Abstract

We introduce an approach to visual analysis of multivariate data that integrates several methods from information visualization, exploratory data analysis (EDA), and geovisualization. The approach leverages the component-based architecture implemented in GeoVISTA Studio to construct a flexible, multiview, tightly (but generically) coordinated, EDA toolkit. This toolkit builds upon traditional ideas behind both small multiples and scatterplot matrices in three fundamental ways. First, we develop a general, MultiForm, Bivariate Matrix and a complementary MultiForm, Bivariate Small Multiple plot in which different bivariate representation forms can be used in combination. We demonstrate the flexibility of this approach with matrices and small multiples that depict multivariate data through combinations of: scatterplots, bivariate maps, and space-filling displays. Second, we apply a measure of conditional entropy to (a) identify variables from a high-dimensional data set that are likely to display interesting relationships and (b) generate a default order of these variables in the matrix or small multiple display. Third, we add conditioning, a kind of dynamic query/filtering in which supplementary (un-displayed) variables are used to constrain the view onto variables that are displayed. Conditioning allows the effects of one or more well understood variables to be removed from the analysis, making relationships among remaining variables easier to explore. We illustrate the individual and combined functionality enabled by this approach through application to analysis of cancer diagnosis and mortality data and their associated covariates and risk factors.

Original languageEnglish (US)
Title of host publicationIEEE Symposium on Information Visualization 2003, InfoVis 2003
Pages31-40
Number of pages10
DOIs
StatePublished - Dec 1 2003
Event9th Annual IEEE Symposium on Information Visualization, InfoVis 2003 - Seattle, WA, United States
Duration: Oct 19 2003Oct 21 2003

Publication series

NameProceedings - IEEE Symposium on Information Visualization, INFO VIS
ISSN (Print)1522-404X

Other

Other9th Annual IEEE Symposium on Information Visualization, InfoVis 2003
CountryUnited States
CitySeattle, WA
Period10/19/0310/21/03

Fingerprint

Display devices
Studios
Entropy
Visualization

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

MacEachren, A., Dai, X., Hardisty, F., Guo, D., & Lengerich, G. (2003). Exploring high-D spaces with Multiform matrices and small multiples. In IEEE Symposium on Information Visualization 2003, InfoVis 2003 (pp. 31-40). [1249006] (Proceedings - IEEE Symposium on Information Visualization, INFO VIS). https://doi.org/10.1109/INFVIS.2003.1249006
MacEachren, Alan ; Dai, Xiping ; Hardisty, Frank ; Guo, Diansheng ; Lengerich, Gene. / Exploring high-D spaces with Multiform matrices and small multiples. IEEE Symposium on Information Visualization 2003, InfoVis 2003. 2003. pp. 31-40 (Proceedings - IEEE Symposium on Information Visualization, INFO VIS).
@inproceedings{753f0fbcbb1f46d7a2fd5ed44515f436,
title = "Exploring high-D spaces with Multiform matrices and small multiples",
abstract = "We introduce an approach to visual analysis of multivariate data that integrates several methods from information visualization, exploratory data analysis (EDA), and geovisualization. The approach leverages the component-based architecture implemented in GeoVISTA Studio to construct a flexible, multiview, tightly (but generically) coordinated, EDA toolkit. This toolkit builds upon traditional ideas behind both small multiples and scatterplot matrices in three fundamental ways. First, we develop a general, MultiForm, Bivariate Matrix and a complementary MultiForm, Bivariate Small Multiple plot in which different bivariate representation forms can be used in combination. We demonstrate the flexibility of this approach with matrices and small multiples that depict multivariate data through combinations of: scatterplots, bivariate maps, and space-filling displays. Second, we apply a measure of conditional entropy to (a) identify variables from a high-dimensional data set that are likely to display interesting relationships and (b) generate a default order of these variables in the matrix or small multiple display. Third, we add conditioning, a kind of dynamic query/filtering in which supplementary (un-displayed) variables are used to constrain the view onto variables that are displayed. Conditioning allows the effects of one or more well understood variables to be removed from the analysis, making relationships among remaining variables easier to explore. We illustrate the individual and combined functionality enabled by this approach through application to analysis of cancer diagnosis and mortality data and their associated covariates and risk factors.",
author = "Alan MacEachren and Xiping Dai and Frank Hardisty and Diansheng Guo and Gene Lengerich",
year = "2003",
month = "12",
day = "1",
doi = "10.1109/INFVIS.2003.1249006",
language = "English (US)",
isbn = "0780381548",
series = "Proceedings - IEEE Symposium on Information Visualization, INFO VIS",
pages = "31--40",
booktitle = "IEEE Symposium on Information Visualization 2003, InfoVis 2003",

