View in EDS HTML Full Text PDF Full Text

Hackathons in Statistics and Data Science Education and Experiences from ASA DataFest

Saved in:
Bibliographic Details
Title: Hackathons in Statistics and Data Science Education and Experiences from ASA DataFest
Language: English
Authors: Serveh Sharifi Far (ORCID 0000-0001-8403-6286), Vanda Inácio, Ozan Evkaya, Amanda Lenzi
Source: Teaching Statistics: An International Journal for Teachers. 2026 48(1):S13-S21.
Availability: Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us
Peer Reviewed: Y
Page Count: 9
Publication Date: 2026
Document Type: Journal Articles
Reports - Descriptive
Descriptors: Statistics Education, Data Science, Competition, Active Learning, Teamwork, Foreign Countries, Transfer of Training, Skill Development, Data Analysis, Visualization, Models, Communication Skills
Geographic Terms: United Kingdom
DOI: 10.1111/test.12404
ISSN: 0141-982X
1467-9639
Abstract: Data hackathons provide a platform for students to work with real and challenging data, allowing them to practice both technical and transferable skills, such as data wrangling, visualization, modeling, effective communication, and teamwork. This level of active learning is difficult to achieve in a typical classroom setting. In this article, we discuss the role and importance of hackathons in statistics and data science education. We also detail our experience as, to our knowledge, the only institution in the UK to have organized the ASA DataFest hackathon. We believe this contribution will interest colleagues who would like to organize an ASA DataFest or a similar event in their institutions.
Abstractor: As Provided
Entry Date: 2026
Accession Number: EJ1505790
Database: ERIC
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
    Url: https://content.ebscohost.com/cds/retrieve?content=AQICAHj0k_4E0hTGH8RJwT4gCJyBsGNe_WN95AvKlDbXJGqwxwEZPcfGN1ROd-I4yQxt2PXRAAAA4zCB4AYJKoZIhvcNAQcGoIHSMIHPAgEAMIHJBgkqhkiG9w0BBwEwHgYJYIZIAWUDBAEuMBEEDFC_u13t0rb5FREUQQIBEICBm6BfoGSi8K6-te-yn-WJVyI9A0uxDYRQqJXiIvLCGu9EVYDBdQDyXruW-yU1BjmLA0D4NP2pmoQhUKRQ9fcDrXMppIss7VoEMaLL7lGFjRMYb9mXbeYMlr1J26bQMff-5OeYQv4nkeH2_b_BukpNA2UeeWEHgyg18gpeVpR8T25WU7OLN3vzlNJU3Wg1-BHOar_mbBPdlGf-mqRv
Text:
  Availability: 1
  Value: <anid>AN0193755397;d8y02jun.26;2026May18.02:26;v2.2.500</anid> <title id="AN0193755397-1">Hackathons in Statistics and Data Science Education and Experiences from ASA DataFest </title> <p>Data hackathons provide a platform for students to work with real and challenging data, allowing them to practice both technical and transferable skills, such as data wrangling, visualization, modeling, effective communication, and teamwork. This level of active learning is difficult to achieve in a typical classroom setting. In this article, we discuss the role and importance of hackathons in statistics and data science education. We also detail our experience as, to our knowledge, the only institution in the UK to have organized the ASA DataFest hackathon. We believe this contribution will interest colleagues who would like to organize an ASA DataFest or a similar event in their institutions.</p> <p>Keywords: ASA DataFest; data competitions; data literacy; data science; teaching statistics; teamwork</p> <hd id="AN0193755397-2">INTRODUCTION</hd> <p>Hackathons are collaborative events where participants, typically professionals, students, and enthusiasts from diverse backgrounds, come together to engage in intensive problem‐solving. These events often span several hours to a few days, during which teams work to innovate and develop solutions to specific challenges. Hackathons serve as platforms not only for the practical application of theoretical knowledge but also for fostering creativity, teamwork, and rapid prototyping. The term "hackathon" is a combination of "hack" and "marathon". Hackathons originated in the late 1990s and early 2000s within the software development community. The first known hackathon took place in 1999, organized by OpenBSD to develop cryptographic software [[<reflink idref="bib29" id="ref1">29</reflink>]]. Today, hackathons are widespread in software development, often focusing on creating new applications, improving existing code, or solving technical challenges. These events are common in tech companies, startups, and universities. However, hackathons have also become popular across other disciplines, evolving beyond software development to encompass a wide range of fields. These include healthcare and medicine (e.g., MIT Hacking Medicine), business and finance (e.g., Barclays RepoHack), and engineering and hardware development (e.g., NASA Space Apps).</p> <p>In contemporary education, hackathons are increasingly recognized as a vital platform that bridges the gap between theoretical classroom instruction and practical real‐world application [[<reflink idref="bib13" id="ref2">13</reflink>]]. In computer science and software engineering education, these events emphasize the development of vital skills such as teamwork, presentation, programming, and domain knowledge, creativity, business acumen, and critical thinking [[<reflink idref="bib25" id="ref3">25</reflink>]]. A study on university students' participation in hackathons across different countries showed that intrinsic motivations influence their intention to participate, while extrinsic motivations play a key role in sustaining ongoing participation. Additionally, older students with more educational experience tend to have higher intentions to both begin and continue participating in these events [[<reflink idref="bib13" id="ref4">13</reflink>]]. Furthermore, findings confirm that the experience of participating in hackathons positively impacts individuals' confidence levels and reduces anxiety [[<reflink idref="bib27" id="ref5">27</reflink>]]. These events also promote peer learning and motivate participants to acquire new skills [[<reflink idref="bib21" id="ref6">21</reflink>]].</p> <p>Hackathons became popular in statistics and data science in the early 2010s, shortly after their emergence in software development and in parallel with the growth of big data and machine learning. Companies and academic institutions began hosting competitions focused on predictive modeling, data analysis, and algorithm development. These events have since been used by companies to identify talent and develop innovative solutions to complex, data‐driven challenges (e.g., [[<reflink idref="bib11" id="ref7">11</reflink>], [<reflink idref="bib22" id="ref8">22</reflink>]]). Hackathons have also become integral to data science education, providing hands‐on experience with real‐world datasets and problems that extend beyond typical classroom data analysis (e.g., [[<reflink idref="bib4" id="ref9">4</reflink>], [<reflink idref="bib14" id="ref10">14</reflink>]]). Hackathons in the data science industry and education, along with their examples, will be discussed in Section 2.