Transforming scagnostics to reveal hidden features

Tuan Nhon Dang; Leland Wilkinson

doi:10.1109/TVCG.2014.2346572

Transforming scagnostics to reveal hidden features

Tuan Nhon Dang, Leland Wilkinson

Computer Science

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

30 Scopus citations

Abstract

Scagnostics (Scatterplot Diagnostics) were developed by Wilkinson et al. based on an idea of Paul and John Tukey, in order to discern meaningful patterns in large collections of scatterplots. The Tukeys' original idea was intended to overcome the impediments involved in examining large scatterplot matrices (multiplicity of plots and lack of detail). Wilkinson's implementation enabled for the first time scagnostics computations on many points as well as many plots. Unfortunately, scagnostics are sensitive to scale transformations. We illustrate the extent of this sensitivity and show how it is possible to pair statistical transformations with scagnostics to enable discovery of hidden structures in data that are not discernible in untransformed visualizations.

Original language	English
Article number	6875999
Pages (from-to)	1624-1632
Number of pages	9
Journal	IEEE Transactions on Visualization and Computer Graphics
Volume	20
Issue number	12
DOIs	https://doi.org/10.1109/TVCG.2014.2346572
State	Published - Dec 31 2014

Keywords

High-Dimensional Visual Analytics
Scagnostics
Scatterplot matrix
Transformation

Access to Document

10.1109/TVCG.2014.2346572

Cite this

@article{1e69c5edb3c64153ac7745c3d7fcf470,

title = "Transforming scagnostics to reveal hidden features",

abstract = "Scagnostics (Scatterplot Diagnostics) were developed by Wilkinson et al. based on an idea of Paul and John Tukey, in order to discern meaningful patterns in large collections of scatterplots. The Tukeys' original idea was intended to overcome the impediments involved in examining large scatterplot matrices (multiplicity of plots and lack of detail). Wilkinson's implementation enabled for the first time scagnostics computations on many points as well as many plots. Unfortunately, scagnostics are sensitive to scale transformations. We illustrate the extent of this sensitivity and show how it is possible to pair statistical transformations with scagnostics to enable discovery of hidden structures in data that are not discernible in untransformed visualizations.",

keywords = "High-Dimensional Visual Analytics, Scagnostics, Scatterplot matrix, Transformation",

author = "Dang, {Tuan Nhon} and Leland Wilkinson",

note = "Publisher Copyright: {\textcopyright} 1995-2012 IEEE.",

year = "2014",

month = dec,

day = "31",

doi = "10.1109/TVCG.2014.2346572",

language = "English",

volume = "20",

pages = "1624--1632",

journal = "IEEE Transactions on Visualization and Computer Graphics",

issn = "1077-2626",

number = "12",

}

TY - JOUR

T1 - Transforming scagnostics to reveal hidden features

AU - Dang, Tuan Nhon

AU - Wilkinson, Leland

PY - 2014/12/31

Y1 - 2014/12/31

N2 - Scagnostics (Scatterplot Diagnostics) were developed by Wilkinson et al. based on an idea of Paul and John Tukey, in order to discern meaningful patterns in large collections of scatterplots. The Tukeys' original idea was intended to overcome the impediments involved in examining large scatterplot matrices (multiplicity of plots and lack of detail). Wilkinson's implementation enabled for the first time scagnostics computations on many points as well as many plots. Unfortunately, scagnostics are sensitive to scale transformations. We illustrate the extent of this sensitivity and show how it is possible to pair statistical transformations with scagnostics to enable discovery of hidden structures in data that are not discernible in untransformed visualizations.

AB - Scagnostics (Scatterplot Diagnostics) were developed by Wilkinson et al. based on an idea of Paul and John Tukey, in order to discern meaningful patterns in large collections of scatterplots. The Tukeys' original idea was intended to overcome the impediments involved in examining large scatterplot matrices (multiplicity of plots and lack of detail). Wilkinson's implementation enabled for the first time scagnostics computations on many points as well as many plots. Unfortunately, scagnostics are sensitive to scale transformations. We illustrate the extent of this sensitivity and show how it is possible to pair statistical transformations with scagnostics to enable discovery of hidden structures in data that are not discernible in untransformed visualizations.

KW - High-Dimensional Visual Analytics

KW - Scagnostics

KW - Scatterplot matrix

KW - Transformation

UR - http://www.scopus.com/inward/record.url?scp=84910038184&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2014.2346572

DO - 10.1109/TVCG.2014.2346572

M3 - Article

AN - SCOPUS:84910038184

SN - 1077-2626

VL - 20

SP - 1624

EP - 1632

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

IS - 12

M1 - 6875999

ER -

Transforming scagnostics to reveal hidden features

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this