1. USING ANALYTICS TO
IMPROVE STUDENT SUCCESS:
A PRIMER ON LEVERAGING
DATA TO ENHANCE STUDENT
PERFORMANCE
March 23, 2014 Matthew D. Pistilli, PhD
2. Plan for the day
Introductions and Purpose
Conceptual Overview
Other Institutions’ Analytics
Five Components of Analytics
Individual/Group Work & Planning
Managing Expectations in Next Steps
3. Who are we?
Where are we from?
Why are we here?
Introductions and Purpose
6. Definitions of Learning Analytics
The measurement, collection, analysis and reporting
of data about learners and their contexts, for
purposes of understanding and optimizing learning
and the environments in which it occurs (SoLAR)
Evaluating large data sets to provide decision
makers with information that can help determine the
best course of action for an organization, with a
specific goal of improving learning outcomes
(EDUCAUSE, 2011)
7. Definitions Continued
Using analytic techniques to help target
instructional, curricular, and support resources to
support the achievement of specific learning goals
(van Bareneveld, Arnold, & Campbell, 2012)
the process of developing actionable insights
through problem definition and the application of
statistical models and analysis against existing
and/or simulated future data (Cooper, 2012)
8. Definitions Continued
Using data to inform decision-making; leveraging
data to identify students in need of academic
support; and allowing direct user interaction with a
tool to engage in some form of sensemaking that
supports a subsequent action (Krumm, Washington,
Lonn, & Teasley)
The use of data, statistical analysis, and
explanatory and predictive models to gain insights
and act on complex issues (Bichsel, 2012)
15. Analytics is about…
Actionable intelligence
Moving research to practice
Basis for design, pedagogy, self-
awareness
Changing institutional culture
Understanding the limitations and
risks
17. Student Involvement Theory
Alexander Astin - UCLA
Involvement:
The amount of physical and psychological
energy that the student devotes to the
academic experience. (1985, p. 134)
Exists on a continuum, with students investing varying
levels of energy
Is both quantitative and qualitative
Direct relationship between student learning and
student involvement
Effectiveness of policy or practice directly related to
their capacity to increase student learning
(Astin, 1999)
19. Inputs
The personal, background, and
educational characteristics that students
bring with them to postsecondary
education that can influence educational
outcomes (Astin, 1984).
20. Inputs
Astin (1993) identified 146 characteristics, including
Demographics
Citizenship
Ethnicity
Residency
Sex
Socioeconomic status
High school academic achievement
Standardized test scores
GPA
Grades in specific courses
Previous experiences & self-perceptions
Reasons for attending college
Expectations
Perceived ability
21. Outcomes
Basic level
Academic Achievement
Retention
Graduation
More abstractly
Skills
Behaviors
Knowledge
The things we are
attempting to
develop in students
22. Environment
Where we have the most control
Factors related to students’ experience while in
college
Astin (1993) identified 192 variables across 8
overarching classifications
Institutional characteristics Financial Aid
Peer group characteristics Major Field Choice
Faculty characteristics Place of residence
Curriculum Student involvement
31. Five Components of Analytic Model
Gather
Predict
ActMonitor
Refine
Components
are cyclical
starting with
gather but
can be
drawn upon
at any point
in the cycle.
33. Gather
Data
In multiple formats
From multiple sources
With insights into students & their success
That can be analyzed & manipulated into formulae
Data is the foundation for this work, and without
good data, the effort may be for naught.
34. Gather
Before gathering, determine what will be gathered.
What question are you trying to answer?
To do so, consider…
Where will your focus be?
What data do you already have (or have access to)?
What else do you need to collect?
Who owns that data?
What will it take to get access to it?
What are the challenges associated with assembling all
the data?
What are the funding implications for data collection and
assembly?
35. Gather
Ultimately, answer the following questions:
1. How will you describe this analytics area to
interested parties?
2. Who are the key stakeholders that need to be
included in discussions?
3. Who should serve as the lead for this area at your
institution?
4. What other considerations are there?
37. Predict
Begins with the question asked in Gather:
What do you want to predict?
How do you identify this as a focus area?
Prediction models built will be driven by
Types of data gathered
Question being answered
What’s currently being predicted?
How?
By whom?
In what realms? Student success?
How can you involve those persons in this effort?
38. Predict
What makes a good model?
Correlation vs. Causation
Expertise required
Data analysis
Statistical
Content
Reliability & Validity
Frequency of updating
Challenges & obstacles
39. Predict
Ultimately, answer the following questions:
1. How will you describe this analytics area to
interested parties?
2. Who are the key stakeholders that need to be
included in discussions?
3. Who should serve as the lead for this area at your
institution?
