ASA DataFestTM @Duke
Are you data driven?


Duke / UNC / NCSU
March 20 - 22, 2015
Find out more!

About

What is DataFest?

ASA DataFestTM is a data analysis competition where teams of up to five students have a weekend to attack a large, complex, and surprise dataset. Your job is to represent your school by finding and communicating insights into these data. The teams that impress the judges will win prizes as well as glory for their school. Everyone else will have a great experience, lots of food, and fun!

While ASA DataFestTM is a competition, the main goal of the event is to promote collaboration. Here is a testimonial from past participants:

  • It was a great experience, with a fun and interesting challenge. One of my favorite parts is how varied the presentations and projects from each team are. I love learning about ways in which others looked at and analyzed the same problem/ data.

  • DataFest was an awesome experience. To me, the best part was working in a team of friends that I usually hung out with, but had not had a chance to work together intensively on a project. We enjoyed analyzing the situations and solving problems together for our client. At the end of the day, we just got to know each other better. It was also fun to interact with other teams to explore other approaches while keeping in mind that we were in competition. The fact that we were given a huge amount of data really challenges us to come up with creative and practical approaches. Another important part was the presentation. Every team had to explain well to the judges their objectives and solutions. Our team won the Best Visualization award which is really awesome. Lastly, the food was fantastic.

ASA DataFestTM is also a great opportunity to gain experience that employers are looking for. Having worked on a data analysis problem at this scale will certainly help make you a good candidate for any position that involves analysis and critical thinking, and it will provide a concrete example to demonstrate your experience during interviews.
Event details
ASA DataFestTM 2015 starts on Friday, March 20, 2015 at 6pm at The Edge at Duke University, and will end by 5pm on Sunday, March 22, 2015.

On Friday we will start with a reception where your surprise client will give a brief introduction to the data you will be working with over the weekend and tell you a bit about what they would like to get out of it. The data will likely be much more complex than what you are used to seeing in your classes, and you will be given free reign to analyze it however you like. In other words, you will come up with a research question that is of interest to you, and conduct the appropriate analysis to answer your question. But you are welcomed, and encouraged, to take cues from the client's introduction when shaping your research question(s).

Presentations and judging will begin ~2pm on Sunday, March 22, 2015. Each team will give a brief (5 minute) presentation of their findings to a panel of judges comprised of faculty and professionals from a variety of fields. There will be prizes in many categories, such as best visualization, best use of external data, and best findings. A finalized list of categories will be announced at the beginning of the competition.
Past DataFests @ Duke
Follow the links below to read about past DataFest events at Duke:


ASA DataFestTM 2015 @Duke is organized by the Department of Statistical Science at Duke University and
co-hosted by the Departments of Statistics and Operations Research at UNC and Statistics at NCSU.

       

Sign up

Participants - sign up for ASA DataFestTM 2015 @Duke below

If you are interested in serving as a VIP Consultant during the event, please let us know your availability here.

Registration is now closed. If you have any questions about registration please contact Mine Çetinkaya-Rundel.
-->

DataFest 2015 @Duke

Congratulations to all 200+ students from Duke, UNC, NCSU, NCCU, North Carolina A&T, UNC Greensboro, and University of Michigan
who participated in ASA DataFest 2015 @Duke,
and a huge thanks to all of our sponsors who made this weekend possible.

We had lots of fun and lots of food, here is the photographic evidence:



And the participants produced incredibly impressive projects. While we can't yet share those with you just yet (until all national DataFest events are over),
please check back at the end of April for our ASA DataFest 2015 @Duke showcase.

There is no reason, however, to wait to congratulate the winners!

Best Visualization: Bayes' Anatomy - Duke University
David Clancy - Statistical Science + Mathematics, Junior
Gregory Poore - Biomedical Engineering, Junior
Michael Lin - Mathematics, Junior
Tori Hall - Statistical Science, Junior

Best Use of Outside Data: Type 3 Errors - Duke University
Justin Yu - Biomedical Engineering, Senior
Matt Tyler - Statistical Science, Senior

Best Insight: poke.R - Duke University
Hong Xu, Engineering Management, MS
Ruofei Wang, Engineering Management, MS
Yang Su, Statistical Science, MS
Yikun Zhou, Statistical & Economic Modeling, MS
Yuyin Gu, Environmental Management, MS

Sponsors

A huge thanks to our sponsors, ASA DataFestTM at Duke cannot run without your support!

Become a sponsor

Panton Inc.

