SlideShare uma empresa Scribd logo
1 de 34
Baixar para ler offline
David Onder
Director of Assessment
Casey Iannone
Consultant
Background
2
Background
3
Freshmen Only
The Problem
• We are asked for program-level data
• Lack of program-level retention and graduation rates
• Complicated (particularly for undergrads)
• Different programs serve different purposes
• High stakes – program prioritization (AA driven)
• Reports lumped all non-retained together
(whether they graduated or stopped out)
4
Reflecting on the past
What We Wanted
• Solid & simple approach (easy to explain and defend)
• Fair
• Useful for all types of programs
• Meaningful for decision-making (high- and low-level)
• Not overly complicated display
• Illuminates
• Overall performance
• Historic trends
• When are students lost
• Something that can be generated yearly w/o too much
effort
7
5 Outcomes
• Five possible outcomes for each student that
declares a given major
• Retained in program
• Graduated in program
• Retained in different program
• Graduated in different program
• Not retained (stop-out/drop-out)
• Exclusive and exhaustive
8
General Approach
• Based on cohorts:
• A student is placed in a program cohort the 1st time
they declare a given program
• Each student in the cohort is flagged as one of the 5
possible outcomes for each ½ year interval (each
regular semester)
• At each interval we report where the members of the
cohort fall
• Each student will only appear in one cohort for a
program (usually)
9
Technical Approach
10
Multiple Iterations
Started with term-level data
This is helpful for programs, in the
context of program history,
but NOT administrators
11
Academic Year
Next combined data into academic years
12
Summary
All students lumped into 3 groups
This is the most summarized data we can (read: are willing to) provide.
The bottom line = Bold 3-group number
13
But how does that compare?
This is average program data to use as a comparison
14
Horizontal stacked bar
• Normally we would never do this, but …..
What are people asking:
1. How is the program performing?
2. How are students performing overall at institution?
3. How many are dropping out?
15
1
2
3
We graph 5 Flags too
@ 1 year @ 4 year @ 6 year
Transitions to completers and drop-outs
16
Compare performance over time
Main question
17
But what about next year?
If we study learning as a data science, we can
reverse engineer the human brain and tailor
learning techniques to maximize the chances of
student success. This is the biggest revolution that
could happen in education, turning it into a data-
driven science, and not such a medieval set of
rumors professors tend to carry on.
-Sebastian Thrun
Most data is only
viewed in one
direction.
A Small Window of
Time Exist to Reach
Students.
The Rising Tide
Of Data.
What is Machine Learning?
Machine learning is the science of getting
computers to act without being explicitly
programmed.
-Stanford University
Supervised Learning
Unsupervised Learning
Continuou
s
Supervised UnsupervisedDiscrete
Classification
or
Categorization
Regression
Clustering
Dimensionality
reduction
Continuou
s
Supervise
d
Unsupervise
d
Discrete
Classification
o KNN
o Trees
o Logistic Regression
o Naïve-Bayes
o SVM
Regression
o Linear
o Polynomial
Decision Trees
Random Forests
Association Analysis
o Apriori
o FP-Growth
Hidden Markov Model
Clustering & Dimensionality
reduction
o SVD
o PCA
o K-means
Ready to enter the
Lab
First-year Retention Example
Student Retention
Binary response:
Retained yes/no
### CREATING MODEL ###
train_new <- DT[1:3032,]
test_new <- DT[3033:3790,]
test_new$fake_retention <- NULL
# Create a new model `my_tree`
my_tree <- rpart( fake_retention ~ SAT + HS.GPA + Gender_Factor + Race_Eth,
data = train_new, method = "class",
control=rpart.control(cp=0.0001) )
# Visualize your new decision tree
prp( my_tree, type = 4, extra = 100, faclen=0, under = TRUE,
compress=FALSE, ycompress=FALSE )
# Make your prediction using `my_tree` and `test_new`
my_prediction <- predict( my_tree, test_new, type = "class“ )
# Create a data frame with two columns: ID & Retained Survived contains your
predictions
vector_studentID <- test_new$ID
my_solution <- data.frame( ID=vector_studentID, Retained=my_prediction )
Brainstorm
Brainstorm
Campus Assessment/Effectiveness Framework
Data Dissemination
Key Stakeholders
Education

