Page 48 - Special Topic Session (STS) - Volume 3

STS515 Alison L. G. et al.

Evolving statistics education for a data science
world
Alison L. Gibbs, Sotirios Damouras
University of Toronto, Canada

Abstract
Statistics is undergoing a period of profound transformation, disrupting its
practice, research, and teaching. The ubiquity of data and the data-driven
scientific paradigm have fundamentally changed the way we analyse data and
have placed new demands on statistics education. There is a recognised
urgency for undergraduate statistics curricula to include the development of
software and programming skills for working with data, and systematic efforts
are already under way to address this. Beyond ensuring the acquisition of
practical skills, this transition period offers the opportunity to realign the
principles and focus of statistics education for the future. In particular,
students need to develop new traits and attitudes that will support their
ongoing academic and professional development in the age of data science.
We propose a set of qualities and higher-order skills that we believe are
essential for our graduating students to remain relevant during the evolution
of Statistics, and we describe practical strategies for fostering these in the
context of introductory courses in statistical reasoning and data science at our
institution.

Keywords
statistics education; introductory course; adaptive expertise; lifelong learning

1. Introduction
The ongoing “Data Revolution,” fuelled by the increasing availability of
both data and computation, is transforming Statistics. This revolution has
created a new land of opportunity, what Cobb (2015) aptly describes as “the
valuable territory [of] the science of data.” Statistics used to have almost
exclusive rights on areas concerned with extracting knowledge from data, but
now finds itself contending with new fields such as Machine Learning, Data
Mining, and Analytics. While realizing that this territory is too expansive to
claim sole ownership, our discipline is trying to identify its place and purview
in this new environment. There is a commonly expressed understanding that
the best way to ensure Statistics does not become marginalized is to engage
with other disciplines. The American Statistical Association (ASA) issued a
statement on the role of Statistics in Data Science (van Dyk et al., 2015) calling
for a “sustained and substantial collaborative effort” in which “statisticians

37 | I S I W S C 2 0 1 9