Using wavelets for data smoothing: A simulation study
- 1 December 1999
- journal article
- research article
- Published by Taylor & Francis in Journal of Applied Statistics
- Vol. 26 (8), 923-932
- https://doi.org/10.1080/02664769921936
Abstract
Wavelet shrinkage has been proposed as a highly adaptable approach to signal smoothing, which can produce optimum results in some senses. This paper examines the performance of the method as a function of its parameters, by simulation for time series showing gradual, rapid and discontinuous variations, for a range of signal-to-noise ratios. Some general conclusions are drawn. The effects of the choice of wavelet, choice of threshold and choice of resolution cut-off are considered. The use of the residual autocorrelation as a diagnostic tool is suggested.Keywords
This publication has 15 references indexed in Scilit:
- Fractal Function Estimation via Wavelet ShrinkageJournal of the Royal Statistical Society Series B: Statistical Methodology, 1997
- On choosing a non-integer resolution level when using wavelet methodsStatistics & Probability Letters, 1997
- On preconditioning the data for the wavelet transform when the sample size is not a power of twoCommunications in Statistics - Simulation and Computation, 1997
- A Wavelet Shrinkage Approach to Tomographic Image ReconstructionJournal of the American Statistical Association, 1996
- Adapting to Unknown Smoothness via Wavelet ShrinkageJournal of the American Statistical Association, 1995
- Visual Error Criteria for Qualitative SmoothingJournal of the American Statistical Association, 1995
- Wavelet Methods for Curve EstimationJournal of the American Statistical Association, 1994
- The Discrete Wavelet Transform in SJournal of Computational and Graphical Statistics, 1994
- WaveletsJournal of Applied Statistics, 1994
- A theory for multiresolution signal decomposition: the wavelet representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989