Mais conteúdo relacionado

Mais procurados

Inaugural lecture: The power of learning analytics to give students (and teac...
Inaugural lecture: The power of learning analytics to give students (and teac...Inaugural lecture: The power of learning analytics to give students (and teac...
Inaugural lecture: The power of learning analytics to give students (and teac...Bart Rienties
 
Digital World: A Freshmore Course for Computational Thinking at SUTD
Digital World: A Freshmore Course for Computational Thinking at SUTDDigital World: A Freshmore Course for Computational Thinking at SUTD
Digital World: A Freshmore Course for Computational Thinking at SUTDOka Kurniawan
 
Toward an automated student feedback system for text based assignments - Pete...
Toward an automated student feedback system for text based assignments - Pete...Toward an automated student feedback system for text based assignments - Pete...
Toward an automated student feedback system for text based assignments - Pete...Blackboard APAC
 
cause effect diagram of a sample problem
cause effect diagram of a sample problemcause effect diagram of a sample problem
cause effect diagram of a sample problemImran Sajol
 
Improving clinical reasoning skills by means of electronic voting
Improving clinical reasoning skills by means of electronic votingImproving clinical reasoning skills by means of electronic voting
Improving clinical reasoning skills by means of electronic votingNynke Bos
 
MCAS and PARCC Results - Spring 2016
MCAS and PARCC Results - Spring 2016MCAS and PARCC Results - Spring 2016
MCAS and PARCC Results - Spring 2016Franklin Matters
 
Rob howe - assessment strategies in a digital age
Rob howe   - assessment strategies in a digital ageRob howe   - assessment strategies in a digital age
Rob howe - assessment strategies in a digital ageRob Howe
 
K12 Curriculum Strategy - December 2008 - draft 10
K12 Curriculum Strategy - December 2008 - draft 10K12 Curriculum Strategy - December 2008 - draft 10
K12 Curriculum Strategy - December 2008 - draft 10Michael Lach
 
Ensuring a Secure Testing Environment
Ensuring a Secure Testing EnvironmentEnsuring a Secure Testing Environment
Ensuring a Secure Testing EnvironmentExamSoft
 
Creating a Collaborative, Data-Driven Framework for Intervention That Targets...
Creating a Collaborative, Data-Driven Framework for Intervention That Targets...Creating a Collaborative, Data-Driven Framework for Intervention That Targets...
Creating a Collaborative, Data-Driven Framework for Intervention That Targets...cpleister
 

Mais procurados (13)

2.11.16 Math Placement Recommendations -SB 359PDF
2.11.16 Math Placement Recommendations -SB 359PDF2.11.16 Math Placement Recommendations -SB 359PDF
2.11.16 Math Placement Recommendations -SB 359PDF
 
Inaugural lecture: The power of learning analytics to give students (and teac...
Inaugural lecture: The power of learning analytics to give students (and teac...Inaugural lecture: The power of learning analytics to give students (and teac...
Inaugural lecture: The power of learning analytics to give students (and teac...
 
Digital World: A Freshmore Course for Computational Thinking at SUTD
Digital World: A Freshmore Course for Computational Thinking at SUTDDigital World: A Freshmore Course for Computational Thinking at SUTD
Digital World: A Freshmore Course for Computational Thinking at SUTD
 
Toward an automated student feedback system for text based assignments - Pete...
Toward an automated student feedback system for text based assignments - Pete...Toward an automated student feedback system for text based assignments - Pete...
Toward an automated student feedback system for text based assignments - Pete...
 
cause effect diagram of a sample problem
cause effect diagram of a sample problemcause effect diagram of a sample problem
cause effect diagram of a sample problem
 
Improving clinical reasoning skills by means of electronic voting
Improving clinical reasoning skills by means of electronic votingImproving clinical reasoning skills by means of electronic voting
Improving clinical reasoning skills by means of electronic voting
 
Creating Safe Space
Creating Safe SpaceCreating Safe Space
Creating Safe Space
 
MCAS and PARCC Results - Spring 2016
MCAS and PARCC Results - Spring 2016MCAS and PARCC Results - Spring 2016
MCAS and PARCC Results - Spring 2016
 
