×

Discussion of “The power of monitoring: how to make the most of a contaminated multivariate sample”. (English) Zbl 1428.62240

Summary: [A. Cerioli et al., ibid. 27, No. 4, 559–587 (2018; Zbl 1427.62047)] is a fine review of the practical value of the forward search and the other related robust estimation methods based around monitoring of quantities of interest over a range of consecutive values of the tuning parameters. From a practical standpoint in data analysis the availability of such tools is essential, and the research reported in this paper has brought them to an wide audience. As a potential user of such tools I am particulary interested in their software implementation on one hand and their applicability to an wide range of data analysis problems. More precisely, I would like to address the following two points: (1) the software availability and computational issues related to monitoring and (2) monitoring in one special case, the case of compositional data.

MSC:

62H12 Estimation in multivariate analysis
62J20 Diagnostics, and linear inference and regression

Citations:

Zbl 1427.62047
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Aitchison J (1986) The statistical analysis of compositional data. Monographs on Statistics and Applied Probability. Chapman & Hall Ltd., London (Reprinted in 2003 with additional material by The Blackburn Press), London (UK), 416 · Zbl 0688.62004 · doi:10.1007/978-94-009-4109-0
[2] Atkinson A, Cerioli A, Riani M (2006) Rfwdmv: forward search for multivariate data. R package version 0.72-2. https://cran.r-project.org/src/contrib/Archive/Rfwdmv/. Accessed Mar 2018 · Zbl 1049.62057
[3] Filzmoser P, Hron K (2008) Outlier detection for compositional data using robust methods. Math Geosci 40:233-248 · Zbl 1135.62040 · doi:10.1007/s11004-007-9141-5
[4] Lall S (2000) The technological structure and performance of developing country manufactured exports, 1985-98. Oxford Dev Stud 28(3):337-369 · doi:10.1080/713688318
[5] R Core Team (2017) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. ISBN 3-900051-07-0. http://www.R-project.org/. Accessed Mar 2018
[6] Riani M, Cerioli A, Torti F (2014) On consistency factors and efficiency of robust S-estimators. TEST 23:356-387. https://www.jstatsoft.org/v067/c01 · Zbl 1308.62106
[7] Riani M, Perrotta D, Cerioli A (2015) The forward search for very large datasets. J Stat Softw Code Snippets 67(1):1-20. https://www.jstatsoft.org/v067/c01
[8] Sordini, E.; Todorov, V.; Corbellini, A.; Blanco-Fernandez, A. (ed.); Gonzalez-Rodriguez, G. (ed.), FSDA4R: porting the FSDA toolbox to R (2016), London
[9] Templ, M.; Hron, K.; Filzmoser, P.; Pawlowsky-Glahn, V. (ed.); Buccianti, A. (ed.), robCompositions: an R-package for robust statistical analysis of compositional data, 341-355 (2011), New York · doi:10.1002/9781119976462.ch25
[10] Todorov V (2017) rrcov3way: robust methods for multiway data analysis, applicable also for compositional data. R package version 0.1-10. http://CRAN.R-project.org/package=rrcov3way
[11] Todorov V, Pedersen AL (2017) Competitive industrial performance report 2016. Volumes I and II. Report, United Nations Industrial Development Organization (UNIDO), Vienna. http://stat.unido.org. Accessed Mar 2018
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.