</p> <p>In this paper, our contribution is twofold: we discuss the role and impact of hackathons in statistics and data science education, and we detail our experience at the University of Edinburgh, which, alongside Heriot‐Watt University, is the first institution in the UK and one of the few in Europe to have organized the American Statistical Association (ASA) DataFest hackathon. ASA DataFest is already well‐established in the USA and, to some extent, in Canada. We aim to encourage universities outside North America to consider organizing an ASA DataFest or a similar event.</p> <hd id="AN0193755397-3">HACKATHONS IN STATISTICS AND DATA SCIENCE AND THEIR ROLE IN EDUCATION</hd> <p>In this section, we first introduce a few significant hackathons in the data science industry, then discuss the impact of hackathons on data science education and present one prominent example of such events, ASA DataFest.</p> <hd id="AN0193755397-4">Hackathons in statistics and data science</hd> <p>Hackathons (also referred to as datathons, datafests, or codecamps) in statistics and data science have become pivotal events that bring together data enthusiasts, statisticians, and machine learning practitioners to tackle complex, real‐world problems through intensive, collaborative efforts. These events provide a platform for participants to apply their skills in data analysis, predictive modeling, and machine learning to large and complex datasets. The datasets are often provided by industry sponsors, government agencies, research institutions, or academic teams. By fostering innovation and creative problem‐solving, these types of hackathons play a crucial role in advancing the field of data science and providing participants with hands‐on experience that can lead to significant breakthroughs or new career opportunities. A few prominent hackathons in the Statistics and Data Science industry are introduced below:</p> <p>Women in Data Science (WiDS) Datathon: Since 2018, WiDS has provided a supportive environment for both beginners and experienced data scientists to participate in a hackathon, tackle critical real‐world problems with social impact, and connect with others in their community who share their interests in data science. The WiDS Datathon is part of the broader WiDS Conference initiative, which aims to inspire and educate women in data science fields, as well as promote diversity and inclusion within the data science community. This challenge attracts many data enthusiasts, particularly women, from around 100 countries to compete together. In the 2022 edition of this event, nearly 80% of the participants were women, compared to the usual less than 20% in other Kaggle competitions [[<reflink idref="bib30" id="ref11">30</reflink>]].</p> <p>The NFL (National Football League) big data bowl: This annual analytics competition, situated at the intersection of sports and data science, has challenged data scientists, sports analysts, and students since 2019 to develop innovative, data‐driven solutions to football‐related problems using real NFL player tracking data. Participants analyze complex datasets provided by the NFL, including information on player movement and game dynamics, to tackle challenges that enhance strategies, player performance, and overall understanding of the game through analytics [[<reflink idref="bib22" id="ref12">22</reflink>]].</p> <p>Kaggle competitions: These are online data science and machine learning challenges hosted on the Kaggle platform, which was established in 2010. They attract data scientists, statisticians, and machine learning enthusiasts from around the world to solve real‐world problems using large datasets and advanced analytical techniques, including machine learning and artificial intelligence [[<reflink idref="bib19" id="ref13">19</reflink>]]. The value of these competitions has been recognized in specific domains, such as forecasting [[<reflink idref="bib5" id="ref14">5</reflink>]], and studies have highlighted their pedagogical value in teaching machine learning [[<reflink idref="bib9" id="ref15">9</reflink>]].</p> <p>DrivenData competitions: This is an annual data science competition hosted by DrivenData since 2015 and sponsored by major organizations such as NASA, Microsoft, Meta AI, and the World Bank. It challenges participants to address significant societal problems in areas like public health, education, sustainability, and disaster response using data science. These competitions are typically conducted online and often run for extended periods, with participation ranging from a few dozen to several thousand individuals. DrivenData competitions emphasize the application of data science for social good, combining technical innovation with real‐world impact, and offer cash prizes to the winners [[<reflink idref="bib11" id="ref16">11</reflink>]].</p> <hd id="AN0193755397-5">The role of hackathons in education</hd> <p>Hackathons or datathons in statistics and data science education are typically competitions where students work on large and complex datasets over the course of a few hours or days to extract insights or answer specific questions. These challenges are independently organized by individual institutions [[<reflink idref="bib20" id="ref17">20</reflink>], [<reflink idref="bib31" id="ref18">31</reflink>]] or are part of collaborative events [[<reflink idref="bib4" id="ref19">4</reflink>]]. A prominent example of a major international event is the American Statistical Association DataFest [[<reflink idref="bib14" id="ref20">14</reflink>]], which we describe in the next subsection. Such hackathons can be powerful tools for enhancing student learning in different areas, for example:</p> <p></p> <ulist> <item> <emph>Multidisciplinary practice</emph> : In today's interconnected world, multidisciplinary education is essential for fostering innovation and helping students develop comprehensive perspectives on complex real‐world issues. Promoting collaboration across diverse fields could enrich learning experiences and enhance understanding of how various disciplines intersect [ [<reflink idref="bib23" id="ref21">23</reflink>] ]. Data science, as a multidisciplinary field, lies at the intersection of statistics, computer science, and domain expertise and critical thinking. Hackathons bridge the gap between such traditionally separate fields and offer excellent opportunities for students to work in multidisciplinary teams and tackle interdisciplinary problems. Additionally, introducing students to the multidisciplinarity of data science early in their academic journey, for example, via the use of real data, helps them understand how data can be used to address intricate real‐world problems [ [<reflink idref="bib7" id="ref22">7</reflink>] ] and equips them with invaluable career skills.