Rob howe - assessment strategies in a digital age
Rob howe   - assessment strategies in a digital ageRob howe   - assessment strategies in a digital age
Rob howe - assessment strategies in a digital age
 
Phase I: Overview
Phase I: OverviewPhase I: Overview
Phase I: Overview
 
K12 Curriculum Strategy - December 2008 - draft 10
K12 Curriculum Strategy - December 2008 - draft 10K12 Curriculum Strategy - December 2008 - draft 10
K12 Curriculum Strategy - December 2008 - draft 10
 
Ensuring a Secure Testing Environment
Ensuring a Secure Testing EnvironmentEnsuring a Secure Testing Environment
Ensuring a Secure Testing Environment
 
Creating a Collaborative, Data-Driven Framework for Intervention That Targets...
Creating a Collaborative, Data-Driven Framework for Intervention That Targets...Creating a Collaborative, Data-Driven Framework for Intervention That Targets...
Creating a Collaborative, Data-Driven Framework for Intervention That Targets...
 

Destaque (8)

Seminario derecho a vivir en familia
Seminario derecho a vivir en familiaSeminario derecho a vivir en familia
Seminario derecho a vivir en familia
 
Handbook for CPK
Handbook for CPKHandbook for CPK
Handbook for CPK
 
CERC 2014 中文題意
CERC 2014 中文題意CERC 2014 中文題意
CERC 2014 中文題意
 
Amistad entre pescador y cocodrilo
Amistad entre pescador y cocodriloAmistad entre pescador y cocodrilo
Amistad entre pescador y cocodrilo
 
Paseando por Torla (Huesca)
Paseando por Torla (Huesca)Paseando por Torla (Huesca)
Paseando por Torla (Huesca)
 
Seminario alfin 2
Seminario alfin 2Seminario alfin 2
Seminario alfin 2
 
La inocencia
La inocenciaLa inocencia
La inocencia
 
The Sec. Manag. Stage 1
The Sec.  Manag. Stage 1The Sec.  Manag. Stage 1
The Sec. Manag. Stage 1
 

Semelhante a 2016 NCAIR Analytics: Reflective to Predictive

At d & data presentation
At d & data presentationAt d & data presentation
At d & data presentationharrindl
 
2020_09_24 «How Learning Analytics Can Inform E-Learning in the New Normal» -...
2020_09_24 «How Learning Analytics Can Inform E-Learning in the New Normal» -...2020_09_24 «How Learning Analytics Can Inform E-Learning in the New Normal» -...
2020_09_24 «How Learning Analytics Can Inform E-Learning in the New Normal» -...eMadrid network
 
The why and what of testa
The why and what of testaThe why and what of testa
The why and what of testaTansy Jessop
 
RtIMTSS SPE 501-Spr
  RtIMTSS                                       SPE 501-Spr  RtIMTSS                                       SPE 501-Spr
RtIMTSS SPE 501-SprVannaJoy20
 
Sacred heart 2014
Sacred heart 2014Sacred heart 2014
Sacred heart 2014EdAdvance
 
The Career Explorer: helping young people with educational choices and career...
The Career Explorer: helping young people with educational choices and career...The Career Explorer: helping young people with educational choices and career...
The Career Explorer: helping young people with educational choices and career...Jisc
 
Using Data for Continuos School Improvement
Using Data for Continuos School ImprovementUsing Data for Continuos School Improvement
Using Data for Continuos School Improvementlindamtz88
 
Why a programme view? Why TESTA?
Why a programme view? Why TESTA?Why a programme view? Why TESTA?
Why a programme view? Why TESTA?Tansy Jessop
 
PRtI and PLC Presentation for AdvancEd
PRtI and PLC Presentation for AdvancEdPRtI and PLC Presentation for AdvancEd
PRtI and PLC Presentation for AdvancEdMike Huber
 
Ordinary to Extraordinary: The Role Each of Us Must Play
Ordinary to Extraordinary: The Role Each of Us Must PlayOrdinary to Extraordinary: The Role Each of Us Must Play
Ordinary to Extraordinary: The Role Each of Us Must Playcatapultlearn
 
