariate analysis, III. Krishnaiah, P.R. (ed.), Academic Press, 241-256 (1973).Google Scholar
- Brillinger, D. R.: Some aspect of the analysis of evoked response experiments. In Statistics and related topics. Csörgö, M., Dawson, D.A. Rao, J.N.K. and Saleh, A.K. (eds.), North-Holland, 15-168 (1980).Google Scholar
- Ferraty, F. and Vieu, P.: Nonparameric functional data analysis. Springer. (2006).Google Scholar
- Maraun, D. and Kurths, J.: Cross-wavelet analysis: signi cance testing and pitfalls. Nonlinear Processes in Geophysics. 11, 505-514 (2004).Google Scholar
- Ramsay, J.O. and Silverman, B.W.: Functional data analysis. Springer. (2005).Google Scholar
- Shumway, R.H.: Applied statistical time series analysis. Prentice-Hall. (1988).Google Scholar
- Vidakovic, B.: Statistical modeling by wavelets. John Wiley & Sons. (1999).Google Scholar