</item> <p></p> <item> <emph>Working with real data</emph> : Experience working with real and challenging data is a key component of the undergraduate curriculum in statistics and data science. Guidelines published by the American Statistical Association [ [<reflink idref="bib3" id="ref23">3</reflink>] ] and the Royal Statistical Society [ [<reflink idref="bib26" id="ref24">26</reflink>] ] emphasize the importance of students becoming familiar with analyzing non‐textbook data and possessing the ability to communicate complex statistical methods to a non‐technical audience. A hackathon such as ASA DataFest provides an excellent opportunity for students to gain such experience [ [[<reflink idref="bib10" id="ref25">10</reflink>], [<reflink idref="bib16" id="ref26">16</reflink>]] ].</item> <p></p> <item> <emph>Active learning</emph> : Active learning is crucial in education as it engages students in the learning process, enhancing their understanding and retention of material. By encouraging students to participate actively through discussions, problem‐solving, and collaborative projects, active learning fosters critical thinking skills and promotes a deeper understanding of concepts. Research has shown that active learning strategies lead to improved academic performance in STEM students [ [<reflink idref="bib12" id="ref27">12</reflink>] ]. Hackathons foster active learning and enhance problem‐solving skills within a concentrated timeframe, offering experiences that are often difficult to replicate in traditional classroom settings due to constraints on time and resources.</item> <p></p> <item> <emph>Networking</emph> : During these events, typically professionals as consultants or mentors guide students in their teamwork analysis of the dataset, answer their questions, and provide insight into the data and analysis. These mentors are usually academic staff, PhD students, or industry professionals. Such interactions allow students to socialize with experts and build valuable professional connections [ [[<reflink idref="bib14" id="ref28">14</reflink>], [<reflink idref="bib21" id="ref29">21</reflink>]] ], in addition to the relationships they build with fellow participants.</item> <p></p> <item> <emph>Equity, diversity, and inclusion</emph> : These events have the potential to provide opportunities to encourage students from different backgrounds to explore and experiment in a specific field, in this case, data science, a subject that might seem enticing and perhaps intimidating to some. Organizers should aim to provide a supportive environment, assisted by peers and guided by academic and industry consultants, so students can gain confidence and skills regardless of their prior experience. There are examples of hackathons that have engaged participants from different backgrounds [ [<reflink idref="bib21" id="ref30">21</reflink>] ] and those that have been specifically designed to promote diversity and inclusion in organizations [ [<reflink idref="bib18" id="ref31">18</reflink>] ]. Notable examples in this area that encourage student participation include WiDS [ [<reflink idref="bib30" id="ref32">30</reflink>] ], which promotes sharing knowledge and learning data science among women, and Technica [ [<reflink idref="bib28" id="ref33">28</reflink>] ], which fosters learning and networking for underrepresented genders in technology.</item> </ulist> <hd id="AN0193755397-6">ASA DataFest</hd> <p>The ASA DataFest is an excellent example of a successful educational hackathon in data science. It is an annual competition founded at UCLA in 2011, which has rapidly grown and is now hosted by many prestigious colleges and universities, primarily across the USA and Canada. The ASA DataFest is a 48‐hour friendly competition where teams of up to five undergraduate students work over a weekend to find and share meaning in a large and complex dataset. The dataset and the analysis in this challenge are typically beyond the scope of what students encounter in their courses. During the event, students are supported by professional mentors who work in data science. At the end of the event, teams summarize their methods and findings in a short presentation to a panel of judges, competing for prizes in the categories of Best Insight, Best Visualization, and Best Use of Outside Data. For a more extensive introduction to the logistics and experiences of DataFest, we refer the reader to [[<reflink idref="bib6" id="ref34">6</reflink>], [<reflink idref="bib8" id="ref35">8</reflink>], [<reflink idref="bib14" id="ref36">14</reflink>]].</p> <p>Since DataFest has become well‐known and widely embraced, there are several studies that have explored DataFest as a research opportunity to examine how students learn in such environments and identify strategies for enhancing their learning experiences. For instance, one study discusses methods to prepare less experienced students for participation in DataFest, focusing on building their confidence and skills [[<reflink idref="bib10" id="ref37">10</reflink>]]. Another study investigates how teams at DataFest effectively apply multidisciplinary tools and domain knowledge in various ways to approach the DataFest tasks productively [[<reflink idref="bib15" id="ref38">15</reflink>]]. DataFest was used in another study as an effective platform to investigate key components of re‐conceptualizing the teaching of undergraduate statistics and data science courses, particularly in the areas of teamwork, data ethics, and designing research questions [[<reflink idref="bib24" id="ref39">24</reflink>]]. These insights highlight the educational potential of DataFest in fostering collaborative learning and skill development among students from diverse backgrounds.</p> <hd id="AN0193755397-7">ASA DATAFEST AT EDINBURGH</hd> <p>In this section, we share our experience as the only UK institution, alongside Heriot‐Watt University, and one of the few in Europe, to organize ASA DataFest. We briefly mention our previous experiences hosting this event in a fully online format before detailing the in‐person event we organized in 2024.</p> <hd id="AN0193755397-8">Online experience in 2020 and 2021</hd> <p>The School of Mathematics at the University of Edinburgh organized this event in a limited format twice before, in 2020 and 2021. Due to the pandemic restrictions at the time, both events took place entirely online, using platforms such as Slack, Zoom, and Gather for communication between students and mentors. The 2020 event was relatively small in scale, while the 2021 event had a larger participation, with 36 groups of students from 10 different schools across the University of Edinburgh and Heriot‐Watt University.