Educational Reforms Of INDIA ppt
Educational  Reforms  Of INDIA pptEducational  Reforms  Of INDIA ppt
Educational Reforms Of INDIA pptDibyendu Das
 
Classroom diagnostic tools training 9.23.14
Classroom diagnostic tools training 9.23.14Classroom diagnostic tools training 9.23.14
Classroom diagnostic tools training 9.23.14nickpaolini81
 
Year 10 Cohort Meeting January 2024.pptx
Year 10 Cohort Meeting January 2024.pptxYear 10 Cohort Meeting January 2024.pptx
Year 10 Cohort Meeting January 2024.pptxmansk2
 
Virtual Bridge Sessions: Key Messages from Research on Blended or Digital Lea...
Virtual Bridge Sessions: Key Messages from Research on Blended or Digital Lea...Virtual Bridge Sessions: Key Messages from Research on Blended or Digital Lea...
Virtual Bridge Sessions: Key Messages from Research on Blended or Digital Lea...College Development Network
 
Learning Analytics In Higher Education: Struggles & Successes (Part 2)
Learning Analytics In Higher Education: Struggles & Successes (Part 2)Learning Analytics In Higher Education: Struggles & Successes (Part 2)
Learning Analytics In Higher Education: Struggles & Successes (Part 2)Lambda Solutions
 
Designing Early Alert Programs Aimed at Fostering Student Success and Persist...
Designing Early Alert Programs Aimed at Fostering Student Success and Persist...Designing Early Alert Programs Aimed at Fostering Student Success and Persist...
Designing Early Alert Programs Aimed at Fostering Student Success and Persist...Mike Dial
 
Technology-Enhanced-Assessment-for-Learning.pptx
Technology-Enhanced-Assessment-for-Learning.pptxTechnology-Enhanced-Assessment-for-Learning.pptx
Technology-Enhanced-Assessment-for-Learning.pptxFroilanAlexCuevas1
 

Semelhante a 2016 NCAIR Analytics: Reflective to Predictive (20)

At d & data presentation
At d & data presentationAt d & data presentation
At d & data presentation
 
2020_09_24 «How Learning Analytics Can Inform E-Learning in the New Normal» -...
2020_09_24 «How Learning Analytics Can Inform E-Learning in the New Normal» -...2020_09_24 «How Learning Analytics Can Inform E-Learning in the New Normal» -...
2020_09_24 «How Learning Analytics Can Inform E-Learning in the New Normal» -...
 
The why and what of testa
The why and what of testaThe why and what of testa
The why and what of testa
 
RtIMTSS SPE 501-Spr
  RtIMTSS                                       SPE 501-Spr  RtIMTSS                                       SPE 501-Spr
RtIMTSS SPE 501-Spr
 
Sacred heart 2014
Sacred heart 2014Sacred heart 2014
Sacred heart 2014
 
The Career Explorer: helping young people with educational choices and career...
The Career Explorer: helping young people with educational choices and career...The Career Explorer: helping young people with educational choices and career...
The Career Explorer: helping young people with educational choices and career...
 
Using Data for Continuos School Improvement
Using Data for Continuos School ImprovementUsing Data for Continuos School Improvement
Using Data for Continuos School Improvement
 
Why a programme view? Why TESTA?
Why a programme view? Why TESTA?Why a programme view? Why TESTA?
Why a programme view? Why TESTA?
 
Attachment.aspx
Attachment.aspxAttachment.aspx
Attachment.aspx
 
PRtI and PLC Presentation for AdvancEd
PRtI and PLC Presentation for AdvancEdPRtI and PLC Presentation for AdvancEd
PRtI and PLC Presentation for AdvancEd
 
Ordinary to Extraordinary: The Role Each of Us Must Play
Ordinary to Extraordinary: The Role Each of Us Must PlayOrdinary to Extraordinary: The Role Each of Us Must Play
Ordinary to Extraordinary: The Role Each of Us Must Play
 
Educational Reforms Of INDIA ppt
Educational  Reforms  Of INDIA pptEducational  Reforms  Of INDIA ppt
Educational Reforms Of INDIA ppt
 
