ds-ed-enar2018

Slides and materials for the "Teaching Data Science at All Levels" invited session at ENAR 2018

Chair: Lance Waller, Emory University

Talks

• Mine Cetinkaya-Rundel (Duke + RStudio) - Data Science as a Gateway to Statistics - Slides

In this talk we will discuss a data science course designed to serve as a gateway to the discipline of statistics, the statistics major, and broadly to quantitative studies. The course is intended for an audience of Duke University students with little to no computing or statistical background, and focuses on data wrangling, exploratory data analysis, data visualization, and effective communication. Unlike most traditional introductory statistics courses, this course approaches statistics from a model-based perspective and introduces simulation-based and Bayesian inference later in the course. A heavy emphasis is placed on reproducibility (with R Markdown) and version control and collaboration (with git/GitHub). In this talk we will discuss in detail the course structure, logistics, and pedagogical considerations as well as give examples from the case studies used in the course. We will also share student feedback, assessment of the success of the course in recruiting students to the statistical science major, and our experience of growing the course from a small seminar course for first-year undergraduates to a larger course open to the entire undergraduate student body.

• Michael I. Love (UNC) - Teaching Data Science for Life Sciences - Slides

Biologists and biomedical researchers find their fields have rapidly advanced toward a state where experiments produce large data outputs they are not formally trained to evaluate. These large datasets must be processed, normalized and appropriately modeled before making scientific inferences. I will discuss various forums through which biologists and biomedical researches are updating their data science skills for working with and publishing on these data, and what informs their choice between collaborating with quantitative researchers and developing data science skills within the “wet lab”. I will also discuss considerations regarding statistical content of short courses and MOOCs available to these scientists to augment their data analytic skills for modern datasets

• Garrett Grolemund - Make Interactive Web Tutorials with learnr and R - Slides & demo

The learnr R package provides a new multimedia approach for teaching statistics and programming with R. With learnr, teachers can combine text, diagrams, videos, pacing cues, code exercises, multiple choice questions, automated grading software and more to create an interactive, selfpaced tutorial. Learnr is based on the familiar R Markdown format, which makes it easy to write learnr tutorials and to host them online. This talk will demonstrate the learnr package and examine several best practices for teaching in a multi-media, self paced format format, a format that may be new to many teachers.

The learnr R package and tutorials can be found at https://rstudio.github.io/learnr/.

• Frauke Kreuter (University of Maryland + University of Mannheim) - Teaching Survey and Data Science Outside Regular Classroom Settings - Slides

Over the last three years we experimented with various events and teaching activities to bring non-STEM students and practitioners up to speed on Survey and Data Science. This talk will highlight three approaches. First, the DataFest, a Data Analysis challenge designed for students to learn and apply data analysis skills during a weekend to create insights out of novel data. Second, the Advanced Data Analytics training provides training in Data Science for federal, state and local government program agency employees coleridgeinitiative.org. Third, an International Professional Training Program in Survey and Data Science survey-data-science.net. In all instances the the majority of the participants are neither computer scientists nor do they have any extensive training in statistics. We found the task-oriented approach with strong peer-to-peer elements to show remarkable successes in brining non-technical people of all ages into a situation where they can critically analyze complex data, and learn how to self-enhance their skillset.

Links

• Requesting Your Input on the Draft NIH Strategic Plan for Data Science input due 4/2/2018
• PDF Strategic Plan
• Comments from Jason Williams, Michael Love and others