</p> <p>In the 2021 ASA DataFest competition, the data was provided by the Rocky Mountain Poison Control Center, which aimed to identify patterns of prescription drug misuse using data from an online survey of compensated participants [[<reflink idref="bib2" id="ref40">2</reflink>]]. Their objectives included uncovering demographic profiles associated with specific drug categories, identifying frequently co‐occurring drug combinations, and predicting future cases of drug misuse. In our event, we instructed the participants to submit a 6‐minute video and a one‐page summary at the end of the event, outlining the primary questions investigated, the methods employed, and a brief summary of their findings. Judges reviewed the submissions independently, assigned scores, and deliberated via Zoom to determine the final winners. The award ceremony was also conducted on Zoom.</p> <hd id="AN0193755397-9">In‐person experience in 2024</hd> <p>After a 2‐year hiatus, we organized the ASA DataFest 2024 as an in‐person event in Edinburgh from 22 to 24 March, inviting all undergraduate students from the University of Edinburgh and Heriot‐Watt University with an interest in data analytics to join. A total of 82 students in 20 teams from 10 different schools (including Mathematics, Informatics, Geosciences, Business, Psychology, and Social and Political Science) participated and collaborated over the weekend. Twelve consultants, including academic staff, PhD students, and data scientists from the industry, volunteered as mentors to guide participants during the event. We also had four judges, two from the industry and two from the School of Mathematics at the University of Edinburgh, who assessed the final presentations. Recruiting sufficient volunteer consultants and judges can be challenging. While we primarily relied on personal contacts, adopting a more proactive approach, such as reaching out through mailing lists, could also be helpful.</p> <p>To promote equity, diversity, and inclusion, we implemented several measures that we also recommend to others organizing similar events. First, we assembled a diverse organizing, mentoring, and judging team, representing a mix of genders, races, and academic disciplines, to provide relatable role models for participants. Second, we advertised the event across relevant schools, providing detailed information to encourage participation from a diverse audience. Third, we published a clear code of conduct on our website to establish expectations for respectful and inclusive behavior. Finally, we ensured the venue was accessible to individuals with disabilities and that there were sufficient spaces for participants to relax or seek support during the event. To further enhance these efforts in the future, we plan to emphasize in our advertising that the event is open to anyone with an interest in data, regardless of their academic background or prior experience. Additionally, showcasing diversity and sharing participant testimonials in our promotional materials could further encourage broad and inclusive participation.</p> <hd id="AN0193755397-10">Logistics</hd> <p>The ASA requires institutions intending to host a DataFest to register by late January or early February. Around mid‐January, a virtual ASA DataFest information town hall takes place, for which registration is also required for attendees. The ASA establishes a timeframe for when the event should take place, typically between mid‐March and the end of April. Each participating university or college can choose a weekend within this period to host their DataFest. Closer to the event, the raw data and associated codebooks are provided to the organizers. The ASA also facilitates communication between the organizers and the data providers, which is extremely helpful in understanding the data and the challenge. It is crucial for organizers to remind students not to disclose the specific data topic for that year's DataFest online before the end of April, as keeping this information confidential helps maintain an element of surprise for participants at each university event. To organize a successful ASA DataFest, it is essential to carefully plan timing, promotion, venue, catering, and budget.</p> <p>We chose March 22–24 for our event since taught lectures in the second semester at the University of Edinburgh concluded in the first week of April 2024, and we wanted to organize our event before the end of the lecture period. This ensured that students were still on campus daily and that the event would not interfere with their exam revision period. After selecting the event's weekend, we began advertising it to undergraduate students from most schools at the University of Edinburgh and the Department of Actuarial Mathematics and Statistics at Heriot‐Watt University in February. Interested students could sign up as a team of up to five or individually to be grouped later by completing an online form available on the website we created for the event. Due to space and budget constraints, we capped the number of participants at 85. We monitored the list of enrolled students and closed the registration before the number of participants exceeded the set limit.</p> <p>The choice of venue for an event like DataFest is crucial, as it must offer an adequate space for students to collaborate in groups and interact with their teammates as well as other teams and mentors. The environment should be bright, well‐ventilated, and conducive to productivity, allowing students to work effectively. Additionally, it should feature social and eating areas and preferably some outdoor space where participants can take walks or grab extra food, and perhaps a quiet room for focused work, enhancing their overall experience. Our venue was a workshop‐style teaching room at the university that met these requirements and was available to use between 9 am and 9 pm. For catering, we used the university's regular suppliers to order lunches, dinners, and refreshments. In addition to onsite communications at the venue during the event, we also created a Microsoft Teams class for the event and added all participants and mentors. Different channels were used for chatting and discussions. Microsoft Teams was also the platform where we shared the data with students and collected their submission files.