Classroom diagnostic tools training 9.23.14
Classroom diagnostic tools training 9.23.14Classroom diagnostic tools training 9.23.14
Classroom diagnostic tools training 9.23.14
 
Year 10 Cohort Meeting January 2024.pptx
Year 10 Cohort Meeting January 2024.pptxYear 10 Cohort Meeting January 2024.pptx
Year 10 Cohort Meeting January 2024.pptx
 
A Quiet Crisis
A Quiet CrisisA Quiet Crisis
A Quiet Crisis
 
Virtual Bridge Sessions: Key Messages from Research on Blended or Digital Lea...
Virtual Bridge Sessions: Key Messages from Research on Blended or Digital Lea...Virtual Bridge Sessions: Key Messages from Research on Blended or Digital Lea...
Virtual Bridge Sessions: Key Messages from Research on Blended or Digital Lea...
 
Learning Analytics In Higher Education: Struggles & Successes (Part 2)
Learning Analytics In Higher Education: Struggles & Successes (Part 2)Learning Analytics In Higher Education: Struggles & Successes (Part 2)
Learning Analytics In Higher Education: Struggles & Successes (Part 2)
 
NYC Social Studies PD
NYC Social Studies PDNYC Social Studies PD
NYC Social Studies PD
 
Designing Early Alert Programs Aimed at Fostering Student Success and Persist...
Designing Early Alert Programs Aimed at Fostering Student Success and Persist...Designing Early Alert Programs Aimed at Fostering Student Success and Persist...
Designing Early Alert Programs Aimed at Fostering Student Success and Persist...
 
Technology-Enhanced-Assessment-for-Learning.pptx
Technology-Enhanced-Assessment-for-Learning.pptxTechnology-Enhanced-Assessment-for-Learning.pptx
Technology-Enhanced-Assessment-for-Learning.pptx
 

Mais de David Onder

2016 AALHE Improving Assessment in Program Review Through Learning Communitie...
2016 AALHE Improving Assessment in Program Review Through Learning Communitie...2016 AALHE Improving Assessment in Program Review Through Learning Communitie...
2016 AALHE Improving Assessment in Program Review Through Learning Communitie...David Onder
 
2015 NCAIR Excel Power Tools
2015 NCAIR Excel Power Tools2015 NCAIR Excel Power Tools
2015 NCAIR Excel Power ToolsDavid Onder
 
2014 AIR Reporting Program-level Retention and Graduation
2014 AIR Reporting Program-level Retention and Graduation2014 AIR Reporting Program-level Retention and Graduation
2014 AIR Reporting Program-level Retention and GraduationDavid Onder
 
2014 AIR "Power" Tools for IR Reporting - workshop
2014 AIR "Power" Tools for IR Reporting - workshop2014 AIR "Power" Tools for IR Reporting - workshop
2014 AIR "Power" Tools for IR Reporting - workshopDavid Onder
 
2014 AIR "Power" Tools for IR Reporting
2014 AIR "Power" Tools for IR Reporting2014 AIR "Power" Tools for IR Reporting
2014 AIR "Power" Tools for IR ReportingDavid Onder
 
2013 NCAIR Report Automation Using Excel
2013 NCAIR Report Automation Using Excel2013 NCAIR Report Automation Using Excel
2013 NCAIR Report Automation Using ExcelDavid Onder
 
2012 SAIR It's not about pie when it comes to the facts
2012 SAIR It's not about pie when it comes to the facts2012 SAIR It's not about pie when it comes to the facts
2012 SAIR It's not about pie when it comes to the factsDavid Onder
 
2012 SAIR The Pie Maker - Automating the Fact Book Creation Process
2012 SAIR The Pie Maker - Automating the Fact Book Creation Process2012 SAIR The Pie Maker - Automating the Fact Book Creation Process
2012 SAIR The Pie Maker - Automating the Fact Book Creation ProcessDavid Onder
 
2012 SAIR Reporting Program-level Retention and Graduation
2012 SAIR Reporting Program-level Retention and Graduation2012 SAIR Reporting Program-level Retention and Graduation
2012 SAIR Reporting Program-level Retention and GraduationDavid Onder
 