Cauchy Sponsor

Duke SSRI

Cauchy Sponsor

SAS

Pareto Sponsor

Duke iiD

Pareto Sponsor

RTI

Pareto Sponsor

Innovation Co-Lab

Pareto Sponsor

MaxPoint

Lognormal Sponsor

APT

Lognormal Sponsor

Google

Lognormal Sponsor

Duke MEMP

Lognormal Sponsor

RStudio

Weibull Sponsor

JMP

Weibull Sponsor

DataCamp

Weibull Sponsor

Revolution Analytics

Weibull Sponsor

Duke Libraries

Acknowledgments

ASA

Acknowledgments

Want to sponsor?

Sponsorship

ASA DataFestTM cannot run without your support.
Please see below for Sponsorship opportunities. Note that your donations are tax-deductible.
Please contact us if you are interested in sponsorship and/or have any questions.

Impact of Your Sponsorship
Your sponsorship of ASA DataFestTM 2015 benefits the ASA DataFestTM @Duke. Any residual funds will support undergraduate statistics education, foster the new generation of data science, and advance our mission of promoting the use of data in the understanding of our environment, our social relationships, and our physical and virtual selves.
Benefits of Sponsorship
Sponsors will be provided with various advertising and recruiting opportunities. But equally important is your time! Please consider visiting us as a "VIP Consultant". Drop by for a couple of hours and talk to the teams to point them in the right direction. It's a wonderful recruiting opportunity and lots of fun, too. We ask that visitors sign up for a time slot so that we'll know when to expect you, but we won't hold you to it: http://goo.gl/forms/vz1fPvGyX2.
Sponsorship Levels
Cauchy Sponsor - $3000 and above
  • Large logo prominently placed on ASA DataFestTM posters and flyers
  • Large logo on official 2015 ASA DataFestTM t-shirt
  • Logo and link on ASA DataFestTM website
  • Short company/organization profile and link on ASA DataFestTM social media (FB, Twitter, etc.)
  • Company/organization name on food table display
  • If requested, company/organization information session on Duke campus advertised to Duke StatSci students as well as all 2015 ASA DataFestTM participants (we will provide the space and advertise your event)
  • Table for HR/recruitment for four hours during DataFest
Pareto Sponsor - $1500 - $3000
  • Medium logo on ASA DataFestTM posters and flyers
  • Medium logo on official 2015 ASA DataFestTM t-shirt
  • Logo and link on ASA DataFestTM website
  • Short company/organization profile and link on ASA DataFestTM social media (FB, Twitter, etc.)
  • Company/organization name on food table display
  • Table for HR/recruitment for two hours during DataFest
Lognormal Sponsor - $1000 - $1500
  • Small logo on ASA DataFestTM posters and flyers
  • Small logo on official 2015 ASA DataFestTM t-shirt
  • Logo and link on ASA DataFestTM website
  • Short company/organization profile and link on ASA DataFestTM social media (FB, Twitter, etc.)
  • Company/organization name on food table display
Weibull Sponsor - $500 - $1000
  • Small logo on ASA DataFestTM posters and flyers
  • Logo and link on ASA DataFestTM website
  • Short company/organization profile and link on ASA DataFestTM social media (FB, Twitter, etc.)
  • Company/organization name on food table display
Acknowledgements - up to $500
  • Logo and link on ASA DataFestTM website
  • Company/organization name on food table display
Ways to give
You can make your donation online at https://www.gifts.duke.edu. Funds should be designated to Trinity College of Arts & Sciences - Experiential learning opportunities. Please note in the comments that the funds are allocated for "Department of Statistical Science - DataFest, Fund code: 3991698". You can also mail your donation to
  • Alumni and Development Records
  • Duke University, Box 90581
  • Durham, NC 27708-0581
  • Phone: (919) 684-2338
  • Fax: (919) 684-8527
Please note on your check "Department of Statistical Science - DataFest, Fund code: 3991698". More information can be found on the Duke Forward page.
Sponsorship questions?
Please do not hesitate to contact Mine Çetinkaya-Rundel, ASA DataFestTM @Duke coordinator, with any questions.

Workshops

These workshops are recommended for DataFest participants, but they're open to everyone.
All workshops will be held in the The Edge Workshop Room.

Sign up

Intro to R

slides | source
Monday, March 16, 6-8pm
Instructors: Gary Larson and Monika Hu, Duke StatSci
Description: Introduction to R as a statistical programming language. This session will introduce the basics of R syntax, getting data into R, various data types and classes, etc. The session assumes no or little background in R.
Sign up

Easy Interactive Charts and Maps with Tableau

slides & recording
Tuesday, March 17, 1:30-3:30pm
Instructor: Angela Zoss, Data Visualization Coordinator, Data & GIS Services Description: Tableau Public (now available for both Windows and Mac) is free software that allows individuals to quickly create interactive visualizations of their research and business analytics data. This workshop will focus on using Tableau Public to create data visualizations, starting with an overview of the structure of the program and the terminology used. The workshop will include a sample data visualization and mapping project, focusing especially on some of the new features in Tableau Public 8. We will also discuss publishing to the Tableau Public web server and related services and tools, like the full Tableau Desktop application (free for full-time students).
Sign up