</p> <p>Budget planning is crucial for the successful organization of such an event, ensuring all necessary expenses are covered without exceeding available funds. In our experience, the main expenses were catering and venue costs, and providing prizes for members of the winning teams. Additionally, we provided name badges and promotional items to participants (e.g., pens, pencils, notebooks, and stickers), some of which were gifted by our sponsors. Applying for funding both within and outside the university is a possible way to cover costs; however, funding opportunities through conventional science funding agencies may be limited for events like this.</p> <hd id="AN0193755397-11">The dataset and its challenges</hd> <p>The dataset for the 2024 edition of DataFest was provided by CourseKata, a platform that develops and publishes a series of e‐books for introductory statistics and data science courses [[<reflink idref="bib2" id="ref41">2</reflink>]]. The developers of CourseKata are interested in improving their online learning resources by examining students' interactions with their e‐books. The challenge provided to participants was to analyze interaction data collected from 11 universities, 48 classes, and over 1600 students, and to offer suggestions for enhancing the student learning experience in statistics at CourseKata. A full dataset, along with a random sample of it, was made available by ASA to the participating institutions; while the size of the full dataset was about 1.56 GB, the subset was more manageable, with a size of around 250 MB. This clearly corroborates the claim that such an event gives students the opportunity to work with data of a complexity they have not encountered before in their coursework.</p> <p>The data providers also supplied the students with a codebook, a variables list file, and a document explaining the challenge and the data files, along with suggestions on "how to get started". The students were tasked with analyzing the data and offering recommendations to improve the CourseKata platform's support for students learning statistics. These recommendations could be directed to the CourseKata team, focusing on identifying patterns of student engagement (e.g., commonly revisited sections, the order in which chapters are read), detecting learning challenges and successes to highlight content that might need improvement or could serve as an example of effective teaching, or suggesting potential new features. Alternatively, suggestions could target students or instructors, highlighting effective learning strategies identified in the data or underutilized approaches that could enhance learning outcomes.</p> <hd id="AN0193755397-12">Workflow during the weekend</hd> <p>Following registration from 5 to 6 pm, the event kicked off on Friday at 6 pm by releasing the data to students on the MS Teams class, presenting them with a brief overview of the event, and watching an introductory video recorded by the CourseKata developers which was provided to participating institutions by the ASA. The main goal for students in the rest of the evening was to access the dataset in their programming tool of choice, mainly R or Python, explore it, and plan their analysis.</p> <p>On Saturday, teams were advised to choose the main questions they wanted to focus on, decide on the methods to answer those questions, and begin analyzing the data. This is the second and most crucial day of the event, during which the bulk of the analysis is expected to be done. We note that, unsurprisingly, deciding which questions to answer was notoriously difficult for some teams, as this represents a shift from the paradigm they are mostly used to: formulating answers to well‐posed questions. Participants were advised to narrow down their questions to specific problems, as time was limited, and focused issues are easier to address. On Sunday, the last day of the event, we suggested that teams spend the morning finalizing their data analysis and interpreting the results, and spend the afternoon preparing their presentations, which had to be submitted by 4 pm. The presentation session started shortly after 4 p.m. and lasted about 2 hours. The judges' discussion followed and took approximately 30 min. The event concluded with an award ceremony where the winners were announced and received their prizes. For a detailed plan of this event, please see [[<reflink idref="bib17" id="ref42">17</reflink>]].</p> <hd id="AN0193755397-13">Presentations and evaluation</hd> <p>Participants were required to deliver their team's analysis in a five‐minute presentation, with the option to use a slide deck. Due to time constraints, the presentations were split into two separate sessions. In each session, two judges, one from academia and one from industry, observed and evaluated each presentation. The judges were provided with a printed table to record their comments on each presentation, along with their assessments for potential rankings or awards in the designated categories. After each presentation, the judges engaged in a brief discussion with the students and asked follow‐up questions. Later, the judges from both sessions convened to determine the final winners. Prizes were awarded to six teams in the categories of Best Insight, Best Visualization, Best Use of Outside Data, and an additional category we introduced for our event, Judges' Pick.</p> <p>The work carried out by the different teams was quite diverse. We briefly highlight the projects of two of the winning teams, respectively, in the categories of Best Insight and Judges' Pick:</p> <p>Shepherd's Pi team: This group aimed to explain the impact of early chapter engagement on the success of students. They first observed that the mean score of the End‐of‐Chapter (EOC) review questions for the first three chapters of a course was positively correlated with the EOC review questions score for the last three chapters. The data from the students in the database were divided into three groups: Bored (often idle and not engaged), Rushing (rarely idle and not engaged), and Diligent (rarely idle and engaged). Then the group used a support vector machine to classify students among these three groups depending on path patterns, that is, the order in which students read the chapters. The classifier was able to distinguish path patterns associated with students achieving high EOC scores. Based on these results, the group recommended improved teaching methods, such as regular session recaps in cases where foundational knowledge is lacking, reinforcing core concepts of the course throughout, and restricting access to later chapters to discourage disengagement or inactivity.