Outlier detection in interval data

A. Pedro Duarte Silva; Peter Filzmoser; Paula Brito

doi:10.1007/s11634-017-0305-y

Outlier detection in interval data

A. Pedro Duarte Silva^*, Peter Filzmoser, Paula Brito

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

7 Citations (Scopus)

Abstract

A multivariate outlier detection method for interval data is proposed that makes use of a parametric approach to model the interval data. The trimmed maximum likelihood principle is adapted in order to robustly estimate the model parameters. A simulation study demonstrates the usefulness of the robust estimates for outlier detection, and new diagnostic plots allow gaining deeper insight into the structure of real world interval data.

Original language	English
Pages (from-to)	785-822
Number of pages	38
Journal	Advances in Data Analysis and Classification
Volume	12
Issue number	3
DOIs	https://doi.org/10.1007/s11634-017-0305-y
Publication status	Published - Sept 2018

Keywords

Interval data
Mahalanobis distance
Outliers
Robust statistics

Access to Document

10.1007/s11634-017-0305-y

http://hdl.handle.net/10400.14/25171

Cite this

@article{d67ebf85168b4f11aa6434524ad2a2ea,

title = "Outlier detection in interval data",

abstract = "A multivariate outlier detection method for interval data is proposed that makes use of a parametric approach to model the interval data. The trimmed maximum likelihood principle is adapted in order to robustly estimate the model parameters. A simulation study demonstrates the usefulness of the robust estimates for outlier detection, and new diagnostic plots allow gaining deeper insight into the structure of real world interval data.",

keywords = "Interval data, Mahalanobis distance, Outliers, Robust statistics",

author = "Silva, {A. Pedro Duarte} and Peter Filzmoser and Paula Brito",

year = "2018",

month = sep,

doi = "10.1007/s11634-017-0305-y",

language = "English",

volume = "12",

pages = "785--822",

journal = "Advances in Data Analysis and Classification",

issn = "1862-5347",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "3",

}

TY - JOUR

T1 - Outlier detection in interval data

AU - Silva, A. Pedro Duarte

AU - Filzmoser, Peter

AU - Brito, Paula

PY - 2018/9

Y1 - 2018/9

N2 - A multivariate outlier detection method for interval data is proposed that makes use of a parametric approach to model the interval data. The trimmed maximum likelihood principle is adapted in order to robustly estimate the model parameters. A simulation study demonstrates the usefulness of the robust estimates for outlier detection, and new diagnostic plots allow gaining deeper insight into the structure of real world interval data.

AB - A multivariate outlier detection method for interval data is proposed that makes use of a parametric approach to model the interval data. The trimmed maximum likelihood principle is adapted in order to robustly estimate the model parameters. A simulation study demonstrates the usefulness of the robust estimates for outlier detection, and new diagnostic plots allow gaining deeper insight into the structure of real world interval data.

KW - Interval data

KW - Mahalanobis distance

KW - Outliers

KW - Robust statistics

UR - http://www.scopus.com/inward/record.url?scp=85038100119&partnerID=8YFLogxK

U2 - 10.1007/s11634-017-0305-y

DO - 10.1007/s11634-017-0305-y

M3 - Article

AN - SCOPUS:85038100119

SN - 1862-5347

VL - 12

SP - 785

EP - 822

JO - Advances in Data Analysis and Classification

JF - Advances in Data Analysis and Classification

IS - 3

ER -

Outlier detection in interval data

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this