Data munging with R and dplyr

slides | solutions | source
Wednesday, March 18, 6-8pm
Instructor: Prof. Colin Rundel, Duke StatSci
Description: This session will demonstrate tools for data manipulation and cleaning of data in R. Majority of the session will use the dplyr and tidyr packages. Some background in R is recommended.
Sign up

Visualization in d3

slides | source
Thursday, March 19, 7-9pm
Instructor: Avi Moondra, Duke StatSci
Description: This is a session for those who have little to no experience with D3.js visualizations. We'll go over some fundamental d3 programming paradigms and work with a few layouts. To see the full power of d3, browse here! Some background in JavaScript or any functional programming language (like R!) is recommended.

Schedule

This page will be updated as the event approaches.

  • Friday, March 20, 2015

    Welcome!

    @The Edge unless otherwise noted

    • 5-6pm - Registration @Perkins 217
    • 6-7pm - Meet the data @Perkins 217
    • 7pm - Dinner
    VIP Consultants available for help until midnight, you can work as late as you like.

  • Saturday, March 21, 2015

    Carry on!

    @The Edge all day

    • 9am - Breakfast
    • 12:30pm - Lunch
    • 6:30pm - Dinner
    VIP Consultants available for help until midnight, you can work as late as you like.

  • Sunday, March 22, 2015

    Wrap up!

    @The Edge unless otherwise noted

    • 9am - Breakfast
    • 12:30pm - Stop work & Lunch
    • 1-4pm - Presentations & judges deliberations @Perkins 217
    • 4-5pm - Award ceremony @Perkins 217
    VIP Consultants available for help until 12:30pm.

Media

If you would like to write about or cover ASA DataFestTM in any way, please don't hesitate to contact us.

FAQ

  • How do I sign up?

    Click here to sign up. Please fill out the form fully. Each member of the team must register separately. Ideally, you will have already chosen a team name, but this can be changed later. If you'd like to compete but don't have a team, send us an email and we'll link you up with other students who are looking for teammates. Seats are limited, so register early! The registration deadline is Friday, March 6, at 5pm. There is a nominal registration fee of $20, but you can apply for a registration grant. To do so, simply check the appropriate box on the registration form. These will be approved on a rolling basis, and you will find out within a few days of applying.
  • Who is eligible to compete?

    All Duke, UNC, NCSU undergraduate and MS students are eligible to compete.
  • What about PhD students?

    We would love to have PhD students get involved as VIP Consultants during the event. Sign up here if you're interested.
  • How large are the teams?

    Teams can be made up of 2-5 students.
  • Do I have to compete in a team?

    Yes, but let us know if we can help you find a team.
  • What if I don't have a team in mind, or if we need more people in the team?

    You can note this when you sign up and we'll put you in touch with others in the same boat.
  • What do I need to compete?

    All you need is a laptop with tools for data analysis (there is no limitation on which software you use) and enthusiasm for data.
  • What are the rules of the competition?

    The rules are very simple:
    • No more than five students members per team.
    • Team members can come and go as they please but all work has to be done on-site. A steady supply of food, beverage, and candy make it more inviting to stay.
    • It's a competition, but a friendly one, so collaboration between teams is not only allowed but highly encouraged. Official ASA DataFestTM consultants (grad students, faculty, VIP consultants, etc.) will also be around throughout the weekend to help with any questions you might have. However you can't have outside help.
  • Do we have to stay the entire time?

    No. You may come and go as you please. However, you are not allowed to work on the project except while you are on ASA DataFestTM grounds, and at least 3 members of your team must attend the introduction.
  • What was DataFest 2014 like?

    It was great! You can read about it here.
  • What can I win?

    ASA student memberships, cash prizes, fame, glory, or some combination thereof... And you get a t-shirt!.
  • Where else is ASA DataFestTM happening?

    ASA DataFestTM is growing fast! This year the event is being held at 5 locations around the US with participation from 15 universities!
    • Duke University event: Duke, UNC, NCSU
    • UCLA event: UCLA, Pomona, Cal State LB, USC, UCR
    • Five Colleges event: Smith College, University of Massachusetts Amherst, Mt. Holyoke College, Amherst College, Hampshire College
    • Emory University
    • Purdue University
    many more coming... If you are interested in holding ASA DataFestTM at your institution, send an email to Mine Çetinkaya-Rundel to get more information on the event.
  • Other questions?

    Please don't hesitate to contact your local organizer with any questions:

Contact us

Questions regarding participation, organization, volunteering, and sponsorship can be directed to Mine Çetinkaya-Rundel.

You can also find us on Twitter and on Facebook.