4. What other considerations are there?
41. Act
Harken back to journalism class…
Who?
What?
Where?
When?
Why?
How?
Add:
Available resources?
Timing
42. Act
Frequency – more is always better
Funding the action
Assessing the impact
What are you assessing?
Were behaviors changed?
How do you know?
Do different actions need to be:
Taken (on your end)?
Suggested (on the students’ end)?
43. Act
Ultimately, answer the following questions:
1. How will you describe this analytics area to
interested parties?
2. Who are the key stakeholders that need to be
included in discussions?
3. Who should serve as the lead for this area at your
institution?
4. What other considerations are there?
45. Monitor
Formative & summative in nature
Can present challenges and obstacles
It’s a process
Current process must be understood
New/parallel processes developed as necessary
Involving others… to some extent, the more the
merrier
Availability of resource (time, money, people)
Timing of monitoring
Ability to react
46. Monitor
Review
Data collected and used… was it
Necessary?
Correct?
Sufficient?
Predictions made… were they
Accurate?
Meaningful?
Actions taken… were they
Useful?
Sustainable?
Feedback received to date
47. Monitor
Ultimately, answer the following questions:
1. How will you describe this analytics area to
interested parties?
2. Who are the key stakeholders that need to be
included in discussions?
3. Who should serve as the lead for this area at your
institution?
4. What other considerations are there?
49. Refine
Self-improvement process for
Analytics at the institution
The institution
Enrolled students
Continual monitoring
Small tweaks here and there
Major changes after periods of time
Updating of algorithms and statistical models
Outcome data important as
Assessment
Additional components for inclusion in the model
50. Refine
What was learned from this effort?
Where are the positives?
Where are the deficiencies?
Was the goal realized?
How does the goal/involvement in the project help
meet institutional goals?
Who else needs to be involved to improve/enhance
the process, actions, and outcomes?
How can lessons learned be applied for future use?
51. Refine
Ultimately, answer the following questions:
1. How will you describe this analytics area to
interested parties?
2. Who are the key stakeholders that need to be
included in discussions?
3. Who should serve as the lead for this area at your
institution?
4. What other considerations are there?
52. Elevator Speech for Project
Determine/solidify Institutional Goal
Work on Component Templates
Individual/Group Work
53. What is your goal for this project?
What have you learned?
What are your next steps?
What questions do you still have?
Institution Reporting & Town Hall
56. Expectations Reality
Plug and Play
Immediate results
Solve every problem –
ever!
Universal adoption
Everyone would love it!
Fits, starts, reboots
Mostly long term
outcomes
Solve some problems,
create some new
problems
Lackluster use
Not everyone loved it
57. Institutional Challenges
Data in many places, “owned” by many
people/organizations
Different processes, procedures, and regulations
depending on data owner
Everyone can see potential, but all want something
slightly different
Sustainability – “can’t you just…”
Faculty participation is essential
Staffing is a challenge
58. New Possibilities
Using data that exists on campus
Taking advantages of existing programs
Bringing a “complete picture” beyond academics
Focusing on the “Action” in “Actionable Intelligence”
60. References
Astin, A. W. (1984). Student involvement: A developmental theory for higher education. Journal of College
Student Development, 24, 297-308.
Astin, A. W. (1993). What matters in college? Liberal Education, 79(4).
Astin, A. W. (1994). What matters in college: Four critical years revisited. San Francisco: Jossey-Bass.
Bichsel, J. (2012, August). Analytics in higher education: Benefits, barriers, progress, and recommendations
(Research Report). Louisville, CO: EDUCAUSE Center for Applied Research. Available:
http://net.educause.edu/ir/library/pdf/ERS1207/ers1207.pdf
Cooper, A. (2012). What is Analytics? Definition and Essential Characteristics. CETIS Analytics Series, 1(5).
Available: http://publications.cetis.ac.uk/2012/521
EDUCAUSE Learning Initiative. (2011). 7 things you should know about first-generation learning analytics.
Louisville, CO: EDUCAUSE. Available: http://www.educause.edu/library/resources/7-things-youshould-
know-about-first-generation-learning-analytics
Krumm, A. E., Waddington, R. J., Lonn, S., & Teasley, S. D. (n.d.). Increasing academic success in undergraduate
engineering education using learning analytics: A design based research project. Available:
https://ctools.umich.edu/access/content/group/research/papers/aera2012_krumm_learning_analytics.
pdf
Oblinger, D. G. and Campbell, J. P. (2007). Academic Analytics, EDUCAUSE White Paper.
Society of Learning Analytics Research. (n.d.) About. [Webpage] Available:
http://www.solaresearch.org/mission/about/