Marti Hearst SIMS 247 SIMS 247 Lecture 5 Brushing and Linking February 3, 1998.

Slides:



Advertisements
Similar presentations
Obligatory cuteness. Guidelines for Using Multiple Views in Information Visualization ● A guideline paper – does not introduce any new techniques, but.
Advertisements

Interaction in Visualization Systems CPSC 533C Presentation Zhangbo Liu (Zephyr) December 7, 2005.
Design of Experiments Lecture I
Math CAMPPP 2011 Plenary 1 What’s the Focus? An Introduction to Algebraic Reasoning Ruth Beatty and Cathy Bruce 1.
DR. MOHD. RUMZI TAUSIF ASST. PROF. (MKT) SBS Unit 1 Nature and Scope of Marketing Research.
Chapter 4 Design Approaches and Methods
© Tan,Steinbach, Kumar Introduction to Data Mining 8/05/ Data Mining: Exploring Data Lecture Notes for Chapter 3 Introduction to Data Mining by Tan,
MTP – Stage 1 Sanobar Nishat. Outline  Peculiarities of the mobile visualization context  Different aspects of mobile visualization design  Map-based.
Visual Analytics Research at WPI Dr. Matthew Ward and Dr. Elke Rundensteiner Computer Science Department.
Interaction Week 10 CPSC 533C, Spring Feb 2004 Tamara Munzner.
Interaction Lecture 11 CPSC 533C, Fall Oct 2004 Tamara Munzner.
SIMS 247 Information Visualization and Presentation Prof. Marti Hearst August 31, 2000.
SIMS 247 Information Visualization and Presentation Prof. Marti Hearst September 14, 2000.
1 SIMS 247: Information Visualization and Presentation Marti Hearst Sept 21, 2005.
1 i247: Information Visualization and Presentation Marti Hearst Multidimensional Graphing.
Knowledge Acquisitioning. Definition The transfer and transformation of potential problem solving expertise from some knowledge source to a program.
Marti Hearst SIMS 247 SIMS 247 Lecture 4 Graphing Multivariate Information January 29, 1998.
1 i247: Information Visualization and Presentation Marti Hearst Interactive Multidimensional Visualization.
Marti Hearst SIMS 247 SIMS 247 Lecture 3 Graphing Basics, Continued January 27, 1998.
Project Life Cycle Jon Ivins DMU. Introduction n Projects consist of many separate components n Constraints include: time, costs, staff, equipment n Assets.
SIMS 247 Information Visualization and Presentation Marti Hearst February 15, 2002.
Lecture 11: Interaction Information Visualization CPSC 533C, Fall 2006 Tamara Munzner UBC Computer Science 17 Oct 2006.
Selective Dynamic Manipulation of Visualizations Chuah, Roth, Mattis, Kolojejchick.
Project Update: Law Enforcement Resource Allocation (LERA) Visualization System Michael Welsman-Dinelle April Webster.
Marti Hearst SIMS 247 SIMS 247 Lecture 6 Linked Interaction as Query Specification February 5, 1998.
1 i247: Information Visualization and Presentation Marti Hearst Graphing and Basic Statistics.
Multidimensional Data Analysis IS 247 Information Visualization and Presentation 22 February 2002 James Reffell Moryma Aydelott Jean-Anne Fitzpatrick.
1 A Rank-by-Feature Framework for Interactive Exploration of Multidimensional Data Jinwook Seo, Ben Shneiderman University of Maryland Hyun Young Song.
AMOS TAKING YOUR RESEARCH TO THE NEXT LEVEL Mara Timofe Research Intern.
Science and Engineering Practices
©2007 Prentice Hall Organizational Behavior: An Introduction to Your Life in Organizations Chapter 19 OB is for Life.
Info Vis: Multi-Dimensional Data Chris North cs3724: HCI.
WPI Center for Research in Exploratory Data and Information Analysis From Data to Knowledge: Exploring Industrial, Scientific, and Commercial Databases.
Visualization By: Simon Luangsisombath. Canonical Visualization  Architectural modeling notations are ways to organize information  Canonical notation.
LÊ QU Ố C HUY ID: QLU OUTLINE  What is data mining ?  Major issues in data mining 2.
Kening Wang, Charles Stegman, Sean W. Mulvenon, and Yanling Xia University of Arkansas, Fayetteville, AR, Using Kriging and Interactive Graphics.
1 Visual Analysis of Large Heterogeneous Social Networks by Semantic and Structural Abstraction Zequian shen, Kwan-Liu Ma, Tina Eliassi-Rad Department.
Unit 2: Engineering Design Process
Research Terminology for The Social Sciences.  Data is a collection of observations  Observations have associated attributes  These attributes are.
Graphical Analysis. Why Graph Data? Graphical methods Require very little training Easy to use Massive amounts of data can be presented more readily Can.
© 2010 Pearson Addison-Wesley. All rights reserved. Addison Wesley is an imprint of Designing the User Interface: Strategies for Effective Human-Computer.
Data Exploration Chapter 9. Introduction  Where to begin?  Data exploration is data-centered query and analysis  Better understand the data and provide.
Crowdsourcing for R&D InnoCentive Case
Copyright © Cengage Learning. All rights reserved. 2 Organizing Data.
Visual Perspectives iPLANT Visual Analytics Workshop November 5-6, 2009 ;lk Visual Analytics Bernice Rogowitz Greg Abram.
The Evolution of ICT-Based Learning Environments: Which Perspectives for School of the Future? Reporter: Lee Chun-Yi Advisor: Chen Ming-Puu Bottino, R.
LECTURE 1 - SCOPE, OBJECTIVES AND METHODS OF DISCIPLINE "ECONOMETRICS"
© 2009 IBM Corporation 1 Space, Time, and Antony Space, Time and Antony Visualizing Then and Now, Here and There.
‘Externalizing Abstract Mathematical Models’ Lisa Tweedie,Robert Spence, Huw Dawkes and Hua Su Department of Electrical Engineering, Imperial College Of.
Data Mining BY JEMINI ISLAM. Data Mining Outline: What is data mining? Why use data mining? How does data mining work The process of data mining Tools.
Tight Coupling of Dynamic Query Filters with Starfield Displays / Spotfire.net Desktop By Chris Ahlberg and Ben Shneiderman / Spotfire Inc. IC280 5/9/02.
Towards a Reference Quality Model for Digital Libraries Maristella Agosti Nicola Ferro Edward A. Fox Marcos André Gonçalves Bárbara Lagoeiro Moreira.
Visage: An All-in-One Tool A Paper by Roth, Lucas, Senn, et al. Presented by Josh Steele.
Lucent Technologies - Proprietary 1 Interactive Pattern Discovery with Mirage Mirage uses exploratory visualization, intuitive graphical operations to.
User Interface Evaluation Introduction Lecture #15.
Introduction Exploring Categorical Variables Exploring Numerical Variables Exploring Categorical/Numerical Variables Selecting Interesting Subsets of Data.
CHAPTER 10 DATA EXPLORATION 10.1 Data Exploration Box 10.1 Data Visualization Descriptive Statistics Box 10.2 Descriptive Statistics Graphs.
Information Visualization: Principles, Promise, and Pragmatics Marti Hearst CHI 2003 Tutorial  
SIMS 247 Lecture 7 Simultaneous Multiple Views
CS201 Lecture 02 Computer Vision: Image Formation and Basic Techniques
Jianping Fan Dept of CS UNC-Charlotte
Module 2: Demand Forecasting 2.
Interaction Week 7 CPSC 533C, Spring 2003
CSc4730/6730 Scientific Visualization
CSc4730/6730 Scientific Visualization
SAS/INSIGHT Demonstration - Exploratory Data Analysis (EDA) techniques
Statistical Data Analysis
CHAPTER 7: Information Visualization
Lecture 1: Descriptive Statistics and Exploratory
Online health and community indicator platforms
Presentation transcript:

Marti Hearst SIMS 247 SIMS 247 Lecture 5 Brushing and Linking February 3, 1998

Marti Hearst SIMS 247 Today Interactive techniquesInteractive techniques –Highlighting –Brushing and Linking Example systemsExample systems –Graham Will’s system –Tweedie’s Influence Explorer –Ahlberg & Sheiderman’s IVEE (Spotfire) –Roth et al.’s VISAGE

Marti Hearst SIMS 247 Review: Why Use Visualizations? PersuadePersuade (Lott rebuttal to State of Union speech) ExplainExplain (Organizational chart, life cycle of worm) ExploreExplore (Inselberg chip detective story) AnalyzeAnalyze (Challenger accident) (Entertain,(Entertain, Amuse)

Marti Hearst SIMS 247 Some Roles of Visualization in Exploring Large Data Sets (Wills 95) Data validationData validation Outlier detectionOutlier detection Suggestion and evaluation of modelsSuggestion and evaluation of models Discovery of relationships among subsets of dataDiscovery of relationships among subsets of data

Marti Hearst SIMS 247 Interactive Techniques Ask what-if questions spontaneously while working through a problemAsk what-if questions spontaneously while working through a problem Control the exploration of subsets of data from different viewpointsControl the exploration of subsets of data from different viewpoints

Marti Hearst SIMS 247 Highlighting (Focusing) Focus user attention on a subset of the data within one graph (from Wills 95)

Marti Hearst SIMS 247 Highlighting: selection within one graph (from Schall 95)

Marti Hearst SIMS 247 Brushing An interactive techniqueAn interactive technique –select a subset of points –see the role played by this subset of points in one or more other views At least two things must be linked together to allow for brushingAt least two things must be linked together to allow for brushing

