Technical appendix to real nonparametric regres - sion using complex wavelets
نویسنده
چکیده
1.1 Pictures of complex wavelets Figure 1 shows the six distinct Daubechies’ wavelets with five vanishing moments. Panels (c) and (f) show respectively the familiar extremal phase and least asymmetric real wavelets, while the other panels show the four distinct complex-valued wavelets. Even though these cDws share the same number of vanishing moments, they are visually very different to each other. In particular, the number of oscillations vary, as does the relative magnitude of the real and imaginary parts.
منابع مشابه
Real nonparametric regression using complex wavelets
Wavelet shrinkage is an effective nonparametric regression technique, especially when the underlying curve has irregular features such as spikes or discontinuities. The basic idea is simple: take the discrete wavelet transform (DWT) of data consisting of a signal corrupted by noise; shrink or remove the wavelet coefficients to remove the noise; and then invert the DWT to form an estimate of the...
متن کاملDenoising Real Images Using Complex-Valued Wavelets
Although the details are more complicated in two dimensions, the basic ideas behind (1) and (2) are the same: a function is described in terms of scaled and shifted copies of the “building blocks” and . More details can be found in (e.g.) Vidakovic (1999). The two families of compactly supported wavelets described by Daubechies (1992) are by far the most commonly used. These “extremal phase” an...
متن کاملBandwidth Selection for Local Linear Regres- Sion: a Simulation Study
This paper provides a simulation study of several popular bandwidth selectors for local linear regression. The study also includes two new selectors which couple the non{asymptotic plug{in and the unbiased risk estimation techniques. These two new selectors are simple to describe, easy to implement and performed very well in our simulation study.
متن کاملBandwidth Selection for Local Linear Regres - sion : A Simulation
This paper provides a simulation study of several popular bandwidth selectors for local linear regression. The study also includes two new selectors which couple the non{asymptotic plug{in and the unbiased risk estimation techniques. These two new selectors are simple to describe, easy to implement and performed very well in our simulation study.
متن کاملWavelets for Nonparametric Stochastic Regression with Pairwise Negative Quadrant Dependent Random Variables
We propose a wavelet based stochastic regression function estimator for the estimation of the regression function for a sequence of pairwise negative quadrant dependent random variables with a common one-dimensional probability density function. Some asymptotic properties of the proposed estimator are investigated. It is found that the estimators have similar properties to their counterparts st...
متن کامل