</p> <p>Chameleons team: This group aimed to investigate which variables in the dataset had the most impact on student success, as measured by the EOC score, while controlling for individual differences between students and institutions. The group analysis was based on a mixed effects model applied to the student engagement data from three online Statistics and Data Science textbooks. A latent class analysis was then used to identify hidden groups and further investigate the effect of different types of learning methods on these groups (e.g., interactive media, written textbooks) and how these methods influence students' success. They found that students who accessed the material late at night did not perform well and recommended implementing a "wellbeing alert" to remind students to take breaks when engaging with the textbooks past midnight. They also provided specific suggestions to CourseKata regarding the organization of materials, such as ensuring that chapters build on one another.</p> <hd id="AN0193755397-14">Anticipated benefits</hd> <p>As a data hackathon, ASA DataFest presents an opportunity to enhance students' learning across several dimensions, as discussed in Section 2.2. Additionally, participants from different schools could become advocates for data literacy within their respective schools, promoting its importance and encouraging others to engage in similar events or courses. This advocacy can extend beyond academia into their future careers, fostering data‐informed decision‐making practices. Moreover, we hope that such events ignite innovative research projects and cultivate collaborative relationships between faculty and students, contributing to the university's academic excellence and research output. By fostering a culture of data inquiry and collaboration, DataFest can play a pivotal role in shaping a generation of data‐skilled professionals.</p> <hd id="AN0193755397-15">CONCLUDING REMARKS</hd> <p>We highlighted some key hackathons in statistics and data science and discussed the role of data hackathons in education. Then we shared our experience as, to our knowledge, the only UK institution, along with Heriot‐Watt University, to have organized ASA DataFest. Organizing this event provided an enriching experience, allowing us to engage with both students and professional data scientists throughout the weekend. The interactions involved discussions on data analysis, modeling, and coding, as well as informal chats during breaks and meals. As we emphasized before, careful planning is crucial for the success of an extended event like this. Adequate attention must be given to the venue, catering, and the technical and scientific support provided by staff to ensure a rewarding experience for all involved.</p> <p>After the event, we collected anonymous feedback from participants through an online form, which was completed by approximately 10% of them. The questions given to participants were: "What did you like about the event?", "What would you change about the event?", "Would you recommend participating in this event to other students in the future?", and "Any additional comments?". The respondents all stated that they would recommend participating in this event to other students in the future. They described the event as "engaging and fun", "a great joint experience for students and staff", and a "good chance to socialise with people" at a "nice venue" with "different categories of prizes". They appreciated the opportunity to "learn a lot" and "apply the knowledge" from their courses to a "challenging data set", expressing that they "hope to do it regularly". Additionally, they described the involved staff and consultants as "supportive" who "provided useful help" and "words of encouragement".</p> <p>Our aim is to establish ASA DataFest as an annual event in Edinburgh. We further hope that by sharing our experience, we can encourage colleagues at institutions outside North America, particularly in the UK, to host an ASA DataFest event. While we acknowledge that each institution will face unique challenges, we believe Section 3 of this paper provides a clear overview of the main steps involved. Additionally, consulting the ASA's advice on hosting a DataFest, such as <emph>DataFest in a Box</emph> [[<reflink idref="bib1" id="ref43">1</reflink>]], and attending their initial virtual information meeting could serve as valuable starting points for organizing the event. Given that <emph>Significance</emph> magazine is now a joint venture of the American Statistical Association, the Royal Statistical Society, and the Statistical Society of Australia, perhaps in the not‐too‐distant future, we could see the emergence of a joint DataFest as well. One approach to moving toward this goal could be running the event locally in different universities, allowing institutions to gain experience and build interest.</p> <hd id="AN0193755397-16">ACKNOWLEDGMENTS</hd> <p>We acknowledge the ASA for coordinating DataFest, along with our event sponsors: the School of Mathematics and the Centre for Statistics at the University of Edinburgh, the Department of Actuarial Mathematics and Statistics at Heriot‐Watt University, Maxwell Institute for Mathematical Sciences, Bayes Centre, International Centre for Mathematical Sciences, and the Royal Statistical Society. We also thank Mine Çetinkaya‐Rundel for organizing the 2020 and 2021 editions of ASA DataFest in Edinburgh.</p> <ref id="AN0193755397-17"> <title> REFERENCES </title> <blist> <bibl id="bib1" idref="ref43" type="bt">1</bibl> <bibtext> American Statistical Association. ASA DataFest in a Box. 2025 available at https://ww2.amstat.org/education/datafest/datafestinabox.cfm.</bibtext> </blist> <blist> <bibl id="bib2" idref="ref40" type="bt">2</bibl> <bibtext> American Statistical Association. Previous DataFests. 2025 available at https://ww2.amstat.org/education/datafest/previous.cfm.</bibtext> </blist> <blist> <bibl id="bib3" idref="ref23" type="bt">3</bibl> <bibtext> American Statistical Association Undergraduate Guidelines Workgroup. 2014 curriculum guidelines for undergraduate programs in statistical science. 2014 available at https://<ulink href="http://www.amstat.org/docs/default‐source/amstat‐documents/guidelines2014‐11‐15.pdf">www.amstat.org/docs/default‐source/amstat‐documents/guidelines2014‐11‐15.pdf</ulink>.</bibtext> </blist> <blist> <bibl id="bib4" idref="ref9" type="bt">4</bibl> <bibtext> C. Anslow, J. Brosz, F. Maurer, and M. Boyes, "Datathons: An experience report of data hackathons for data science education," Proceedings of the 47th ACM technical symposium on computing science education, ser. SIGCSE '16, Association for Computing Machinery, New York, NY, USA, 2016, pp. 615–620. https://doi.org/10.1145/2839509.2844568.