}

MacEachren, A, Dai, X, Hardisty, F, Guo, D & Lengerich, G 2003, Exploring high-D spaces with Multiform matrices and small multiples. in IEEE Symposium on Information Visualization 2003, InfoVis 2003., 1249006, Proceedings - IEEE Symposium on Information Visualization, INFO VIS, pp. 31-40, 9th Annual IEEE Symposium on Information Visualization, InfoVis 2003, Seattle, WA, United States, 10/19/03. https://doi.org/10.1109/INFVIS.2003.1249006

Exploring high-D spaces with Multiform matrices and small multiples. / MacEachren, Alan; Dai, Xiping; Hardisty, Frank; Guo, Diansheng; Lengerich, Gene.

IEEE Symposium on Information Visualization 2003, InfoVis 2003. 2003. p. 31-40 1249006 (Proceedings - IEEE Symposium on Information Visualization, INFO VIS).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Exploring high-D spaces with Multiform matrices and small multiples

AU - MacEachren, Alan

AU - Dai, Xiping

AU - Hardisty, Frank

AU - Guo, Diansheng

AU - Lengerich, Gene

PY - 2003/12/1

Y1 - 2003/12/1

N2 - We introduce an approach to visual analysis of multivariate data that integrates several methods from information visualization, exploratory data analysis (EDA), and geovisualization. The approach leverages the component-based architecture implemented in GeoVISTA Studio to construct a flexible, multiview, tightly (but generically) coordinated, EDA toolkit. This toolkit builds upon traditional ideas behind both small multiples and scatterplot matrices in three fundamental ways. First, we develop a general, MultiForm, Bivariate Matrix and a complementary MultiForm, Bivariate Small Multiple plot in which different bivariate representation forms can be used in combination. We demonstrate the flexibility of this approach with matrices and small multiples that depict multivariate data through combinations of: scatterplots, bivariate maps, and space-filling displays. Second, we apply a measure of conditional entropy to (a) identify variables from a high-dimensional data set that are likely to display interesting relationships and (b) generate a default order of these variables in the matrix or small multiple display. Third, we add conditioning, a kind of dynamic query/filtering in which supplementary (un-displayed) variables are used to constrain the view onto variables that are displayed. Conditioning allows the effects of one or more well understood variables to be removed from the analysis, making relationships among remaining variables easier to explore. We illustrate the individual and combined functionality enabled by this approach through application to analysis of cancer diagnosis and mortality data and their associated covariates and risk factors.

AB - We introduce an approach to visual analysis of multivariate data that integrates several methods from information visualization, exploratory data analysis (EDA), and geovisualization. The approach leverages the component-based architecture implemented in GeoVISTA Studio to construct a flexible, multiview, tightly (but generically) coordinated, EDA toolkit. This toolkit builds upon traditional ideas behind both small multiples and scatterplot matrices in three fundamental ways. First, we develop a general, MultiForm, Bivariate Matrix and a complementary MultiForm, Bivariate Small Multiple plot in which different bivariate representation forms can be used in combination. We demonstrate the flexibility of this approach with matrices and small multiples that depict multivariate data through combinations of: scatterplots, bivariate maps, and space-filling displays. Second, we apply a measure of conditional entropy to (a) identify variables from a high-dimensional data set that are likely to display interesting relationships and (b) generate a default order of these variables in the matrix or small multiple display. Third, we add conditioning, a kind of dynamic query/filtering in which supplementary (un-displayed) variables are used to constrain the view onto variables that are displayed. Conditioning allows the effects of one or more well understood variables to be removed from the analysis, making relationships among remaining variables easier to explore. We illustrate the individual and combined functionality enabled by this approach through application to analysis of cancer diagnosis and mortality data and their associated covariates and risk factors.

UR - http://www.scopus.com/inward/record.url?scp=78649532416&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649532416&partnerID=8YFLogxK

U2 - 10.1109/INFVIS.2003.1249006

DO - 10.1109/INFVIS.2003.1249006

M3 - Conference contribution

C2 - 21947129

AN - SCOPUS:78649532416

SN - 0780381548

SN - 9780780381544

T3 - Proceedings - IEEE Symposium on Information Visualization, INFO VIS

SP - 31

EP - 40

BT - IEEE Symposium on Information Visualization 2003, InfoVis 2003

ER -

MacEachren A, Dai X, Hardisty F, Guo D, Lengerich G. Exploring high-D spaces with Multiform matrices and small multiples. In IEEE Symposium on Information Visualization 2003, InfoVis 2003. 2003. p. 31-40. 1249006. (Proceedings - IEEE Symposium on Information Visualization, INFO VIS). https://doi.org/10.1109/INFVIS.2003.1249006