The R Journal: article published in 2020, volume 12:2

miWQS: Multiple Imputation Using Weighted Quantile Sum Regression PDF download
Paul M. Hargarten and David C. Wheeler , The R Journal (2020) 12:2, pages 226-250.

Abstract The miWQS package in the Comprehensive R Archive Network (CRAN) utilizes weighted quantile sum regression (WQS) in the multiple imputation (MI) framework. The data analyzed is a set/mixture of continuous and correlated components/chemicals that are reasonable to combine in an index and share a common outcome. These components are also interval-censored between zero and upper thresholds, or detection limits, which may differ among the components. This type of data is found in areas such as chemical epidemiological studies, sociology, and genomics. The miWQS package can be run using complete or incomplete data, which may be placed in the first quantile, or imputed using bootstrap or Bayesian approach. This article provides a stepwise and hands-on approach to handle uncertainty due to values below the detection limit in correlated component mixture problems.

Received: 2020-04-04; online 2021-01-14, supplementary material, (3.7 Kb)
CRAN packages: miWQS, wqs, gWQS, mice, norm, mi, coda, Rsolnp, glm2, rlist, Hmisc, tidyr, ggplot2, survival, invgamma, truncnorm, purrr, GGally, rticles
CRAN Task Views implied by cited CRAN packages: MissingData, SocialSciences, OfficialStatistics, Bayesian, ClinicalTrials, Econometrics, Multivariate, Distributions, gR, Graphics, Optimization, Phylogenetics, ReproducibleResearch, Survival, TeachingStatistics

CC BY 4.0
This article and supplementary materials are licensed under a Creative Commons Attribution 4.0 International license.

  author = {Paul M. Hargarten and David C. Wheeler},
  title = {{miWQS: Multiple Imputation Using Weighted Quantile Sum
  year = {2021},
  journal = {{The R Journal}},
  doi = {10.32614/RJ-2021-014},
  url = {},
  pages = {226--250},
  volume = {12},
  number = {2}