Lecture 1: Beautiful graphics in R

Slides:



Advertisements
Similar presentations
1 Eric Rasmusen, Eric Rasmusen, 7 November 2006 Graphs and Tables.
Advertisements

1 G492 Eric Rasmusen, 14 September 2009 Graphs.
ENV Envisioning Information Lecture 8 – Good Design – What we can learn from Tufte Ken Brodlie
Lecture 06: Design II February 5, 2013 COMP Visualization.
Theory of Data Graphics Part 1 Most of a graphic’s ink should vary in response to data variation (see chapters 4-6)
Lecture 5 advanced multipanel plots Trevor A. Branch Beautiful graphics in R, FISH554 SAFS, University of Washington.
Lecture 8: tables, text annotations, mathematical expressions, legends, custom axes Trevor A. Branch Beautiful graphics in R, FISH507H SAFS,
The visual display of quantitative data Joyce Chapman, Consultant for Communications & Data Analysis State Library of North Carolina,
Introduction to Data Analytics
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc. 3.1 Chapter Three Art and Science of Graphical Presentations.
Source: Tufte E. (2001) The Visual Display of Quantitiative Information. 2 nd Ed. Cheshire: Graphics Press Originally published in American Education,
Mathematics for all: sense and nonsense of statistical representations Heleen Verhage, Freudenthal Institute PME25 Summer Institute, July 2001.
Graphical Data Displays and Interpretation 2009 October 9.
Graphing With Excel 2010 University of Michigan – Dearborn Science Learning Center Based on a presentation by James Golen Revised by Annette Sieg…
Graphical Data Displays and Interpretation Wednesday, October 9.
Scientific Communication and Technological Failure presentation for ILTM, July 9, 1998 Dan Little.
Visualization and Data Mining. 2 Outline  Graphical excellence and lie factor  Representing data in 1,2, and 3-D  Representing data in 4+ dimensions.
Design World Graphical Integrity
Copyright © 2005 Brooks/Cole, a division of Thomson Learning, Inc. 3.1 Chapter Three Art and Science of Graphical Presentations.
2007 會計資訊系統計學 ( 一 ) 上課投影片 3.1 Chapter Three Art and Science of Graphical Presentations.
Data Visualization.
The Oral Presentation Kim E. Barrett, Ph.D. Professor of Medicine and Vice Chair for Research Department of Medicine University of California, San Diego,
1 Determining Effective Data Display with Charts.
Information Visualization in Data Mining S.T. Balke Department of Chemical Engineering and Applied Chemistry University of Toronto.
How to Produce Statistical Graphics General Clinical Research Center August 15, 2005 Rachel Enriquez.
Edward R. Tufte Copyright © 2006 Patrick McDermott UCB Extension Tufte, Edward R., Envisioning Information, Cheshire, Connecticut: Graphics.
Jeffrey Nichols Displaying Quantitative Information May 2, 2003 Slide 0 Displaying Quantitative Information An exploration of Edward R. Tufte’s The Visual.
Information Graphics Joyeeta Dutta-Moscato July 9, 2013.
Principles of Graphical Excellence Best Paper: ALAIR April 5–6, 2001 AIR: June 2-5, 2002, Toronto Focus-IR, February 21, 2003 Anna T. Waggener, Ph.D. Institutional.
Mark P. Baldwin Northwest Research Associates, USA Cargese UTLS Summer School, 6 Oct Data Graphics AndTypography.
Tabular Display of Data Prepared by: Gary Klass
Mark P. Baldwin Northwest Research Associates, USA Cargese UTLS Summer School, 6 Oct Data Graphics AndTypography.
CMPT 880/890 Writing labs. Outline Presenting quantitative data in visual form Tables, charts, maps, graphs, and diagrams Information visualization.
ACOT Intro/Copyright Succeeding in Business with Microsoft Excel 2010: Chapter1.
Graphical Display and Presentation of Quantitative Information 13 February 2006.
Gary Klass Department of Politics and Government Illinois State University.
Graphical Excellence CMSC 120: Visualizing Information 2/7/08 Lecture Part II.
Week 6. Turn in “Charting Prices” Partner Check “Figuring Commission” and “Buying Stock” Turn in your Commission Check to Ms. Drake with your explanation.
1 Eric Rasmusen, March 10, 2014 Graphs and Tables.
Department of Politics and Government Illinois State University
MIS2502: Data Analytics Principles of Data Visualization David Schuff
Bad Charts Matt Arnold. Moiré The Visual Display of Quantitative Information Edward R. Tufte.
COMMUNICATING DATA USING GRAPHICS MIS2502 Data Analytics.
Four types Data maps (17-19, Tufte, also History of the World in 100 Seconds)History of the World in 100 Seconds Time series Narrative graphics of space.
1 CSE 2337 Chapter 3 Data Visualization With Excel.
Worth 1,000 Words How to use information graphics to make data meaningful National Association for Career and Technical Education Information May 17, 2012.
CONFIDENTIAL Data Visualization Katelina Boykova 15 October 2015.
Graphing. Graphs Data must be shown in a way that allows others to understand your results easily and rapidly. There are many types of graphs. The type.
MIS2502: Data Analytics Principles of Data Visualization.
Recap Iterative and Combination of Data Visualization Unique Requirements of Project Avoid to take much Data Audience of Problem.
Data Visualization.
MIS5101: What is Analytics? Principles of Data Visualization.
Guidelines for Graphing Data Erin E. Barton. Rationale Visual inspection of graphed data is the primary means by which data analysis occurs in SCR Graphs.
Presenting Multivariate Data Harry R. Erwin, PhD School of Computing and Technology University of Sunderland.
LAB 01: BAR AND LINE CHARTS February 3, 2015 SDS 136 Communicating with Data.
Data Visualization.
Trevor A. Branch Beautiful graphics in R, FISH554
Lecture 4: overplotting and multipanel plots
Display of Quantitative Information
Lecture 5 advanced multipanel plots
MIS2502: Data Analytics Principles of Data Visualization
Data Visualization Data visualization principles. Tell a story
MIS2502: Data Analytics Principles of Data Visualization
CSc4730/6730 Scientific Visualization
Graphical Data Displays and Interpretation
Statistical power is….
Keller: Stats for Mgmt & Econ, 7th Ed
Statistical power is….
Keller: Stats for Mgmt & Econ, 7th Ed
Presentation transcript:

Lecture 1: Beautiful graphics in R Trevor A. Branch tbranch@uw.edu Beautiful graphics in R, FISH554 SAFS, University of Washington

Source: www.phdcomics.com 7 Dec 2012

Project and credit Project: four complex figures, three from your data, one redrawn from Porzio et al. (more details: class website https://canvas.uw.edu/courses/881902) For credit, electronic submission of draft figures (10 March), presentation of your best figure in class (online 16 March, in class 17 March), submission of final figures (21 March)

During class My aim is to ensure that all of you can produce beautiful, informative figures for your MS/PhD and scientific papers Listen to the lecture or read the handout or follow along with the PowerPoint on your computer or try out R code that I present What happens if I type this? Don’t just ask me, try it yourself!

Tufte: Principles of graphical excellence Well-designed presentation of interesting data Complex ideas communicated with clarity, precision, and efficiency Greatest number of ideas in shortest time with least ink in smallest space Nearly always multivariate Requires telling the truth about the data

Napoleon’s campaign to conquer Russia Original plot by Minard (1861) Tufte (2001) The visual display of quantitative information, p. 41

Tufte: better graphics Lie factor and exaggeration Chartjunk Maximize data:ink ratio Erase non-data ink Increase the data density Labels on the figures

Figure: New York Times, 9 August 1978, p. D-2 Tufte (2001) The visual display of quantitative information, p. 57-59

“Here there are many decorations, but no lies” Tufte (2001) The visual display of quantitative information, p. 59

1978 dollar should be 2 X Lie Factor 9.5… by volume 59.4 Principle: The number of information carrying dimensions depicted should not exceed the number of dimensions in the data 1978 dollar should be 2 X Lie Factor 9.5… by volume 59.4 Washington Post, October 25, 1978, p. 1 New York Times, January 27, 1981, p. D-1 Tufte (2001) The visual display of quantitative information, p. 70-71

