Transcript Bachelor Data

Guidelines for Undergraduate
Programs in Statistics
Beth Chance – Cal Poly
([email protected])
Feedback can be sent to Rebecca Nichols,
ASA Director of Education
([email protected])
Background/Motivation
• More statistical content in lower grade levels
• Statistics enrollments are increasing
• Bachelor’s degrees (673 in 2003; 1656 in 2013)
• Increased need for graduates who can “think
with data”
• McKinsey report: Shortage of 140,000 to 190,000
million people with deep analytic skills… 1.5 million
managers (who can use data) to make effective
decisions
• Prior guidelines approved by ASA Board in 2000
NCES Digest of Education Statistics
1/8/2016
Joint Mathematics Meetings
2
Background
• Spring 2013 incoming ASA President Nat Schenker appointed a
working group with representatives from academia, industry, and
government to make recommendations
• Beth Chance (Cal Poly), Steve Cohen (NSF), Scott Grimshaw (BYU),
Johanna Hardin (Pomona), Tim Hesterberg (Google), Roger Hoerl
(Union), Nicholas Horton (Amherst, Chair), Chris Malone (Winona
State), Rebecca Nichols (ASA), and Deborah Nolan (Berkeley)
• New guidelines were endorsed by the Board of Directors of the
American Statistical Association on November 15, 2014.
1/8/2016
Joint Mathematics Meetings
3
The American Statistical Association endorses the value of
undergraduate programs in statistics as a reflection of the
increasing importance of the discipline. We expect statistics
programs to provide sufficient background in the following core
skill areas: statistical methods and theory, data management,
computation, mathematical foundations, and statistical practice.
Statistics programs should be flexible enough to prepare
bachelor's graduates to either be functioning statisticians or go
on to graduate school.
1/8/2016
Joint Mathematics Meetings
4
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
• Skills needed
• Curriculum topics (Bachelor’s Degree)
• Curriculum topics (Minors/Concentrations)
• Additional resources
1/8/2016
Joint Mathematics Meetings
5
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
•
•
•
•
Equip students with quantitative skills to use in flexible ways
Emphasize concepts and tools for working with data
Provide experience with design and analysis
Distinct from mathematics
• Skills needed
• Curriculum topics (Bachelor’s Degree)
• Curriculum topics (Minors/Concentrations)
• Additional resources
1/8/2016
Joint Mathematics Meetings
6
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
• Skills needed
• Curriculum topics (Bachelor’s Degree)
• Curriculum topics (Minors/Concentrations)
• Additional resources
1/8/2016
Joint Mathematics Meetings
o Statistical
o Mathematical
o Computational
o “Statistical practice”
o Substantive Area
7
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
• Skills needed
• Curriculum topics (Bachelor’s Degree)
• Content
• Pedagogy
• Curriculum topics (Minors/Concentrations)
• Additional resources
1/8/2016
Joint Mathematics Meetings
8
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
o Statistical topics
• Statistical theory
• Skills needed
• Exploratory and graphical data analysis methods
• Curriculum topics
• Statistical modeling (parametric and non(Bachelor’s Degrees)
parametric)
• Design of studies and issues of bias, causality, and
• Curriculum topics
confounding
(Minors/Concentrations)
• Additional resources
1/8/2016
Joint Mathematics Meetings
9
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
o Statistical topics
• Skills needed
o Mathematical topics, probability
• Calculus (integration and differentiation)
• Curriculum topics
through multivariable calculus
(Bachelor’s Degrees)
• Applied linear algebra
• Curriculum topics
• Probability
(Minors/Concentrations)
• Emphasis on connections between these
concepts and their applications in statistics
• Additional resources
• Why and How statistical methods work
• Communicate in language of mathematics
1/8/2016
Joint Mathematics Meetings
10
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
o Statistical topics
• Principles
o Mathematical topics, probability
• Skills needed
o Computational topics
• Curriculum topics
• Algorithmic thinking/problem solving
(Bachelor’s Degrees)
• Programming concepts and Higher-level
• Curriculum topics
languages
(Minors/Concentrations)
• Ability to access data in variety of ways
• Additional resources
• Database concepts and technology
• Computationally intensive methods
• Reproducibility
1/8/2016
Joint Mathematics Meetings
11
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
• Skills needed
• Curriculum topics
(Bachelor’s Degrees)
• Curriculum topics
(Minors/Concentrations)
• Additional resources
1/8/2016
o Statistical topics
o Mathematical topics, probability
o Computational topics
o “Statistical practice” topics
• Effective technical writing, presentations,
and visualizations with technical and
nontechnical audiences
• Ethical standards of practice
• Teamwork and collaboration
• Planning for data collection
• Data management
The undergraduate experience should include
an internship, "capstone" course, consulting
experience, or a combination
Joint Mathematics Meetings
12
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
• Skills needed
• Curriculum topics
(Bachelor’s Degrees)
• Curriculum topics
(Minors/Concentrations)
• Additional resources
1/8/2016
o Statistical topics
o Mathematical topics, probability
o Computational topics
o “Statistical practice” topics
o Pedagogy
• Emphasize real data and authentic applications
• Present data in a context that is both meaningful
to students and indicative of the science behind
the data
• Include experience with statistical computing
• Encourage synthesis of theory, methods, and
applications
• Offer frequent opportunities to develop
communication skills
Joint Mathematics Meetings
13
Key Skills
• Effective statisticians at any level display an integrated combination
of skills (statistical theory, application, data and computation,
mathematics, and communication)
• Students need scaffolded exposure to develop connections between
statistical concepts/theory and their application to statistical practice
• Need multiple opportunities to analyze messy data using modern
statistical practices
• Programs should provide their students with sufficient background in
each of these areas
1/8/2016
Joint Mathematics Meetings
14
Key Changes
• Increased importance of data-related skills
• Embrace a more comprehensive view of modeling
• Model building, explanatory models, predictive modeling, etc.
