Premium
Implications of the Data Revolution for Statistics Education
Author(s) -
Ridgway Jim
Publication year - 2016
Publication title -
international statistical review
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.051
H-Index - 54
eISSN - 1751-5823
pISSN - 0306-7734
DOI - 10.1111/insr.12110
Subject(s) - data science , big data , computer science , curriculum , interpretation (philosophy) , visualization , management science , sociology , data mining , engineering , pedagogy , programming language
Summary There has never been a more exciting time to be involved in statistics. Emerging data sources provide new sorts of evidence, provoke new sorts of questions, make possible new sorts of answers and shape the ways that evidence is used to influence policy, public opinion and business practices. Significant developments include open data, big data, data visualisation and the rise of data‐driven journalism. These developments are changing the nature of the evidence that is available, the ways in which it is presented and used and the skills needed for its interpretation. Educators should place less emphasis on small samples and linear models and more emphasis on large samples, multivariate description and data visualisation. Techniques used to analyse big data need to be taught. The increasing diversity of data usage requires deeper conceptual analysis in the curriculum; this should include explorations of the functions of modelling, and the politics of data and ethics. The data revolution can invigorate the existing curriculum by exemplifying the perils of biassed sampling, corruption of measures and modelling failures. Students need to learn to think statistically and to develop an aesthetic for data handling and modelling based on solving practical problems.