info vis test 1

Simpson's Paradox

A: A trend that appears in groups of data but disappears or reverses when the groups are combined.

Purposes of information visualization

A: Analysis (exploration) and Presentation (communication).

key components of visualization?

A: Representation (visual encoding) and Interaction (user control/exploration).

nominal data

A: Categories with no inherent order (e.g., colors, names).

ordinal data

A: Ordered categories, but no fixed numeric scale (e.g., rankings).

interval data

A: Ordered, evenly spaced values without a true zero (e.g., °C temperature).

data marks

A: Points, lines, and areas used to represent data.

data channels

A: Visual variables (position, size, orientation, color).

Position

A: Which channel is most accurate for comparing values?.

Magnitude

A:What does size represent in visualization?

Angles/directions

A: What does orientation represent?

Hue for categories, intensity for magnitude

Q: How is color used in visualization?

figure/ground

A: Distinguishing objects from the background.

proximity

A: Items close together are perceived as a group.

similarity

A: Similar shapes/colors are perceived as related.

symmetry

A: Symmetric elements are grouped together.

closure

A: Incomplete shapes are perceived as whole.

common fate

A: Elements moving together are seen as grouped.

connectedness

A: Linked elements are perceived as related.

continuity

A: Lines/curves are perceived as continuous paths.

pre-attentive processing

A: Instant detection of features (color, orientation, size).

attentive processing

A: Requires focused effort (reading numbers, fine detail).

low-level visualization tasks

A: Retrieve Value, Filter, Find Extreme (others: Compute Value, Sort, Determine Range, Characterize Distribution, Find Anomalies, Cluster, Correlation).

Analyze, Search, Query.

Q: What are the higher-level task categories?

bivariate data

A: Data with two variables (e.g., scatterplots).

trivariate data

A: Data with three variables (e.g., 3D plots).

polyline plot

A: Visualizing many variables (parallel coordinates).

mosaic plot

A: Showing proportions in categorical data.

heat map

A: Color-coded matrix showing magnitude.

radar chart

A: Radial display for comparing multiple variables.

expressiveness principle

A: Show all and only the information in the data.

effectiveness principle

A: Use the most accurate channels for the task.

graphical integrity

A: Data should be represented truthfully.

lie factor formula

A: (Size of effect shown in graph) ÷ (Size of effect in data).

uncertainty visualized

A: Confidence intervals, error bars, probability distributions.

importance of accuracy in visualization

A: To ensure correct interpretation of the data.

usefulness of animation

A: Showing change over time (but can mislead if overused).

forms of narrative visualization.

A: Annotated chart, Infographic, Slideshow (others: Magazine Style, Film/Video, Data Comics, Flow Chart).

martini glass structure

A: Author-driven intro, then reader exploration.

interactive slideshow

A: Step-by-step presentation with some flexibility.

drill-down story

A: Starts broad, then allows deeper exploration.