RobStatTM v1.0.2


Monthly downloads



Robust Statistics: Theory and Methods

Companion package for the book: "Robust Statistics: Theory and Methods, second edition", <>. This package contains code that implements the robust estimators discussed in the recent second edition of the book above, as well as the scripts reproducing all the examples in the book.



This repository contains a development version of the companion package to the 2nd edition of the book Robust Statistics: Theory and Methods, by Ricardo Maronna, Doug Martin, Victor Yohai and Matias Salibian-Barrera.

  • The latest official version of the package is available on CRAN. You should probably use that version.
  • To install the "development" version on GitHub, use
  • The scripts reproducing the examples and figures in the book can be found in the folder inst/scripts.

Bug reports

We use GitHub issues to track and solve potential bugs in our package. When submitting your bug report please:

  1. Check if your issue / bug has been fixed by trying to reproduce it using the latest version of the package.

  2. Isolate the problem by creating a minimal reproducible example (see below)

  3. Create an issue for this repository. Refer to this page for instructions on how to create a GitHub issue.

A good bug report should not require others to contact you to find more information. Please try to be as detailed as possible in your report. What is your environment? What steps will reproduce the issue? What outcome did you expect and what outcome did you get?


A short and descriptive bug report title

A summary of the issue and the OS environment in which it occurs. Include the steps required to reproduce the bug.

  1. This is the first step
  2. This is the second step
  3. Further steps, etc.

Any other information you want to share that is relevant to the issue being reported. This might include the lines of code that you have identified as causing the bug, and potential solutions.

Minimal reproducible examples

(This section is adapted from Rob Hyndman's notes on minimal reproducible examples).

A Minimal reproducible example (MRE) is intended to reproduce an error using the smallest amount of code possible. To check that your MRE code is reproducible, try running it in a fresh R session before you submit the issue. Using minimal reproducible examples saves package developers time in wading through messy code that is not relevant to the apparent bug.

A MRE should consist of a single R script file that can be run without error in a fresh R session, and should contain the following three sections:

  • Packages to be loaded.
  • The shortest amount of code that reproduces the problem.
  • The output of sessionInfo() as a comment.

Please remove anything that is not necessary to reproduce the problem.

Try to use one of the built-in datasets if possible. If you need to include some data, then use dput() so the data can be included as part of the same text file. In most cases, you do not need to include all of your data, just a small subset that will allow the problem to be reproduced.

If you randomly generate some data, use set.seed(somenumber).

Please spend time adding comments so we can understand your code quickly.

Functions in RobStatTM

Name Description
covRobMM MM robust multivariate location and scatter estimator
SMPY SM regression estimator using Pen~a-Yohai candidates
covRob Robust multivariate location and scatter estimators
ShinyUI Open the Shiny interface for the package
covClassic Classical Covariance Estimation
lmrobdetDCML Robust Distance Constrained Maximum Likelihood estimators for linear regression
drop1.lmrobdetMM RFPE of submodels of an lmrobdetMM fit
lmrobdetMM.RFPE Robust Final Prediction Error
locScaleM Robust univariate location and scale M-estimators
MMPY MM regression estimator using Pen~a-Yohai candidates
shock Shock data
INVTR2 Robust R^2 coefficient of determination
initPP Robust multivariate location and scatter estimators
bisquare Tuning parameter the rho loss functions
pcaRobS Robust principal components
biochem Biochem data
lmrobM Robust estimators for linear regression with fixed designs
covRobRocke Rocke's robust multivariate location and scatter estimator
neuralgia Neuralgia data
rho Rho functions
rhoprime The first derivative of the rho function
bus Bus data
cov.dcml Approximate covariance matrix of the DCML regression estimator.
fastmve Minimum Volume Ellipsoid covariance estimator
oats Oats data
lmrobM.control Tuning parameters for lmrobM
alcohol Alcohol data
wine Wine data
opt Tuning parameter for a rho function in the (asymptotic bias-) optimal family
image Image data
lmrobdet.control Tuning parameters for lmrobdetMM and lmrobdetDCML
prcompRob Robust Principal Components Cont'd
step.lmrobdet Robust stepwise using RFPE
logregBY Bianco and Yohai estimator for logistic regression
algae Algae data
flour Flour data
skin Skin data
mopt Tuning parameter for a rho function in the modified (asymptotic bias-) optimal family
stackloss Stackloss data
scaleM M-scale estimator
rhoprime2 The second derivative of the rho function
lmrobLinTest Robust likelihood ratio test for linear hypotheses
waste Waste data
logregWML Weighted likelihood estimator for the logistic model
logregWBY Bianco and Yohai estimator for logistic regression
DCML DCML regression estimator
vehicle Vehicle data
lmrobdetMM Robust linear regression estimators
glass Glass data
hearing Hearing data
mineral Mineral data
resex Resex data IRWLS iterations for S- or M-estimators
No Results!

Vignettes of RobStatTM

No Results!

Last month downloads


Date 2020-03-02
LazyData yes
License GPL (>= 3)
RoxygenNote 6.1.1
Encoding UTF-8
VignetteBuilder knitr, R.rsp
NeedsCompilation yes
Packaged 2020-03-02 20:35:25 UTC; matias
Repository CRAN
Date/Publication 2020-03-03 00:30:02 UTC

Include our badge in your README