This package carries out level-dependent cross-validation method for the selection of thresholding value in wavelet shrinkage. This procedure is implemented by coupling a conventional cross validation with an imputation method due to a limitation of data length, a power of 2. It can be easily applied to classical leave-one-out and k-fold cross validation. Since the procedure is computationally fast, a level-dependent cross validation can be performed for wavelet shrinkage of various data such as a data with correlated errors.
|Depends:||R (≥ 2.15.1), wavethresh (≥ 4.6.1), EbayesThresh (≥ 1.3.2)|
|Author:||Donghoh Kim, Hee-Seok Oh|
|Maintainer:||Donghoh Kim <donghoh.kim at gmail.com>|
|License:||GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]|
|CRAN checks:||CVThresh results|
|Windows binaries:||r-devel: CVThresh_1.1.1.zip, r-release: CVThresh_1.1.1.zip, r-oldrel: CVThresh_1.1.1.zip|
|OS X Mavericks binaries:||r-release: CVThresh_1.1.1.tgz, r-oldrel: CVThresh_1.1.1.tgz|
|Old sources:||CVThresh archive|
Please use the canonical form https://CRAN.R-project.org/package=CVThresh to link to this page.