USCOTS 2017 - Keynotes

  • With Chris Wild (University of Auckland)

    Abstract:

    "Oh Say, Can you see …?" But how then can we see?  And what can help us to see? We will start with our most basic graphics: dot plots, bar charts, and scatter plots. Taking this simple, plain, home-cooked fare as a base, we will start to add spices  – each on its own a simply-understood condiment. We will add colour, size, shape, transparency, zooming, identification and brushing, zooming, subsetting and movement. And perhaps most powerfully of all, we will exploit the simple idea of stepping though lists: lists of variables, of values of variables, of colours, palettes, shapes and more. Then we’ll stir it all up, apply heat and see what pops out. At least that’s the glimmering of the recipe as I start to cook. But how will it turn out? See you at the tasting!

  • With Rob Kass (Carnegie Mellon University)

    Abstract:

    People often think of statistics as a collection of particular data-analytic techniques, such as t-tests, chi-squared goodness-of-fit, linear regression, etc., which seem to bear little relation to each other and whose implementation is carried out through a series of somewhat arbitrary rules. But the field of statistics, as an academic discipline, strives for something much deeper, namely, the development and characterization of data collection and analysis methods according to well-defined principles, as a means of quantifying knowledge about underlying phenomena and rationalizing the learning and decision-making process. While many good ideas have helped modernize content and delivery of introductory statistics, I believe more effort should be directed toward giving students an appreciation of the ways the field of statistics makes progress. In other words, I think more can be done to narrow the gap between statistics education and statistical practice.

  • With Deb Nolan (University of California – Berkeley)

    Abstract:

    Statistics teaching typically has students work with data that are ready for them to apply a particular method to carry out a statistical analysis. This approach makes a lot of sense for most of our courses, but should not be our students’ only encounter with data. Working with raw data can lead to better statistical thinking skills and build confidence in our students that they are capable of handling new problems and data in the future. However, we need to expose the computational thinking involved as we wrangle with data and avoid treating this process as simply an ad hoc messy task. Furthermore, when we infuse statistical thinking earlier in the data-analysis lifecycle, students gain an alternative and important opportunity to learn. In this talk, we describe an integrated approach to teaching that incorporates computational and statistical thinking skills throughout the fuller data-analysis lifecycle, from data acquisition and cleaning to data organization and analysis to communicating results.

  • With Mine Çetinkaya-Rundel (Duke University)

    Abstract:

    What draws students to statistics? For some, the answer is mathematics, and for those a course in probability theory might be an attractive entry point. For others, their first exposure to statistics might be an applied introductory statistics course that focuses on methodology. This talk presents an alternative focus for a gateway to statistics: an introductory data science course focusing on data wrangling, exploratory data analysis, data visualization, and effective communication and approaching statistics from a model-based, instead of an inference-based, perspective. A heavy emphasis is placed on best practices for statistical computation, such as reproducibility and collaborative computing through literate programming and version control. I will discuss specific details of this course and how it fits into a modern undergraduate statistics curriculum as well as the success of the course in recruiting students to a statistics major.

  • With Jay Lehmann (College of San Mateo)

    Abstract:

    Many community college students come ill prepared for college work. In fact, at College of San Mateo, only about 13% of students progress through the two-course algebra sequence and pass statistics within 2 years. A small but growing percentage of community colleges have created a prestatistics course, which is an accelerated path for non-STEM students. By removing an exit point and preparing students solely for statistics, there is great potential for success. Instead of focusing on computations, my department emphasizes concepts, interpretations, and portions of descriptive statistics that students typically find challenging. We will discuss how to design and teach such a course as well as how to avoid potential problems.