</bibtext> </blist> <blist> <bibl id="bib5" idref="ref14" type="bt">5</bibl> <bibtext> C. S. Bojer and J. P. Meldgaard, Kaggle forecasting competitions: An overlooked learning opportunity, Int. J. Forecast.37 (2021), no. 2, 587–603. https://doi.org/10.1016/j.ijforecast.2020.07.007.</bibtext> </blist> <blist> <bibl id="bib6" idref="ref34" type="bt">6</bibl> <bibtext> M. Çetinkaya‐Rundel, DataFest Shows Spike in Growth, Provides Immersive Experience, American Statistical Association, 2017 available at https://stattrak.amstat.org/2017/%2009/01/datafestspike/.</bibtext> </blist> <blist> <bibl id="bib7" idref="ref22" type="bt">7</bibl> <bibtext> M. Çetinkaya‐Rundel and V. Ellison, A fresh look at introductory data science, J. Stat. Data Sci. Educ.29 (2020), no. sup1, S16–S26. https://doi.org/10.1080/10691898.2020.1804497.</bibtext> </blist> <blist> <bibl id="bib8" idref="ref35" type="bt">8</bibl> <bibtext> M. Çetinkaya‐Rundel and D. Stangl, Taking a chance in the classroom: A celebration of data, Chance26 (2013), no. 3, 43–46. https://doi.org/10.1080/09332480.2013.845451.</bibtext> </blist> <blist> <bibl id="bib9" idref="ref15" type="bt">9</bibl> <bibtext> W. Chow, "A Pedagogy That Uses a Kaggle Competition for Teaching Machine Learning: An Experience Sharing," 2019 IEEE International Conference on Engineering, Technology and Education, IEEE, Yogyakarta, IN, 2019, pp. 1–5. https://doi.org/10.1109/TALE48000.2019.9226005.</bibtext> </blist> <blist> <bibtext> N. M. Dalzell and C. Evans, Increasing student access to and readiness for statistical competitions, J. Stat. Data Sci. Educ.31 (2023), no. 3, 258–263. https://doi.org/10.1080/26939169.2023.2167750.</bibtext> </blist> <blist> <bibtext> DrivenData. DrivenData competitions. 2024 available at https://<ulink href="http://www.drivendata.org/competitions/">www.drivendata.org/competitions/</ulink>.</bibtext> </blist> <blist> <bibtext> S. Freeman, S. L. Eddy, M. McDonough, M. K. Smith, N. Okoroafor, H. Jordt, and M. P. Wenderoth, Active learning increases student performance in science, engineering, and mathematics, Proc. Natl. Acad. Sci.111 (2014), no. 23, 8410–8415. https://doi.org/10.1073/pnas.1319030111.</bibtext> </blist> <blist> <bibtext> M. B. Garcia, Hackathons as extracurricular activities: Unraveling the motivational orientation behind student participation, Comput. Appl. Eng. Educ.30 (2022), no. 6, 1903–1918. https://doi.org/10.1002/cae.22564.</bibtext> </blist> <blist> <bibtext> R. Gould, DataFest: Celebrating Data in the Data Deluge, Sustainability in Statistics Education. Proceedings of the Ninth International Conference on Teaching Statistics (ICOTS9, July 2014), 2014, Katie Makar and Bruno de Sousa and Robert Gould, eds, 1‐4, International Association for Statistical Education International Statistical Institute, Flagstaff, Arizona, USA. https://iase‐web.org/icots/9/proceedings/pdfs/ICOTS9_4F2_GOULD.pdf</bibtext> </blist> <blist> <bibtext> T. Higgins, J. M. Karch, and J. K. Hammerman, "Studying Interdisciplinary Thinking About Complex Real‐World Data at DataFest," IASE 2023 Satellite Conference Proceedings: Fostering Learning in Statistics and Data Science, 2023, International Association for Statistical Education, Toronto, Canada, 2023https://par.nsf.gov/biblio/10458486.</bibtext> </blist> <blist> <bibtext> N. J. Horton, Challenges and opportunities for statistics and statistical education: Looking back, looking forward, Am. Stat.69 (2015), no. 2, 138–145. https://doi.org/10.1080/00031305.2015.1032435.</bibtext> </blist> <blist> <bibtext> DataFest 2024 at EDI. 2024 available at https://edi-datafest.netlify.app/schedule/.</bibtext> </blist> <blist> <bibtext> M. Htun, Promoting diversity and inclusion through engagement: The APSA 2018 hackathon, PS: Political Sci.52 (2019), no. 4, 677–683. https://doi.org/10.1017/S1049096519000593.</bibtext> </blist> <blist> <bibtext> Kaggle. Kaggle competitions. 2024 available at https://<ulink href="http://www.kaggle.com/competitions">www.kaggle.com/competitions</ulink>.</bibtext> </blist> <blist> <bibtext> K. Kuter and C. Wedrychowicz, Hosting a data science hackathon with limited resources, Stat10 (2021, e338 sta4.338), no. 1, e338. https://doi.org/10.1002/sta4.338.</bibtext> </blist> <blist> <bibtext> A. Nandi and M. Mandernach, "Hackathons as an informal learning platform," Proceedings of the 47th ACM technical symposium on computing science education, ser. SIGCSE '16, Association for Computing Machinery, Memphis, Tennessee, USA, 2016, pp. 346–351. https://doi.org/10.1145/2839509.2844590.</bibtext> </blist> <blist> <bibtext> National Football League (NFL). Big data bowl. 2024 available at https://operations.nfl.com/gameday/analytics/big-data-bowl/.</bibtext> </blist> <blist> <bibtext> National Math and Science Initiative (NMSI). Stem education beyond silos: Encouraging cross‐disciplinary collaboration. 2023 available at https://<ulink href="http://www.nms.org/Resources/Newsroom/Blog/2023/December‐2023/STEM‐Education‐Beyond‐Silos‐Encouraging‐Cross‐disc.aspx">www.nms.org/Resources/Newsroom/Blog/2023/December‐2023/STEM‐Education‐Beyond‐Silos‐Encouraging‐Cross‐disc.aspx</ulink>.</bibtext> </blist> <blist> <bibtext> J. Noll and M. Tackett, Insights from DataFest point to new opportunities for undergraduate statistics courses: Team collaborations, designing research questions, and data ethics, Teach. Stat.45 (2023), no. S1, S5–S21. https://doi.org/10.1111/test.12345.</bibtext> </blist> <blist> <bibtext> J. Porras, A. Knutas, J. Ikonen, A. Happonen, J. Khakurel, and A. Herala, "Code Camps and Hackathons in Education ‐ Literature Review and Lessons Learned," Hawaii International Conference on System Sciences, University of Hawaii at Manoa, Hawaii, USA, 2019https://api.semanticscholar.org/CorpusID:102352264.</bibtext> </blist> <blist> <bibtext> Royal Statistical Society. Master's (level 7) standards in statistics. 2017 available at https://rss.org.uk/RSS/media/File-library/Membership/Prof%20Dev/rss-level7-standards.pdf.</bibtext> </blist> <blist> <bibtext> M. Rys, A. M. Górska, and h. P. Korzynski, Navigating the hackathon: Exploring participant experience, confidence and anxiety, Eur. J. Educ.59 (2024), no. 3, e12656. https://doi.org/10.1111/ejed.12656.</bibtext> </blist> <blist> <bibtext> Technica. Technica. https://gotechnica.org/2024.</bibtext> </blist> <blist> <bibtext> The OpenBSD Project. OpenBSD hackathons. 2024 available at https://<ulink href="http://www.openbsd.org/hackathons.html">www.openbsd.org/hackathons.html</ulink>.</bibtext> </blist> <blist> <bibtext> Women in Data Science (WiDS). WiDS datathon. 2024https://<ulink href="http://www.widsworldwide.org/about/">www.widsworldwide.org/about/</ulink>.