Asymmetric Prior in Wavelet Shrinkage

• Autores: Alex Rodrigo Dos Santos Sousa
• Localización: Revista Colombiana de Estadística, ISSN-e 2389-8976, ISSN 0120-1751, Vol. 45, Nº. 1, 2022, págs. 41-63
• Idioma: inglés
• DOI: 10.15446/rce.v45n1.92567
• Títulos paralelos:
  • Priori asimétrico en contracción de ondículas
• Enlaces
  • Texto completo
• Resumen
  • español

    Resumen En la contracción de las ondículas bayesianas, se supone que los coeficientes a priori ya propuestos de las ondículas son simétricos alrededor de cero. Aunque esta suposición es razonable en muchas aplicaciones, no es general. El presente artículo propone el uso de una regla de contracción asimétrica basada en la mezcla discreta de una función de masa puntual en cero y una distribución beta asimétrica como priori de los coeficientes de ondícula en un modelo de regresión no paramétrico. Se proporcionan propiedades estadísticas tales como sesgo, varianza, riesgos clásicos y bayesianos de la regla asimétrica asociada y se obtienen los rendimientos de la regla propuesta en estudios de simulación que involucran coeficientes distribuidos asimétricos artificiales y las funciones de prueba de Donoho-Johnstone. También se analiza la aplicación en un conjunto de datos sísmicos reales.

  • English

    Abstract In bayesian wavelet shrinkage, the already proposed priors to wavelet coefficients are assumed to be symmetric around zero. Although this assumption is reasonable in many applications, it is not general. The present paper proposes the use of an asymmetric shrinkage rule based on the discrete mixture of a point mass function at zero and an asymmetric beta distribution as prior to the wavelet coefficients in a non-parametric regression model. Statistical properties such as bias, variance, classical and bayesian risks of the associated asymmetric rule are provided and performances of the proposed rule are obtained in simulation studies involving artificial asymmetric distributed coefficients and the Donoho-Johnstone test functions. Application in a seismic real dataset is also analyzed.

• Referencias bibliográficas
  • Abramovich, F.,Benjamini, Y. (1996). 'Adaptive thresholding of wavelet coefficients'. Computational Statistics and Data Analysis....
  • Abramovich, F.,Sapatinas, T.,Silverman, B. (1998). 'Wavelet thresholding via a bayesian approach'. Royal Statistical Society. 725
  • Angelini, C.,Vidakovic, B. (2004). 'Gama-minimax wavelet shrinkage: a robust incorporation of information about energy of a signal in...
  • Antoniadis, A.,Bigot, J.,Sapatinas, T. (2001). 'Wavelet estimators in nonparametric regression: a comparative simulation study'. Journal...
  • Beenamol, M.,Prabavathy, S.,Mohanalin, J. (2012). 'Wavelet based seismic signal de-noising using shannon and tsallis entropy'. Computers...
  • Bhattacharya, A.,Pati, D.,Pillai, N.,Dunson, D. (2015). 'Dirichlet-laplace priors for optimal shrinkage'. Journal of the American...
  • Chipman, H.,Kolaczyk, E.,McCulloch, R. (1997). 'Adaptive bayesian wavelet shrinkage'. Journal of the American Statistical Association....
  • Cutillo, L.,Jung, Y.,Ruggeri, F.,Vidakovic, B. (2008). 'Larger posterior mode wavelet thresholding and applications'. Journal of Statistical...
  • Donoho, D. L. (1995). 'De-noising by soft-thresholding'. IEEE Transactions on Information Theory. 613
  • Donoho, D. L. (1995). 'Nonlinear solution of linear inverse problems by wavelet-vaguelette decomposition'. Applied and Computational...
  • Donoho, D. L.,Johnstone, I. M. (1994). 'Ideal denoising in an orthonormal basis chosen from a library of bases'. Comptes Rendus de...
  • Donoho, D. L.,Johnstone, I. M. (1994). 'Ideal spatial adaptation by wavelet shrinkage'. Biometrika. 425
  • Donoho, D. L.,Johnstone, I. M. (1995). 'Adapting to unknown smoothness via wavelet shrinkage'. Journal of the American Statistical...
  • Donoho, D. L.,Johnstone, I. M.,Kerkyacharian, G.,Picard, D. (1995). 'Wavelet shrinkage: Asymptopia? (with discussion)'. Royal Statistical...
  • Donoho, D. L.,Johnstone, I. M.,Kerkyacharian, G.,Picard, D. (1996). 'Density estimation by wavelet thresholding'. Annals of Statistics....
  • Griffin, J.,Brown, P. (2017). 'Hierarquical shrinkage priors for regression models'. Bayesian Analysis. 12. 135
  • Jansen, M. (2001). Noise reduction by wavelet thresholding. Springer. New York.
  • Johnstone, L.,Silverman, B. (2005). 'Empirical bayes selection of wavelet thresholds'. The Annals of Statistics. 1700
  • Karagiannis, G.,Konomi, B.,Lin, G. (2015). 'A bayesian mixed shrinkage prior procedure for spatial-stochastic basis selection and evaluation...
  • Lian, H. (2011). 'On posterior distribution of bayesian wavelet thresholding'. Journal of Statistical Planning and Inference. 318
  • Mallat, S. G. (1998). A Wavelet Tour of Signal Processing. Academic Press, San Diego.
  • Nason, G. P. (1996). 'Wavelet shrinkage using cross-validation'. Journal of the Royal Statistical Society B. 463
  • Reményi, N.,Vidakovic, B. (2015). 'Wavelet shrinkage with double weibull prior'. Communications in Statistics: Simulation and Computation....
  • Sousa, A. (2020). 'Bayesian wavelet shrinkage with logistic prior'. Communications in Statistics: Simulation and Computation.
  • Sousa, A.,Garcia, N.,Vidakovic, B. (2021). 'Bayesian wavelet shrinkage with beta prior'. Computational Statistics. 36. 1341
  • Torkamani, R.,Sadeghzadeh, R. (2017). 'Bayesian compressive sensing using wavelet based markov random fields'. Signal Processing:...
  • Vidakovic, B. (1998). 'Nonlinear wavelet shrinkage with bayes rules and bayes factors'. Journal of the American Statistical Association....
  • Vidakovic, B. (1999). Statistical Modeling by Wavelets. Wiley. New York.
  • Vidakovic, B.,Ruggeri, F. (2001). 'Bams method: Theory and simulations'. Sankhya: The Indian Journal of Statistics. 234