Marti Hearst SIMS 247 Link similar types of graphs: Brushing a Scatterplot Matrix (Figure from Tweedie et al. 96; See also Cleveland & McGill 84, 88)

Marti Hearst SIMS 247 Link different types of graphs: Scatterplots and histograms and bars (from Wills 95)

Marti Hearst SIMS 247 Baseball data: Scatterplots and histograms and bars (from Wills 95) select high salaries avg career HRs vs avg career hits (batting ability) avg assists vs avg putouts (fielding ability) how long in majors distribution of positions played

Marti Hearst SIMS 247 What was learned from interaction with this baseball data? –Seems impossible to earn a high salary in the first three years –High salaried players have a bimodal distribution (peaking around 7 & 13 yrs) –Hits/Year a better indicator of salary than HR/Year –High paid outlier with low HR and medium hits/year. Reason: person is player-coach –There seem to be two differentiated groups in the put-outs/assists category (but not correlated with salary) Why?

Marti Hearst SIMS 247 Linking types of assist behavior to position played (from Wills 95)

Marti Hearst SIMS 247 Animating brushing on fielding information (Look at Lucent’s EDV )

Marti Hearst SIMS 247 Influence Explorer (Tweedie et al. 96) Manufacturing light bulbsManufacturing light bulbs A set of equations relateA set of equations relate –parameters (values chosen by designer) to –performance Goal: find parameter values for a desired kind of performanceGoal: find parameter values for a desired kind of performance –Example: How to build a very bright bulb that lasts for 6 months?

Marti Hearst SIMS 247 Traditional Design Process Can go from parameters -> performanceCan go from parameters -> performance Can’t do the reverse!Can’t do the reverse! Standard solution:Standard solution: –guess some parameters –compute results –adjust parameters –iterate until get close to desired performance Time-consuming and tedious!Time-consuming and tedious!

Marti Hearst SIMS 247 Using a Model Choose a region in parameter space that covers a large number of pointsChoose a region in parameter space that covers a large number of points Compute the resulting design space for all these pointsCompute the resulting design space for all these points

Marti Hearst SIMS 247 Another difficulty Cannot design for only one point in the performance spaceCannot design for only one point in the performance space –Manufacturing process is variable –Must define a tolerance region region of acceptibility: the desired performance space yield is the intersection is where the usable bulbs will end up

Marti Hearst SIMS 247 Influence Explorer Goals:Goals: –Large yields –Low cost (from wider tolerances) Approach:Approach: –Introduce complexity in stages –Give designer a qualitative understanding –Interactivity allows designer to quickly explore tradeoffs among settings

Marti Hearst SIMS 247 An Innovation! Show how many items fail by one, two, or three performance criteria (Tweedie et al. 96)

Marti Hearst SIMS 247 Also restrict the range of parameter settings. How many constraints away from success? (Tweedie et al. 96) Coding seems complex initially, but suits the designers’ needs and is easily learned.

Marti Hearst SIMS 247 Previous figure with re-coding

Marti Hearst SIMS 247 References for this Lecture Wills, Graham J. Visual Exploration of Large Structured Datasets, New Techniques and Trends in Statistics, IOS Press, Graham J. Visual Exploration of Large Structured Datasets, New Techniques and Trends in Statistics, IOS Press, Lucent’s EDV guide. EDV guide. Cleveland, W.S. and McGill, R. The Many Faces Of A Scatterplot. Journal of the American Statistical Association, 79, pp , 1984.Cleveland, W.S. and McGill, R. The Many Faces Of A Scatterplot. Journal of the American Statistical Association, 79, pp , Cleveland, W.S. and McGill, R., eds. Dynamic Graphics For Statistics. Wadsworth & Brooks, 1988.Cleveland, W.S. and McGill, R., eds. Dynamic Graphics For Statistics. Wadsworth & Brooks, Tweedie, Lisa, Spence, Robert, Dawkes, Huw, and Su, Hua. Externalising Abstract Mathematical Models. Proceedings of ACM SIGCHI, April Lisa, Spence, Robert, Dawkes, Huw, and Su, Hua. Externalising Abstract Mathematical Models. Proceedings of ACM SIGCHI, April Roth, Steven F., Chuah, Mei C., Kerpedjiev, Stephan, Kolojejchick, John, and Lucas, Peter. Towards an Information Visualization Workspace: Combining Multiple Means of Expression. Human-Computer Interaction Journal, 1997, in press.Roth, Steven F., Chuah, Mei C., Kerpedjiev, Stephan, Kolojejchick, John, and Lucas, Peter. Towards an Information Visualization Workspace: Combining Multiple Means of Expression. Human-Computer Interaction Journal, 1997, in press. Schall, Matthew. SPSS DIAMOND: a visual exploratory data analysis tool. Perspective, 18 (2), Matthew. SPSS DIAMOND: a visual exploratory data analysis tool. Perspective, 18 (2),