• Continue to enhance experiences that promote
unstructured learning and enhance teamwork
• Research, Capstones, Internships, REU, etc. (non textbook data)
• Continue to promote communication skills
• Multiple opportunities to practice
1/8/2016
Joint Mathematics Meetings
15
Key Points
“These guidelines are intended to be flexible while
ensuring that programs provide students with the
appropriate background along with necessary critical
thinking and problem-solving skills to thrive in our
increasingly data-centric world. Programs are
encouraged to be creative with their curriculum to
provide a synthesis of theory, methods, computation,
and applications.”
1/8/2016
Joint Mathematics Meetings
16
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
• Skills needed
• Curriculum topics
(Bachelor’s Degrees)
• Curriculum topics
(Minors/Concentrations)
• Additional resources
1/8/2016
• General statistical methodology
• Statistical modeling (e.g.,
multiple regression,
confounding, diagnostics)
• Facility with professional
statistical software, data
management skills
plus elective topics, capstone
and/or relevant courses from
other departments
Joint Mathematics Meetings
17
ASA Guidelines
http://www.amstat.org/education/curriculumguidelines.cfm
• Principles
• Skills needed
• Curriculum topics
(Bachelor’s Degrees)
• Curriculum topics
(Minors/Concentrations)
• Additional resources
1/8/2016
• Resource Material for
Minors/Concentrations
• White papers (Ethics,
Internships, Smaller Programs,
Learning Outcomes)
• November 2015 issue of The
American Statistician
• Webinar series
Joint Mathematics Meetings
18
Next Steps
• Faculty development
• Engagement with two year colleges
• Surveys of graduates and employers
• Certification/accreditation pathway
• Multiple pathways for introduction to statistics
• Periodic review
1/8/2016
Joint Mathematics Meetings
19
Example – Cal Poly curriculum proposals (2015)
• Orientation to the major
• History, Big Data, Ethics, Communication, Computing (R)
• Introductory sequence
• Simulation-based, integration of theory and applications, R Markdown
• Sophomore level communication course
• In addition to senior level communication and consulting course
• Regression modelling
• Predictive modelling (e.g., splines, classification trees)
• Linear models course
• More electives
• Survival analysis, Applied probability models, Multi-level data
• Launch of Interdisciplinary Minor in Data Science (with Computer Science)
1/8/2016
Joint Mathematics Meetings
20
Parting Questions
• What is the dividing line between a bachelor’s degree and a master’s
degree (2013)?
• What types of careers can BS students find?
• Can we improve student preparation for life after graduation?
• Creative solutions?
•
•
•
•
1/8/2016
Capstones
Substantive area
Big data
How develop “statistical practice” skills
Joint Mathematics Meetings
21
Recommendations Master’s Degree Programs
• Graduates should have a solid foundation in statistical theory and methods.
• Programming skills are critical and should be infused throughout the graduate student
experience.
• Communication skills are critical and should be developed and practiced throughout
graduate programs.
• Collaboration, teamwork, and leadership development should be part of graduate
education.
• Students should encounter non-routine, real problems throughout their graduate
education.
• Internships, co-ops, or other significant immersive work experiences should be
integrated into graduate education.
• Programs should be encouraged to periodically survey recent graduates and employers
of their recent graduates as a means of evaluating the success of their programs and to
examine if other programmatic changes are warranted.
1/8/2016
Joint Mathematics Meetings
22