pmledecon: Deconvolution Density Estimation using Penalized MLE

Given a sample with additive measurement error, the package estimates the deconvolution density - that is, the density of the underlying distribution of the sample without measurement error. The method maximises the log-likelihood of the estimated density, plus a quadratic smoothness penalty. The distribution of the measurement error can be either a known family, or can be estimated from a "pure error" sample. For known error distributions, the package supports Normal, Laplace or Beta distributed error. For unknown error distribution, a pure error sample independent from the data is used.

Version: 0.2.1
Depends: R (≥ 3.6.0)
Imports: stats, splitstackshape, rmutil
Published: 2022-05-30
DOI: 10.32614/CRAN.package.pmledecon
Author: Yun Cai [aut, cre], Hong Gu [aut], Tobias Kenney [aut]
Maintainer: Yun Cai <Yun.Cai at>
License: GPL (≥ 3)
NeedsCompilation: no
CRAN checks: pmledecon results


Reference manual: pmledecon.pdf


Package source: pmledecon_0.2.1.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): pmledecon_0.2.1.tgz, r-oldrel (arm64): pmledecon_0.2.1.tgz, r-release (x86_64): pmledecon_0.2.1.tgz, r-oldrel (x86_64): pmledecon_0.2.1.tgz
Old sources: pmledecon archive

Reverse dependencies:

Reverse imports: DBNMFrank


Please use the canonical form to link to this page.