Toggle navigation
Intro Data Viz
Students
Mark Boyer
Jennifer Chaussee
Andy Mannix
Juan Martinez
Jake Nicol
Jason Paladino
Joaquin Palomino
Christopher Schodt
Xavier Malina
Shubham Goel
Class notes
What is data?
Data visualization: basic principles
Interviewing data: exploratory graphical analysis
Interviewing data: using databases
Acquiring, cleaning and formatting data
Making static graphics
Polishing static graphics
Principles of mapping
Making static maps and processing geodata
Making interactive maps
Visualizing networks
Coding interactive graphics
Software
Data
Email instructor
Name
Email
1. Identify the categorical variables from this list: a) day of the week; b) height (metres); c) identifies as conservative or liberal; d) speed (mph); e) weight (lbs); f) speed (high, medium, low).
2. List five possible aggregate measures for a continuous variable, with a one-sentence explanation of each.
3. Explain what is meant by a negative correlation.
4. You suspect that children who get less sleep per night score worse on math tests because they are tired. When drawing a scatter plot of the data, what variable would you put on the Y axis, and why?
5. Under what circumstance might you draw a chart using a logarithmic scale for one axis?
6. List these visual cues in order of the accuracy with which values from the encoded data can be perceived, from most to least accurate: a) area; b) position (on an aligned scale); c) color/hue; d) length (not aligned).
7. You need to plot the split between the Republican and Democratic vote for every presidential election since 1980. What type of chart would you choose? Explain your choice.
8. You are encoding a continuous variable by the area of circles. If a value of 10 is represented by a circle of 4 pixels radius, what is the radius in pixels of a circle corresponding to a value of 40?
9. You need to represent two categorical variables using color. If you pick yellow for one variable, what would be a good choice for the second? Explain your choice.
10. What type of color scheme would you pick to represent percentage change in population by county between the 2000 and 2010 U.S. Census: sequential, diverging, or qualitative? Explain your choice.
Submit
(Your answers will also be sent to the email address you provided.)