Statistical Graphics and Visualization, Spring 2007

www.stat.cmu.edu/~vventura

Instructor: Valerie Ventura, Department of Statistics
Office: Baker Hall 229E
e-mail: vventura@stat.cmu.edu
Office Hours: Monday: 3:00-4:00pm or by appointment
http://www.stat.cmu.edu/~vventura

Teaching and lab Assistant: Erich Huang, Department of Statistics
Office: FMS 328A or FMS 320 (TA room)
e-mail: ephuang@stat.cmu.edu
Office hour: Tuesday, 3:00-4:00pm

Lectures: Monday and Wednesday, 12:30-1:20, BH255A
Computer labs: Friday, 12:30-1:20, BH140F

Overview

Graphs are powerful tools for representing and interpreting data. They can provide more information than statistical tests and are often more convincing. Graphs are often the quickest path to winning an argument and producing action. This course teaches the methods and principles which will allow you to realize the full potential of graphics. It also includes a subsidiary focus on the aesthetics and clarity of graphical presentation.

Course Objectives

In this course you will:

Learn how to critically interpret graphics appearing in the popular press, academic publications, and software packages.
Learn how to choose the right graph for the point you are trying to make or, if necessary, how to design a new kind of graph.
Create statistical graphics using the R software package.
Analyze data and answer statistical questions with graphs.
Develop an appreciation for graphical aesthetics and learn to critique graphical presentations.

Texts

William S. Cleveland (1993) Visualizing Data. Hobart Press.

Recommended Background Reading in Statistics and the Use of R

John Maindonald and John Braun (2003) Data Analysis and Graphics Using R. An Example-Based Approach. Cambridge University Press.

Statistical Graphics

Edward R. Tufte (2002) The Visual Display of Quantitative Information. 2nd Edition. Graphics Press.

Howard Wainer (2005) Graphical Discovery. A Trout in the Milk and Other Visual Adventures. Princeton University Press.

Schedule

The schedule is organized around data of increasing dimension: 1-D, 2-D, 3-D, and beyond.

univariate data
- histograms, dot strips, density estimates, boxplots, quantile-quantile plots
- pies, bars, dotcharts
- visual perception of magnitudes
bivariate data, time series
- scatterplots, curve fitting, line graphs
- visual perception of curves
- categorical data plots: mosaics and 2x2 table plots
three-dimensional data
- using perspective, glyphs, and colors
- surface plots vs. contour plots
- visual perception of color
maps
- map projections, map coloring, map smoothing
- animated maps
hyper-variate data
- dynamic graphics, fly-throughs
- interactive graphics, brushing
- projection and slicing

Format

The course is taught in lecture format on Monday and Wednesday and via hands-on practice on Fridays in a computer lab.
Lectures will contain the material needed to complete the homeworks and lab assignments. There are two texts; nonetheless, ATTENDANCE and participation in class are critical for learning.
There will be a weekly OFFICE HOUR where you can meet one-on-one with the instructor and a separate office hour for the teaching assistant.
In the computer labs, you will learn how to create statistical graphics, under supervision of the lab assistant. Computer labs are mandatory. Each Friday, a LAB ASSIGNMENT will be handed out at the beginning of the session which must be completed during the lab period.

You must get the attention of the lab assistant who will check your results and give you 50% credit for the lab.

Following the lab, you will have until midnight to submit a "polished" version of your answers electronically to the Lab Assistant. This version should include sentences providing the interpretation of the results. The remaining 50% of the lab grade will be awarded for this electronically submitted set of answers.
Computer labs will use a free software package called R, which is similar to S-plus. Unlike Data Desk or Minitab, R is a full-fledged programming language, and you can use it to perform what is, for all practical purposes, an unlimited set of operations. You can download personal versions of R for Windows, Linux or Mac OS10 operating systems.

HOMEWORK will be assigned weekly and coordinated with the lectures and labs. The purpose of these assignments is to improve your understanding of the methods and their results. The Review Quiz from Lecture 1 will count as a homework assignment.
The homework will generally be due Tuesdays by midnight.
Homework will involve answering questions related to the lectures and creating graphics similar to what you practiced in lab. It will be posted on the web and can be handed in or emailed to us. Reading and homework should take about six hours per week.
There will be two MIDSEMESTER EXAMINATIONS:

The first will be in-class on Monday February 19.
The second will be a lab exam on Friday April 27.

The FINAL PROJECT for the course will be due during the final exam period.

Grading

Your final grade will be based on:

Homework: 25%
Labs: 25%
Midsemester Exams 20%
Final project: 30%

Each homework assignment will be worth 100 points. These points will be divided approximately equally among each of the parts of the assignment. The Review Quiz will count as a single homework assignment.

The lowest homework grade will be dropped except if it is the last assignment of the semester which is mandatory. The remaining homework grades will be used to compute the homework grade. The same procedure will be used for computer lab grades.

Extensions:

The standard extensions (medical, university event, or religious holiday) must be accompanied by an official form as described in the student handbook.

All work and computer code must be your own. Sharing code or answers will result in zero credit and a letter to your dean. See the CMU Student Handbook on Cheating and Plagiarism.