Finding multivariate outliers with FastPCS

Vakili, Kaveh; Schmitt, Éric

doi:10.1016/j.csda.2013.07.021

Cited by 24 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remarkably, the finite sample breakdown point of an estimator can be derived without recourse to concepts of chance or randomness using geometrical features of Email addresses: eric.schmitt@wis.kuleuven.be (Eric Schmitt), viktoria.oellerer@kuleuven.be (ViktoriaÖllerer), kaveh.vakili@wis.kuleuven.be (Kaveh Vakili) a sample alone (Donoho , 1982). Recently, Vakili and Schmitt (2014) introduced the Projection Congruent Subset (PCS) method. PCS computes an outlyingness index, as well as estimates of location and scatter derived from it.…”

Section: Introductionmentioning

confidence: 99%

The finite sample breakdown point of PCS

Schmitt

Öllerer

Vakili

2014

Statistics & Probability Letters

Self Cite

View full text Add to dashboard Cite

a Corresponding author. Afdeling Statistiek, Celestijnenlaan 200b -bus 2400, 3001 Leuven. Tel +32 16 37 23 40. b Faculty of Business and Economics, ORSTAT, KU Leuven, Belgium. c Afdeling Statistiek, Celestijnenlaan 200b -bus 2400, 3001 Leuven. AbstractThe Projection Congruent Subset (PCS) is new method for finding multivariate outliers. PCS returns an outlyingness index which can be used to construct affine equivariant estimates of multivariate location and scatter. In this note, we derive the finite sample breakdown point of these estimators.

show abstract

Section: Introductionmentioning

confidence: 99%

The finite sample breakdown point of PCS

Schmitt

Öllerer

Vakili

2014

Statistics & Probability Letters

Self Cite

View full text Add to dashboard Cite

show abstract

“…One way of detecting outliers is to plot the data points (if possible) and visually inspect the resultant plot for points which lie far outside the general distribution. Another way is to run the analysis on the entire dataset, and then eliminating those points which do not meet mathematical 'control limits' for variability from a trend, and then repeating the analysis on the remaining data (Vakili and Schmitt, 2014).…”

Section: Resultsmentioning

confidence: 99%

Significance of field trials data cleaning process for making more reliable breeder decisions

Babić¹,

Čanak²,

Vujošević³

et al. 2019

Selekcija i semenarstvo

View full text Add to dashboard Cite

Field trials supposed to enable selection of the most successful genotypes which is critical because of the existence of Genotype by Environment interaction. To assess this interaction we are forced to conduct field trials in several environments and/or years. When we asses grain yield of maize hybrids during the breeding process, it is always based on multi-environment small plot field trial (MESPT). That is why this part of the breeding process is most demanding in terms of technical, financial and labor requirements. In this paper, one possible systematic approach to assessing multi-environment field trials conduction is described. The main goal of the described approach is to provide the best possible results with the use of reasonable resources. As the results of trials cannot be directly interpreted without previous statistical processing, quality of raw data as input for biometrical (statistical) analysis is essential for obtaining a relevant and objective measure of genotype relative value in terms of productivity and adaptability (reliability) of new advanced maize hybrids. There are many definitions of data quality but data is generally considered high quality if it is fit for intended uses in operations, decision making and planning. The main aim of this paper is to underline the importance of the data cleaning process in MESPT.

show abstract

“…We implemented the MCD using the proportion 0·75, as recommended by Rousseeuw & Driessen (; preliminary analyses revealed that the results were not sensitive to this proportion), with the function CovNAMcd in the r package rrcovNA (Todorov & Filzmoser ). In preliminary analyses, the MCD outperformed a different robust method called the projection congruent subset (Schmitt, Oellerer & Vakili ; Vakili & Schmitt , results not shown).…”

Section: Methodsmentioning

confidence: 99%

Composite measures of selection can improve the signal‐to‐noise ratio in genome scans

et al. 2017

View full text Add to dashboard Cite

Summary The growing wealth of genomic data is yielding new insights into the genetic basis of adaptation, but it also presents the challenge of extracting the relevant signal from multi‐dimensional datasets. Different statistical approaches vary in their power to detect selection depending on the demographic history, type of selection, genetic architecture and experimental design. Here, we develop and evaluate new approaches for combining results from multiple tests, including multivariate distance measures and methods for combining P‐values. We evaluate these methods on (i) simulated landscape genetic data analysed for differentiation outliers and genetic‐environment associations and (ii) empirical genomic data analysed for selective sweeps within dog breeds for loci known to be selected for during domestication. We also introduce and evaluate how robust statistical algorithms can be used for parameter estimation in statistical genomics. On the simulated data, many of the composite measures performed well and had decreased variation in outcomes across many sampling designs. On the empirical dataset, methods based on combining P‐values generally performed better with clearer signals of selection, higher significance of the signal, and in closer proximity to the known selected locus. Although robust algorithms could identify neutral loci in our simulations, they did not universally improve power to detect selection. Overall, a composite statistic that measured a robust multivariate distance from rank‐based P‐values performed the best. We found that composite measures of selection could improve the signal of selection in many cases, but they were not a panacea and their power is limited by the power of the univariate statistics they summarize. Since genome scans are widely used, improving inference for prioritizing candidate genes may be beneficial to medicine, agriculture, and breeding. Our results also have application to outlier detection in high‐dimensional datasets and to combining results in meta‐analyses in many disciplines. The compound measures we evaluate are implemented in the r package minotaur.

show abstract

Finding multivariate outliers with FastPCS

Cited by 24 publications

References 15 publications

The finite sample breakdown point of PCS

The finite sample breakdown point of PCS

Significance of field trials data cleaning process for making more reliable breeder decisions

Composite measures of selection can improve the signal‐to‐noise ratio in genome scans

Contact Info

Product

Resources

About