data science for all: a university-wide course in data literacy
TRANSCRIPT
DATA SCIENCE FOR ALL: A UNIVERSITY-WIDE COURSE IN DATA
LITERACY
David SchuffProfessor of Management Information Systems
Temple University, Philadelphia, [email protected] | @dschuff | community.mis.temple.edu/dschuff
ABOUT ME •Teaching
•data analytics, information
systems strategy, process design
•Research
• application of visualization to DSS,
data warehousing, impact of user-
generated content
•Led Temple Analytics Challenge,
University-wide data
visualization contest
OVERVIEW
• University-wide course in data literacy
• Designed for non-technical audience
• Pilot Fall 2014; 220 students in Spring 2016
• Discussion and exercise-based
• Exercises using Tableau, Excel, and Piktochart
• Work with real data sets
• The Environment
• Rationale
• Why Tableau?
• Course Learning Goals
• Content Overview
AGENDA
THE ENVIRONMENT:TEMPLE UNIVERSITY
• Large public urban University in North
Philadelphia
• 37,000+ students
• 17 schools and colleges, including:
liberal arts, business, education, law, media and
communication, music and dance, engineering
• 140 bachelor degree programs; 126 master’s
programs; 57 doctoral programs
RATIONALE: WHY A UNIVERSITY-WIDE COURSE?
• The data scientist has been declared the
“sexiest job of the 21st century.”
(Davenport and Patil, 2012)
• While most undergraduates won’t be
data scientists, they still need to be data
literate
• Infusing basic data literacy into the
curriculum is an opportunity to have
maximum impact on the workforce
WHY TABLEAU?
• Easy to learn for non-technical audience
• Strong on descriptive analytics
• Highly visual interface
• Skills also applicable to Microsoft Excel
• Attractive licensing for students
• Can use after the class is over
COURSE LEARNING GOALS
1. Describe how advances in
technology enable the field of data science.
2. Locate sources of data relevant to their
field of study.
3. Identify and correct problems with data
sets to facilitate analysis.
4. Combine data sets from different
sources.
5. Assess the quality of a data source.
6. Convey meaningful insights from a data
analysis through visualizations.
7. Analyze a data set using pivot tables.
8. Determine meaning in textual data using
text mining.
9. Identify when advanced analytics
techniques are appropriate.
10. Predict events that will occur together using association
mining.
MAPPING LEARNING GOALS TO KRATHWOHL’S (2002) DIMENSIONS
Knowledge
DimensionCount
Factual 2
Conceptual 5
Procedural 8
Cognitive Process
DimensionCount
Remember 2
Understand 2
Apply 5
Analyze 4
Evaluate 4
Create 2
Reflects how course incorporates skill
building and application.
MAPPING LEARNING GOALS TO KRATHWOHL’S (2002) TAXONOMY GRID
Remember Understand Apply Analyze Evaluate Create
Factual
Conceptual
Procedural
1
3 4
5,
86 67
2, 10
8
9
CONTENT OVERVIEW: FOUR MODULES
Module 1: Data in Our Daily
Lives
Module 2: Telling Stories With
Data
Module 3: Working With
Data in the Real World
Module 4: Analyzing Data
LEARNING GOALS BY MODULE
Temple University’s
GenEd Learning Goals
Module 1: Data
in Our Daily
Lives
Module 2:
Telling Stories
with Data
Module 3:
Working with
Data in the Real
World
Module 4:
Analyzing
Data
Information Literacy
Critical Thinking
Communications Skills
Retrieve, Organize, And Analyze Data
How Technology Encourages
Discovery
Technological Thinking for Everyday
Problems
THE CLASSROOM
The “Netbook Room”
• 68 basic laptops
• Windows OS
• Tableau, Excel, and
Chrome
• Wireless connectivity
• Allows for in-class
exercises during every
session
MODULE 1: DATA IN OUR DAILY LIVES
Theory and hypotheses
Content versus structure of data
Identifying sources of data and assessing credibility
Key Topics Sample Exercise:
Identifying Sources of Data
MODULE 2: TELLING STORIES WITH DATA
Communicating ideas through data
Principles of data visualization
Infographics
Key Topics Sample Exercise:
Mapping Food Atlas Data from the USDA
Mapping geographic data
Choosing the right chart type
Creating calculated fields
Teaching with Tableau
MODULE 2: TELLING STORIES WITH DATA
Sample Activity:
Visualizing Automobile
Fuel Economy(data from the EPA)
Average Fuel Economy
versus Engine
Displacement
CO2 Emissions versus
Engine Displacement
MODULE 3: WORKING WITH DATA IN THE REAL WORLD
Data quality
Data cleansing
Choosing practical measures (KPIs)
Key Topics Sample Exercise: Visualizing Air Travel KPIs (data from the Bureau of Transportation Statistics)
Creating KPI scorecards
Combining multiple datasets
Creating interactive dashboards
Teaching with Tableau
MODULE 3: WORKING WITH DATA IN THE REAL WORLD
Sample Exercise:
Creating Interactive
Dashboards
(data from the Pew
Research Project on
Excellence in Journalism)
MODULE 4: ANALYZING DATA
Big data versus data analytics
Sentiment analysis
Simple forecasting
Key Topics Sample Exercise:
Simple Predictive Analytics for Sales Data
Forecasting
Pivot Tables and Hierarchies
Visualizing word frequency
Teaching with Tableau
MODULE 4: ANALYZING DATA
Sample Exercise:
Analyzing the NCAA
2014 season
(data from Spreadsheet
Sports.com)
FINAL PROJECT: ORIGINAL DATA ANALYSIS
Does
education
really lead to
higher
income?
Where
should
Temple’s
Basketball
team take
their shots?
How do
world events
impact US
trade?
SUMMARY
• University-wide data literacy course
• Designed to scale
• For non-technical audience
• Emphasizes discussion and hands-on
work
• 21 original in-class exercises
• Seven Tableau; four Excel
QUESTIONS?
David SchuffProfessor of Management Information Systems
Temple University, Philadelphia, PA
[email protected] | @dschuff | community.mis.temple.edu/dschuff