README.md

In giannamonti/RobZS: Robust ZeroSum Regression

RobZS

RobZS is an R-package for fitting robust linear log-contrast models [1] combined with the elastic-net regularization [2].

By combining the least trimmed squares (LTS) objective function with the elastic-net penalty, Monti et al. (2020) introduced the sparse least trimmed squares estimator with compositional covariates for high dimensional data with continuos [3] and binary [4] response. They proposed a trimmed version of the ZeroSum estimator [5].

Most part of the R code is adapted from [6].

Installation

You can install the released version of RobZS from GitHub with:

devtools::install_github("giannamonti/RobZS")

References

1. Aitchison J, Bacon-Shone J (1984) Log Contrast Models for Experiments with Mixtures. Biometrika; 71(2): 323-330.
2. Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67(2):301-320.
3. Monti GS, Filzmoser, P (2021) Sparse least trimmed squares regression with compositional covariates for high dimensional data, submitted manuscript
4. Monti GS, Filzmoser, P (2021) Robust Logistic Zero-Sum Regression for Microbiome Compositional Data, submitted manuscript
5. Altenbuchinger M, Rehberg T, Zacharias HU, et al. (2017) Reference point insensitive molecular data analysis. Bioinformatics; 33 2: 219-226.
6. Kurnaz FS, Hoffmann I, Filzmoser P (2018) Robust and sparse estimation methods for high-dimensional linear and logistic regression. Chemometrics and Intelligent Laboratory Systems; 172: 211 - 222.

giannamonti/RobZS documentation built on July 15, 2021, 3:22 a.m.