2011 SAIR Updating Digital Measures Activity Insight Using MS Office - Handouts
2011 SAIR Updating Digital Measures Activity Insight Using MS Office - Handouts2011 SAIR Updating Digital Measures Activity Insight Using MS Office - Handouts
2011 SAIR Updating Digital Measures Activity Insight Using MS Office - HandoutsDavid Onder
 
2011 SAIR It's not about pie when it comes to the facts
2011 SAIR It's not about pie when it comes to the facts2011 SAIR It's not about pie when it comes to the facts
2011 SAIR It's not about pie when it comes to the factsDavid Onder
 
2010 SACSCOC Administrative Program Review - with handouts
2010 SACSCOC Administrative Program Review - with handouts2010 SACSCOC Administrative Program Review - with handouts
2010 SACSCOC Administrative Program Review - with handoutsDavid Onder
 
CCPRO 2016 Power Presentation
CCPRO 2016 Power PresentationCCPRO 2016 Power Presentation
CCPRO 2016 Power PresentationDavid Onder
 

Mais de David Onder (13)

2016 AALHE Improving Assessment in Program Review Through Learning Communitie...
2016 AALHE Improving Assessment in Program Review Through Learning Communitie...2016 AALHE Improving Assessment in Program Review Through Learning Communitie...
2016 AALHE Improving Assessment in Program Review Through Learning Communitie...
 
2015 NCAIR Excel Power Tools
2015 NCAIR Excel Power Tools2015 NCAIR Excel Power Tools
2015 NCAIR Excel Power Tools
 
2014 AIR Reporting Program-level Retention and Graduation
2014 AIR Reporting Program-level Retention and Graduation2014 AIR Reporting Program-level Retention and Graduation
2014 AIR Reporting Program-level Retention and Graduation
 
2014 AIR "Power" Tools for IR Reporting - workshop
2014 AIR "Power" Tools for IR Reporting - workshop2014 AIR "Power" Tools for IR Reporting - workshop
2014 AIR "Power" Tools for IR Reporting - workshop
 
2014 AIR "Power" Tools for IR Reporting
2014 AIR "Power" Tools for IR Reporting2014 AIR "Power" Tools for IR Reporting
2014 AIR "Power" Tools for IR Reporting
 
2013 NCAIR Report Automation Using Excel
2013 NCAIR Report Automation Using Excel2013 NCAIR Report Automation Using Excel
2013 NCAIR Report Automation Using Excel
 
2012 SAIR It's not about pie when it comes to the facts
2012 SAIR It's not about pie when it comes to the facts2012 SAIR It's not about pie when it comes to the facts
2012 SAIR It's not about pie when it comes to the facts
 
2012 SAIR The Pie Maker - Automating the Fact Book Creation Process
2012 SAIR The Pie Maker - Automating the Fact Book Creation Process2012 SAIR The Pie Maker - Automating the Fact Book Creation Process
2012 SAIR The Pie Maker - Automating the Fact Book Creation Process
 
2012 SAIR Reporting Program-level Retention and Graduation
2012 SAIR Reporting Program-level Retention and Graduation2012 SAIR Reporting Program-level Retention and Graduation
2012 SAIR Reporting Program-level Retention and Graduation
 
2011 SAIR Updating Digital Measures Activity Insight Using MS Office - Handouts
2011 SAIR Updating Digital Measures Activity Insight Using MS Office - Handouts2011 SAIR Updating Digital Measures Activity Insight Using MS Office - Handouts
2011 SAIR Updating Digital Measures Activity Insight Using MS Office - Handouts
 
2011 SAIR It's not about pie when it comes to the facts
2011 SAIR It's not about pie when it comes to the facts2011 SAIR It's not about pie when it comes to the facts
2011 SAIR It's not about pie when it comes to the facts
 
2010 SACSCOC Administrative Program Review - with handouts
2010 SACSCOC Administrative Program Review - with handouts2010 SACSCOC Administrative Program Review - with handouts
2010 SACSCOC Administrative Program Review - with handouts
 
CCPRO 2016 Power Presentation
CCPRO 2016 Power PresentationCCPRO 2016 Power Presentation
CCPRO 2016 Power Presentation
 

