The Choice of a Primary Resolution and Basis Functions in Wavelet Series for Random or Irregular Design Points Using Bayesian Methods Park, Chun-Gun;
In this paper, the choice of a primary resolution and wavelet basis functions are introduced under random or irregular design points of which the sample size is free of a power of two. Most wavelet methods have used the number of the points as the primary resolution. However, it turns out that a proper primary resolution is much affected by the shape of an unknown function. The proposed methods are illustrated by some simulations.