Program Content - Class 1
Page contents
Module dates,
Course dataset documentation and reference materials,
Module presentations and recordings (posted within ~1 week after each module ends), and
Module agendas (posted ~1-2 weeks before modules begin)
Suggested project outline
Research question
Approach (including validation)
Data
Results
Caveats
Next steps/the future
Module dates
Module 1: Feb 8-10
Module 2: Feb 22-24
Module 3: Mar 22-24
Module 4: Apr 19-21
Presentations: Jun 8-9
Dataset documentation
datasets from agencies
An overview of core datasets can be seen on this pdf.
The core datasets and field descriptions are listed below. Note: these are the description files received from the agencies providing data, the data and documentation in ADRF may not match exactly to these descriptions:
IL DOC admissions: link to pdf
IL DOC exits: link to pdf
More details on EDUCLVL and HCLASS fields:
IDES wage records ("il_wage"): link to pdf
IDES quarterly enhanced dataset ("il_qcew_employers"): link to pdf
HUD program data: link to pdf (note descriptions are of unaggregated data and not all fields will be included due to data use agreements)
Parole data dictionary: link to Sheet
derived datasets
These are data that the ADRF team created as instruction materials
Person table: link to Sheet
reference info
Table relationships: link to PDF, link to HTML
Offenses and SPPS codes: lookup table
module 1 presentations
Feb 7 - welcome & introduction
Introduction presentation: PowerPoint slides
Jeri Mulrow's presentation: PowerPoint slides
Project definition and scoping tutorial: PowerPoint slides
Why spatial thinking matters: PDF slides
Project examples of social issues and data science: PowerPoint slides
feb 8 - intro to datasets & programming
Introduction session: PowerPoint slides
Orientation to the ADRF and Intro to Python: PowerPoint slides
feb 9 - webscraping & apis
More details on project examples from Rayid's talk: http://dssg.uchicago.edu/projects
Data collection (Alex's slides): link
module 2 presentations
Feb 22 - Databases
Welcome & sample project organization: link to PowerPoint
Databases & SQL: link to PowerPoint
Tom Herzog's presentation: link to PowerPoint
feb 23 - record linkage
Full day recording: link to WebEx video
Record linkage overview: link to PowerPoint
Record linkage - similarity measures and algorithms: link to PDF
Bonus: interview with Jon Sperling and Veronica Helms on Linking National Health Surveys and HUD Administrative Data
Additional slides (9am Feb 24th session): link to slides
Record Linkage by Tokle, Ying, and Bender (note: do not share this document. Password to read is "donotshare"): link to PDF
Ravi Shroff's presentation: link to PDF
feb 24 - programming with big data
Full day recording: link to WebEx video
Programming with Big Data: link to PDF, link to PowerPoint
Jonathan's "working in ADRF" slides: link to PDF
interim material
module 3 materials
Please note: all times below are Central time.
Wednesday 3/22/2017 Machine Learning
Thursday 3/23/2017 Text Analysis + Spatial Analysis
Full day recording: link to WebEx video
Text Analysis: slides
friday 3/24/2017 Network + Project Work
Full day recording: link to WebEx video
module 4 Materials
wednesday 4/19/2017 Inference
Full day recording: link to WebEx video
Error Framework (ppt slides, PDF slides)
Bruce Meyer (slides)
Thursday 4/20/2017 Visualization
Full day recording: link to WebEx video
Friday 4/21/2017 Privacy, Confidentiality, and Ethics
Full day recording: link to WebEx video
presentation information
presentation schedule
Please note: all times are US Eastern. Presentations should last ~20 minutes with ~10 minute Q&A sessions.
Friday, June 9 (recording)
M3 - 9:30 (presentation: ppt | pdf, paper & update summary)
M1 - 10:00 (presentation, paper)
N2 - 10:30 (presentation, paper)
C4 - 11:30 (presentation, paper)
C2 - 12:00 (presentation, paper)
Thursday, June 8
N3 - 9:30 (presentation)
N4 - 10:00 (presentation, paper)
M2 - 10:30 (presentation, paper)
C1 - 11:00 (presentation)
C3 - 11:30 (presentation)
M4 - 12:00 (presentation)
Presentation logistics
Please send us your presentation by 2pm on June 7th so we can add it to the website for download as a backup option in case there are any WebEx issues.
We do expect you all to watch the other project presentations and give the team feedback via this form (we will only share the anonymized feedback to the project teams). We believe this is an important part of the program as you will see how other groups have used the techniques from class and get feedback from a wide audience. If for some reason you cannot make the presentations in real time the WebEx recording will be posted to the website within ~1 day.
WebEx information
When you join please mute your connection. If using the audio conference number please be sure to enter your Attendee ID so it is more clear who is presenting or asking questions.
link: https://umd.webex.com/umd/j.php?MTID=m508e2ad4db4263ee27f63545592b2bd0
Meeting number (access code): 852 866 121
Meeting password: presentation