Empirical Bayes wavelet smoothing via DWT

Smooth homogeneous Gaussian data.

Usage

smash_dwt(
  x,
  sigma,
  filter.number = 1,
  family = "DaubExPhase",
  ebnm_params = list(mode = 0),
  W = NULL
)

Arguments

x

data

sigma

known standard error

filter.number, family

wavelet family and filter number as in wavethresh package

ebnm_params

a list of `ebnm` parameters

W

the dwt matrix for calc posterior variance. Remove the first row which is all 1/sqrt(n)

Value

a list of

mu.est:

posterior mean

mu.est.var:

posterior variance

loglik:

log likelihood

dKL:

KL divergence between g(the prior) and q(the posterior)