Bagplots, boxplots, and outlier detection for functional data

Rob J. Hyndman; Han Lin Shang

doi:10.1007/978-3-7908-2062-1_31

Bagplots, boxplots, and outlier detection for functional data

Rob J. Hyndman^*, Han Lin Shang

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

We propose some new tools for visualizing functional data and for identifying functional outliers. The proposed tools make use of robust principal component analysis, data depth and highest density regions. We compare the proposed outlier detection methods with the existing “functional depth” method, and show that our methods have better performance on identifying outliers in French male age-specific mortality data.

Original language	English
Title of host publication	Functional and operatorial statistics
Editors	Sophie Dabo-Niang, Frâedâeric Ferraty
Place of Publication	Heidelberg
Publisher	Springer
Pages	201-207
Number of pages	7
ISBN (Electronic)	9783790820621
ISBN (Print)	9783790820614
DOIs	https://doi.org/10.1007/978-3-7908-2062-1_31
Publication status	Published - 2008
Externally published	Yes
Event	International Workshop on Functional and Operatorial Statistics (1st : 2008) - Toulouse, France Duration: 19 Jun 2008 → 21 Jun 2008

Publication series

Name	Contributions to statistics
Publisher	Springer
ISSN (Print)	1431-1941

Conference

Conference	International Workshop on Functional and Operatorial Statistics (1st : 2008)
Country/Territory	France
City	Toulouse
Period	19/06/08 → 21/06/08

Keywords

Functional Data
Outlier Detection
Principal Component Score
High Density Region
Robust Principal Component Analysis

Access to Document

10.1007/978-3-7908-2062-1_31

Cite this

@inproceedings{0d3b90d214a340b780f6d9c508e54226,

title = "Bagplots, boxplots, and outlier detection for functional data",

abstract = "We propose some new tools for visualizing functional data and for identifying functional outliers. The proposed tools make use of robust principal component analysis, data depth and highest density regions. We compare the proposed outlier detection methods with the existing “functional depth” method, and show that our methods have better performance on identifying outliers in French male age-specific mortality data.",

keywords = "Functional Data, Outlier Detection, Principal Component Score, High Density Region, Robust Principal Component Analysis",

author = "Hyndman, {Rob J.} and Shang, {Han Lin}",

year = "2008",

doi = "10.1007/978-3-7908-2062-1_31",

language = "English",

isbn = "9783790820614",

series = "Contributions to statistics",

publisher = "Springer",

pages = "201--207",

editor = "Sophie Dabo-Niang and Fr{\^a}ed{\^a}eric Ferraty",

booktitle = "Functional and operatorial statistics",

note = "International Workshop on Functional and Operatorial Statistics (1st : 2008) ; Conference date: 19-06-2008 Through 21-06-2008",

}

Hyndman, RJ & Shang, HL 2008, Bagplots, boxplots, and outlier detection for functional data. in S Dabo-Niang & F Ferraty (eds), Functional and operatorial statistics. Contributions to statistics, Springer, Heidelberg, pp. 201-207, International Workshop on Functional and Operatorial Statistics (1st : 2008), Toulouse, France, 19/06/08. https://doi.org/10.1007/978-3-7908-2062-1_31

Bagplots, boxplots, and outlier detection for functional data. / Hyndman, Rob J.; Shang, Han Lin.
Functional and operatorial statistics. ed. / Sophie Dabo-Niang; Frâedâeric Ferraty. Heidelberg: Springer, 2008. p. 201-207 (Contributions to statistics).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Bagplots, boxplots, and outlier detection for functional data

AU - Hyndman, Rob J.

AU - Shang, Han Lin

PY - 2008

Y1 - 2008

N2 - We propose some new tools for visualizing functional data and for identifying functional outliers. The proposed tools make use of robust principal component analysis, data depth and highest density regions. We compare the proposed outlier detection methods with the existing “functional depth” method, and show that our methods have better performance on identifying outliers in French male age-specific mortality data.

AB - We propose some new tools for visualizing functional data and for identifying functional outliers. The proposed tools make use of robust principal component analysis, data depth and highest density regions. We compare the proposed outlier detection methods with the existing “functional depth” method, and show that our methods have better performance on identifying outliers in French male age-specific mortality data.

KW - Functional Data

KW - Outlier Detection

KW - Principal Component Score

KW - High Density Region

KW - Robust Principal Component Analysis

U2 - 10.1007/978-3-7908-2062-1_31

DO - 10.1007/978-3-7908-2062-1_31

M3 - Conference proceeding contribution

SN - 9783790820614

T3 - Contributions to statistics

SP - 201

EP - 207

BT - Functional and operatorial statistics

A2 - Dabo-Niang, Sophie

A2 - Ferraty, Frâedâeric

PB - Springer

CY - Heidelberg

T2 - International Workshop on Functional and Operatorial Statistics (1st : 2008)

Y2 - 19 June 2008 through 21 June 2008

ER -

Bagplots, boxplots, and outlier detection for functional data

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this