CS 235: User Interface Design November 26 Class Meeting Department of Computer Science San Jose State University Fall 2014 Instructor: Ron Mak mak.

CS 235: User Interface DesignNovember 26 Class Meeting

Department of Computer ScienceSan Jose State University

Fall 2014Instructor: Ron Mak

www.cs.sjsu.edu/~mak

http://www.cs.sjsu.edu/~mak

Computer Science Dept.Fall 2014: November 26

CS 235: User Interface Design© R. Mak

2

Online Course Evaluations

Evaluation period closes Wednesday, Dec. 10.

If you don’t fill out the online SOTES by Dec. 10, you will have a 3-week delay in the release of your grades.



3

Examples of Quantitative Relationships

Quantitative information Relationship

Units of a product sold per geographic region

Sales related to geography

Revenue by quarter Revenue related to time

Expenses by department and month Expenses related to organizational structure and time

A company’s market share compared to that of its competitors

Market share related to companies

The number of employees who received each of five possible performance ratings (1-5) during the last annual performance review

Employee counts related to performance ratings

Show Me the Numbers, 2nd ed.by Stephen FewAnalytics Press, 2012



4

Relationships within Categories

Nominal Ordinal Interval Hierarchical



5

Relationships within Categories: Nominal

Values in a category are discreteand have no intrinsic order.

Example:




6

Relationships within Categories: Ordinal

Categorical items have a prescribed order.

Meaningless to display them out of order. Except perhaps in reversed order.

Examples:

First, second, third, … Small, medium, large Best, second best, …



7

Relationships within Categories: Interval

Categorical items consist of a sequential series of numerical ranges that subdivide a larger range of quantitative values into smaller ranges.

Examples:




8

Relationships within Categories: Hierarchical

Multiple categories that are closely associated with each other as separate levels in a series of parent-child connections.

Example:




9

Relationships between Quantities

Ranking Ratio Correlation



10

Relationships between Quantities: Ranking

The order in which categorical items are displayed is based on associated quantitative values.

Example:




11

Relationships between Quantities: Ratio

A number that expresses the relative quantities of two values obtained by dividing one by the other.

The ratio of a part to the whole is generally expressed as a percentage.

Example:




12

Relationships between Quantities: Correlation

A comparison of two paired sets of quantitative values to determine whether increases in one value correspond to either increases or decreases in the other.

Allows us to predict the values of one variable by knowing or controlling the values of another.

Example: Number of years employees have been doing

particular jobs vs. productivity in those jobs. Does productivity increase or decrease with tenure?



13

Numbers that Summarize

Measures of average Mean Median

Measures of variation Spread Standard deviation

Measures of ratio

Measures of correlation Linear correlation coefficient



14

Measures of Average: Arithmetic Mean

Sum all the values and divide the sum by the number of values.

Treats every value equally, no matter now extreme.

Example:




15

Measures of Average: Arithmetic Mean, cont’d

The arithmetic mean can be a misleading summary of a set of numbers.

Example:




16

Measures of Average: Median

The middle value of a sorted set of values. Not sensitive to extreme values. Better at expressing what’s a typical value.

Example:




17

Measures of Variation: Spread

The difference between the lowest and the highest of a set of values.




18

Measures of Variation: Standard Deviation

Measures the variation in a set of values relative to the arithmetic mean.

Formulas:

For n items takenfrom the entire set.

For the entire setof n items.



19

Measures of Variation: Standard Deviation, cont’d

Percentage of values that fall within 1, 2, or 3 standard deviations from the mean in a normal distribution.

68%of the values

95%of the values

99.7%of the values




20

Ways to Express Measures of Ratio

Sentence Example: Two out of five customers …

Fraction Examples: ½ ⅔ ⅞

Rate Example: 0.4

Percentage Example: 45%



21

Types of Analyses

Time series Part-to-Whole and Ranking Deviation Distribution Correlation Multivariate

Ultimate goal: Provide insight for the user.



22

Correlation Analysis

Characteristics of correlation:

Direction Strength Shape



23

Linear Correlation Coefficient

All values are between -1 and +1. 0 = no correlation. +1 = perfect positive linear correlation -1 = perfect negative linear correlation The closer the value is to -1 or +1,

the stronger the linear correlation.



24

Linear Correlation Coefficient, cont’d




25





26





27

Logarithmic Correlation

Now You See Itby Stephen FewAnalytics Press, 2009



28

Exponential Correlation




29

Polynomial Correlation




30

Correlation Does Not Imply Causation!

A strong correlation between two variablesdoes not imply that one causes the other.

Further statistical tests are necessaryto calculate the likelihood of true causation.

See http://en.wikipedia.org/wiki/

Correlation_does_not_imply_causation

http://en.wikipedia.org/wiki/Correlation_does_not_imply_causation





31

Correlation Does Not Imply Causation! cont’d

See http://en.wikipedia.org/wiki/

Correlation_does_not_imply_causation

Invalid insight:Eating ice cream causes crime.(Actually, both are causedby warmer weather.)






32

Correlation Does Not Imply Causation! cont’d Highly correlated:

Infants sleeping with the lights on and the development of myopia (near sightedness).

Invalid insight:Sleeping with the lights on causes a child to become near-sighted.

True causation: Parents who are near-sighted have more lights on. Children inherit near-sightedness from their parents.



33

Beware of False Correlations!

See:

http://www.tylervigen.com

http://www.dailymail.co.uk/sciencetech/article-2640550/Does-sour-cream-cause-bike-accidents-No-looks-like-does-Graphs-reveal-statistics-produce-false-connections.html

http://www.buzzfeed.com/kjh2110/the-10-most-bizarre-correlations

http://www.tylervigen.com/












34

Multivariate Analysis

Compare multiple instances of several variables at once.

Identify similarities and differences among items that are each characterized by a common set of variables.

Which items are most alike? Which items are most exceptional? How can items be grouped based on similarity? What multivariate profile corresponds best to a

particular outcome?



35

Multivariate Displays

Glyphs Whiskers and stars Multivariate heatmaps Parallel coordinate plots



36

Multivariate Displays: Glyphs

Variable Visual attribute

Body temperature Color

Blood type Head shape

Body mass index Torso thickness

Heart rate Position of the arms

Blood sugar level Position of the legs




37

Multivariate Displays: Glyphs, cont’d

Chernoff faces

http://mathworld.wolfram.com/ChernoffFace.html





38

Multivariate Displays: Whiskers and Stars

Each line represents a different variable. The line length encodes the variable’s value.




39

Multivariate Displays: Heatmaps




40

Multivariate Displays: Parallel Plots




41

Multivariate Displays: Parallel Plots, cont’d

Look for patterns!


CS 235: User Interface Design November 26 Class Meeting Department of Computer Science San Jose State University Fall 2014 Instructor: Ron Mak mak.

Documents

user interface design

user interface designnovember

mak computer science

stephen fewanalytics

rankingthe order

prescribed order

intrinsic order

reversed order