</bibtext> </blist> <blist> <bibtext> K. K. F. Yuen and A. O. M. Wong, "Designing an Effective Hackathon Via University‐Industry Collaboration for Data Science Education," 2021 IEEE international conference on engineering, technology education (TALE), IEEE, Wuhan, China, 2021, pp. 1–6. https://doi.org/10.1109/TALE52509.2021.9678826.</bibtext> </blist> </ref> <aug> <p>By Serveh Sharifi Far; Vanda Inácio; Ozan Evkaya and Amanda Lenzi</p> <p>Reported by Author; Author; Author; Author</p> </aug> <nolink nlid="nl1" bibid="bib29" firstref="ref1"></nolink> <nolink nlid="nl2" bibid="bib13" firstref="ref2"></nolink> <nolink nlid="nl3" bibid="bib25" firstref="ref3"></nolink> <nolink nlid="nl4" bibid="bib27" firstref="ref5"></nolink> <nolink nlid="nl5" bibid="bib21" firstref="ref6"></nolink> <nolink nlid="nl6" bibid="bib11" firstref="ref7"></nolink> <nolink nlid="nl7" bibid="bib22" firstref="ref8"></nolink> <nolink nlid="nl8" bibid="bib14" firstref="ref10"></nolink> <nolink nlid="nl9" bibid="bib30" firstref="ref11"></nolink> <nolink nlid="nl10" bibid="bib19" firstref="ref13"></nolink> <nolink nlid="nl11" bibid="bib20" firstref="ref17"></nolink> <nolink nlid="nl12" bibid="bib31" firstref="ref18"></nolink> <nolink nlid="nl13" bibid="bib23" firstref="ref21"></nolink> <nolink nlid="nl14" bibid="bib26" firstref="ref24"></nolink> <nolink nlid="nl15" bibid="bib10" firstref="ref25"></nolink> <nolink nlid="nl16" bibid="bib16" firstref="ref26"></nolink> <nolink nlid="nl17" bibid="bib12" firstref="ref27"></nolink> <nolink nlid="nl18" bibid="bib18" firstref="ref31"></nolink> <nolink nlid="nl19" bibid="bib28" firstref="ref33"></nolink> <nolink nlid="nl20" bibid="bib15" firstref="ref38"></nolink> <nolink nlid="nl21" bibid="bib24" firstref="ref39"></nolink> <nolink nlid="nl22" bibid="bib17" firstref="ref42"></nolink>
Header DbId: eric
DbLabel: ERIC
An: EJ1505790
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Hackathons in Statistics and Data Science Education and Experiences from ASA DataFest
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Serveh+Sharifi+Far%22">Serveh Sharifi Far</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0001-8403-6286">0000-0001-8403-6286</externalLink>)<br /><searchLink fieldCode="AR" term="%22Vanda+Inácio%22">Vanda Inácio</searchLink><br /><searchLink fieldCode="AR" term="%22Ozan+Evkaya%22">Ozan Evkaya</searchLink><br /><searchLink fieldCode="AR" term="%22Amanda+Lenzi%22">Amanda Lenzi</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Teaching+Statistics%3A+An+International+Journal+for+Teachers%22"><i>Teaching Statistics: An International Journal for Teachers</i></searchLink>. 2026 48(1):S13-S21.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 9
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2026
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Descriptive
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Statistics+Education%22">Statistics Education</searchLink><br /><searchLink fieldCode="DE" term="%22Data+Science%22">Data Science</searchLink><br /><searchLink fieldCode="DE" term="%22Competition%22">Competition</searchLink><br /><searchLink fieldCode="DE" term="%22Active+Learning%22">Active Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Teamwork%22">Teamwork</searchLink><br /><searchLink fieldCode="DE" term="%22Foreign+Countries%22">Foreign Countries</searchLink><br /><searchLink fieldCode="DE" term="%22Transfer+of+Training%22">Transfer of Training</searchLink><br /><searchLink fieldCode="DE" term="%22Skill+Development%22">Skill Development</searchLink><br /><searchLink fieldCode="DE" term="%22Data+Analysis%22">Data Analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Visualization%22">Visualization</searchLink><br /><searchLink fieldCode="DE" term="%22Models%22">Models</searchLink><br /><searchLink fieldCode="DE" term="%22Communication+Skills%22">Communication Skills</searchLink>
– Name: Subject
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22United+Kingdom%22">United Kingdom</searchLink>
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1111/test.12404
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 0141-982X<br />1467-9639
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Data hackathons provide a platform for students to work with real and challenging data, allowing them to practice both technical and transferable skills, such as data wrangling, visualization, modeling, effective communication, and teamwork. This level of active learning is difficult to achieve in a typical classroom setting. In this article, we discuss the role and importance of hackathons in statistics and data science education. We also detail our experience as, to our knowledge, the only institution in the UK to have organized the ASA DataFest hackathon. We believe this contribution will interest colleagues who would like to organize an ASA DataFest or a similar event in their institutions.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2026
– Name: AN
  Label: Accession Number
  Group: ID
  Data: EJ1505790
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1505790
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1111/test.12404
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 9
        StartPage: S13
    Subjects:
      – SubjectFull: Statistics Education
        Type: general
      – SubjectFull: Data Science
        Type: general
      – SubjectFull: Competition
        Type: general
      – SubjectFull: Active Learning
        Type: general
      – SubjectFull: Teamwork
        Type: general
      – SubjectFull: Foreign Countries
        Type: general
      – SubjectFull: Transfer of Training
        Type: general
      – SubjectFull: Skill Development
        Type: general
      – SubjectFull: Data Analysis
        Type: general
      – SubjectFull: Visualization
        Type: general
      – SubjectFull: Models
        Type: general
      – SubjectFull: Communication Skills
        Type: general
      – SubjectFull: United Kingdom
        Type: general
    Titles:
      – TitleFull: Hackathons in Statistics and Data Science Education and Experiences from ASA DataFest
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Serveh Sharifi Far
      – PersonEntity:
          Name:
            NameFull: Vanda Inácio
      – PersonEntity:
          Name:
            NameFull: Ozan Evkaya
      – PersonEntity:
          Name:
            NameFull: Amanda Lenzi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 09
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 0141-982X
            – Type: issn-electronic
              Value: 1467-9639
          Numbering:
            – Type: volume
              Value: 48
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Teaching Statistics: An International Journal for Teachers
              Type: main
ResultId 1