CVThresh (version 1.1.0)

cvwavelet: Wavelet reconstruction by level-dependent Cross-Validation

Description

This function reconstructs the noise data by level-dependent cross-validation wavelet shrinkage.

Usage

cvwavelet(y=y, ywd=ywd, cv.optlevel, cv.bsize=1, cv.kfold, 
    cv.random=TRUE, cv.tol=0.1^3, cv.maxiter=100,
    impute.vscale="independent", impute.tol=0.1^3, impute.maxiter=100,
    filter.number=10, family="DaubLeAsymm", thresh.type ="soft", ll=3)

Arguments

y

observation

ywd

DWT object

cv.optlevel

thresholding levels

cv.bsize

block size of cross-validation

cv.kfold

the number of fold of cross-validation

cv.random

whether or not random cross-validation scheme should be used. Set cv.random=TRUE for random cross-validation scheme

cv.tol

tolerance for cross-validation

cv.maxiter

maximum iteration for cross-validation

impute.vscale

specifies whether variance is adjusted level-by-level or not. ``level" or ``independent"

impute.tol

tolerance for imputation

impute.maxiter

maximum iteration for imputation

filter.number

specifies the smoothness of wavelet in the decomposition (argument of WaveThresh)

family

specifies the family of wavelets ``DaubExPhase" or ``DaubLeAsymm" (argument of WaveThresh)

thresh.type

specifies the type of thresholding ``hard" or ``soft" (argument of WaveThresh)

ll

specifies the lowest level to be thresholded

Value

• y
  observations
• yimpute
  imputed values by provided cross-validation scheme
• yc
  reconstruction by level-dependent cross-validation wavelet shrinkage
• cvthresh
  threshold values by level-dependent cross-validation

Details

This function performs level-dependent cross-validation wavelet shrinkage.

See Also

cvtype, cvimpute.by.wavelet, cvwavelet.after.impute.

Examples

data(ipd)
y <- as.numeric(ipd); n <- length(y); nlevel <- log2(n)
ywd <- wd(y)
out <- cvwavelet(y=y, ywd=ywd, cv.optlevel=c(3:(nlevel-1)), 
                     cv.bsize=2, cv.kfold=4)

ts.plot(ts(out$yc, start=1229.98, deltat=0.02, frequency=50),
   main="Level-dependent Cross Validation", xlab = "Seconds", ylab="")