Último

How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17Celine George
 
Activity 2-unit 2-update 2024. English translation
Activity 2-unit 2-update 2024. English translationActivity 2-unit 2-update 2024. English translation
Activity 2-unit 2-update 2024. English translationRosabel UA
 
Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatYousafMalik24
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Mark Reed
 
Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4JOYLYNSAMANIEGO
 
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxiammrhaywood
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parentsnavabharathschool99
 
Integumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.pptIntegumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.pptshraddhaparab530
 
Keynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designKeynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designMIPLM
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Celine George
 
AUDIENCE THEORY -CULTIVATION THEORY - GERBNER.pptx
AUDIENCE THEORY -CULTIVATION THEORY -  GERBNER.pptxAUDIENCE THEORY -CULTIVATION THEORY -  GERBNER.pptx
AUDIENCE THEORY -CULTIVATION THEORY - GERBNER.pptxiammrhaywood
 
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTSGRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTSJoshuaGantuangco2
 
Concurrency Control in Database Management system
Concurrency Control in Database Management systemConcurrency Control in Database Management system
Concurrency Control in Database Management systemChristalin Nelson
 
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxINTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxHumphrey A Beña
 
ROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptxROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptxVanesaIglesias10
 
Full Stack Web Development Course for Beginners
Full Stack Web Development Course  for BeginnersFull Stack Web Development Course  for Beginners
Full Stack Web Development Course for BeginnersSabitha Banu
 
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdfInclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdfTechSoup
 

Último (20)

How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17How to Add Barcode on PDF Report in Odoo 17
How to Add Barcode on PDF Report in Odoo 17
 
Activity 2-unit 2-update 2024. English translation
Activity 2-unit 2-update 2024. English translationActivity 2-unit 2-update 2024. English translation
Activity 2-unit 2-update 2024. English translation
 
Earth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice greatEarth Day Presentation wow hello nice great
Earth Day Presentation wow hello nice great
 
Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)Influencing policy (training slides from Fast Track Impact)
Influencing policy (training slides from Fast Track Impact)
 
YOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptx
YOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptxYOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptx
YOUVE_GOT_EMAIL_PRELIMS_EL_DORADO_2024.pptx
 
Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4Daily Lesson Plan in Mathematics Quarter 4
Daily Lesson Plan in Mathematics Quarter 4
 
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptxECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
ECONOMIC CONTEXT - PAPER 1 Q3: NEWSPAPERS.pptx
 
Choosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for ParentsChoosing the Right CBSE School A Comprehensive Guide for Parents
Choosing the Right CBSE School A Comprehensive Guide for Parents
 
Integumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.pptIntegumentary System SMP B. Pharm Sem I.ppt
Integumentary System SMP B. Pharm Sem I.ppt
 
Keynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-designKeynote by Prof. Wurzer at Nordex about IP-design
Keynote by Prof. Wurzer at Nordex about IP-design
 
Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17Field Attribute Index Feature in Odoo 17
Field Attribute Index Feature in Odoo 17
 
AUDIENCE THEORY -CULTIVATION THEORY - GERBNER.pptx
AUDIENCE THEORY -CULTIVATION THEORY -  GERBNER.pptxAUDIENCE THEORY -CULTIVATION THEORY -  GERBNER.pptx
AUDIENCE THEORY -CULTIVATION THEORY - GERBNER.pptx
 
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptxYOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
YOUVE GOT EMAIL_FINALS_EL_DORADO_2024.pptx
 
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTSGRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
GRADE 4 - SUMMATIVE TEST QUARTER 4 ALL SUBJECTS
 
Concurrency Control in Database Management system
Concurrency Control in Database Management systemConcurrency Control in Database Management system
Concurrency Control in Database Management system
 
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxINTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
 
ROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptxROLES IN A STAGE PRODUCTION in arts.pptx
ROLES IN A STAGE PRODUCTION in arts.pptx
 
Full Stack Web Development Course for Beginners
Full Stack Web Development Course  for BeginnersFull Stack Web Development Course  for Beginners
Full Stack Web Development Course for Beginners
 
Raw materials used in Herbal Cosmetics.pptx
Raw materials used in Herbal Cosmetics.pptxRaw materials used in Herbal Cosmetics.pptx
Raw materials used in Herbal Cosmetics.pptx
 