Chartjunk and exaggeration “The Graph of the Magical Parallelipipeds” Inflation +103% Population +10% New York state expenditure: the Graph of Magic Parallelipeds: chartjunk inflation (103%) population growth (10%) distortion Tufte (2001) The visual display of quantitative information, p. 66

Tufte (2001) The visual display of quantitative information, p. 67

Principle: in time-series displays of money, deflated and standardized units of monetary measurement are nearly always better than nominal units. Tufte (2001) The visual display of quantitative information, p. 68

“In time-series displays of money, deflated and standardized units of monetary measurement are nearly always better than nominal units” Tufte (2001) The visual display of quantitative information, p. 68

The number of numbers plotted per cm2 (Tufte) Data density index The number of numbers plotted per cm2 (Tufte) DDI = 0.05 for Fig. 2 of Uzzi et al. (2013) High numbers are better Commonly ranges from 0.1 to >300 Calculation: Science pages are 8.25 X 10.5 inches. Figure takes up 25% of height and 60% of width, so 0.25*10.5*0.6*8.25 = 13 sq in = 13*2.5*2.5 = 81.25 square cm. DDI = 4/81.25 = 0.05 Figure: Uzzi et al. (2013) Atypical combinations and scientific impact. Science 342:468-472 Tufte ER (2001) The visual display of quantitative information

Maximize the data-ink ratio, within reason Erase non-data-ink, within reason Erase redundant data-ink, within reason Tufte (2001) The visual display of quantitative information, p. 93-95

Kooi (1971) Fundamentals of electroencephalography, New York, p. 110 Tufte (2001) The visual display of quantitative information, p. 93

Kelley & Bowen (1967) American Political Science Review, 61:371 Tufte (2001) The visual display of quantitative information, p. 94-95

Pauling (1947) General chemistry, San Francisco, p. 64 Data-ink ratio: < 0.6 Data-ink ratio: 0.9 Pauling (1947) General chemistry, San Francisco, p. 64 Tufte (2001) The visual display of quantitative information, p. 102-105

Tufte (2001) The visual display of quantitative information, p. 102-105

Label the figures, not the legends 1.2 2.2 1.3 2.3 CJFAS-mandated style Labels directly on subplots Lessard et al. (2008) CJFAS 65:2269-2278

Principles of graphics design Above all else show the data Maximize the data-ink ratio Erase non-data-ink Erase redundant data-ink Revise and edit Tufte (2001) The visual display of quantitative information, p. 105

Tufte (2001) The visual display of quantitative information, p. 102 Barplots 1 Kuznicki & McCutcheon (1979) Journal of Experimental Psychology: General, 108:76 Tufte (2001) The visual display of quantitative information, p. 102

Barplots 2 Tufte (2001) The visual display of quantitative information, p. 126-128

Erase the box Tufte (2001) The visual display of quantitative information, p. 126-128

Leave only the tick marks Tufte (2001) The visual display of quantitative information, p. 126-128

Erase some data to make a white grid Tufte (2001) The visual display of quantitative information, p. 126-128

Parallel boxplots Tufte (2001) The visual display of quantitative information, p. 125

Parallel boxplots “Original has 50 horizontals and 30 vertical lines, revised needs only 10 verticals to show the same data” Original has 50 horizontals and 30 vertical lines, revised needs only 10 verticals to show the same data. Relevant on informal, exploratory data analysis, where the research workers time should be devoted to matters other than drawing lines. Tufte (2001) The visual display of quantitative information, p. 125

Scatterplots Tufte (2001) The visual display of quantitative information, p. 130-133

Scatterplots Axes double as quartile plots for displaying marginals of the plot (p.132). Tufte (2001) The visual display of quantitative information, p. 130-133

Scatterplots Tufte (2001) The visual display of quantitative information, p. 130-133

Turn axes into quartiles Axes double as quartile plots for displaying marginals of the plot (p.132). Tufte (2001) The visual display of quantitative information, p. 133

Age distribution of the population of France Rather use tint shades of gray, or encode with labels on the graphic. Tufte (2001) The visual display of quantitative information, p. 113

How do people cite Worm et al. (2006)? P-value Sample size Draft figure: Branch TA Analysis of Worm et al. (2006) Science 314:787-790