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdfInclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
Inclusivity Essentials_ Creating Accessible Websites for Nonprofits .pdf
 

2016 NCAIR Analytics: Reflective to Predictive

  • 1. David Onder Director of Assessment Casey Iannone Consultant
  • 4. The Problem • We are asked for program-level data • Lack of program-level retention and graduation rates • Complicated (particularly for undergrads) • Different programs serve different purposes • High stakes – program prioritization (AA driven) • Reports lumped all non-retained together (whether they graduated or stopped out) 4
  • 5.
  • 7. What We Wanted • Solid & simple approach (easy to explain and defend) • Fair • Useful for all types of programs • Meaningful for decision-making (high- and low-level) • Not overly complicated display • Illuminates • Overall performance • Historic trends • When are students lost • Something that can be generated yearly w/o too much effort 7
  • 8. 5 Outcomes • Five possible outcomes for each student that declares a given major • Retained in program • Graduated in program • Retained in different program • Graduated in different program • Not retained (stop-out/drop-out) • Exclusive and exhaustive 8
  • 9. General Approach • Based on cohorts: • A student is placed in a program cohort the 1st time they declare a given program • Each student in the cohort is flagged as one of the 5 possible outcomes for each ½ year interval (each regular semester) • At each interval we report where the members of the cohort fall • Each student will only appear in one cohort for a program (usually) 9
  • 11. Multiple Iterations Started with term-level data This is helpful for programs, in the context of program history, but NOT administrators 11
  • 12. Academic Year Next combined data into academic years 12
  • 13. Summary All students lumped into 3 groups This is the most summarized data we can (read: are willing to) provide. The bottom line = Bold 3-group number 13
  • 14. But how does that compare? This is average program data to use as a comparison 14
  • 15. Horizontal stacked bar • Normally we would never do this, but ….. What are people asking: 1. How is the program performing? 2. How are students performing overall at institution? 3. How many are dropping out? 15 1 2 3
  • 16. We graph 5 Flags too @ 1 year @ 4 year @ 6 year Transitions to completers and drop-outs 16 Compare performance over time
  • 17. Main question 17 But what about next year?
  • 18.
  • 19. If we study learning as a data science, we can reverse engineer the human brain and tailor learning techniques to maximize the chances of student success. This is the biggest revolution that could happen in education, turning it into a data- driven science, and not such a medieval set of rumors professors tend to carry on. -Sebastian Thrun
  • 20. Most data is only viewed in one direction.
  • 21. A Small Window of Time Exist to Reach Students.
  • 23. What is Machine Learning?
  • 24. Machine learning is the science of getting computers to act without being explicitly programmed. -Stanford University
  • 25.
  • 28. Continuou s Supervise d Unsupervise d Discrete Classification o KNN o Trees o Logistic Regression o Naïve-Bayes o SVM Regression o Linear o Polynomial Decision Trees Random Forests Association Analysis o Apriori o FP-Growth Hidden Markov Model Clustering & Dimensionality reduction o SVD o PCA o K-means
  • 29. Ready to enter the Lab
  • 30. First-year Retention Example Student Retention Binary response: Retained yes/no
  • 31. ### CREATING MODEL ### train_new <- DT[1:3032,] test_new <- DT[3033:3790,] test_new$fake_retention <- NULL # Create a new model `my_tree` my_tree <- rpart( fake_retention ~ SAT + HS.GPA + Gender_Factor + Race_Eth, data = train_new, method = "class", control=rpart.control(cp=0.0001) ) # Visualize your new decision tree prp( my_tree, type = 4, extra = 100, faclen=0, under = TRUE, compress=FALSE, ycompress=FALSE ) # Make your prediction using `my_tree` and `test_new` my_prediction <- predict( my_tree, test_new, type = "class“ ) # Create a data frame with two columns: ID & Retained Survived contains your predictions vector_studentID <- test_new$ID my_solution <- data.frame( ID=vector_studentID, Retained=my_prediction )
  • 32.
  • 34. Brainstorm Campus Assessment/Effectiveness Framework Data Dissemination Key Stakeholders Education