ENBIS-18 in Nancy

2 – 25 September 2018; Ecoles des Mines, Nancy (France) Abstract submission: 20 December 2017 – 4 June 2018

George Box Award: Ron Kenett. Award Talk on "The Real Work of Data Science: How to Turn Data into Information, Better Decisions, and Stronger Organizations"

3 September 2018, 16:40 – 17:40

Abstract

Submitted by
Authors
Ron S. Kenett (KPA Ltd., Raanana, Samuel Neaman Institute, Technion, Haifa and Institute for Drug Development, The Hebrew University, Jerusalem)
Abstract
In 1962, John Tukey called for a reformation of academic statistics. In a famous paper titled “The Future of Data Analysis,” he pointed to the existence of an as-yet unrecognized science, whose subject was learning from data. He called it “data analysis.” In 1997, C. F. Jeff Wu, upon his inauguration lecture as Carver Professor of Statistics at University of Michigan, presented a talk titled “Statistics = Data Science?” in which he advocated that statistics be renamed data science and statisticians data scientists. My career in Statistics involved working on data science, quality management, biostatistics, experimental design, causality models, customer surveys, compositional data, and other application domains. The implication is that, while there is considerable overlap between statistics and data science, the two are not the same. The talk will provide a statistician’s perspective on data science. The main message is that statistics needs to contribute its unique selling points (what marketing people call USPs) to the data science movement. That is, as statisticians, we need to propose methods and ideas that complement and extend the current development of data science. Over the years, I worked with colleagues on several frameworks that do so. The first framework was a simple approach to assessing impact that we labeled practical statistical efficiency (Kenett et al, 2003). The second one emphasizes a life-cycle view of statistics, starting from problem elicitation on through impact assessment (Kenett, 2015). The third framework is based on eight dimensions for assessing information quality, labeled InfoQ (Kenett and Shmueli, 2016). These dimensions can serve as a research roadmap for modern statistics. Examples of research in two of the InfoQ dimensions, Data Structure and Data Integration, will be mentioned. Moreover, building on John Tukey’s 1962 paper and Jeff Wu’s 1997 address, the role of data science (and data scientists) in organizations will be discussed on the basis of a forthcoming book on this topic (Kenett and Redman, 2019). Specifically, the talk will refer to the evolution of the leader in statistical methodology or Director of Statistical Methods advocated by Deming as necessary in organizations who aim to become more competitive (Deming, 1986). So, responding to Tukey, “the future is here, and it is called data science”, and Statistics has a major role in it.

1. Deming, W.E. (1986), Out of the Crisis. MIT Press, Cambridge, MA.
2. Kenett, R.S., Coleman, S.Y. and Stewardson, D. (2003), “Statistical Efficiency: The Practical Perspective,” Quality and Reliability Engineering International, 19, pp. 265-272.
3. Kenett, R.S. (2015), “Statistics: A Life Cycle View, Quality Engineering (with discussion),” 27(1), pp. 111-129.
4. Kenett, R.S and Shmueli, G. (2016), Information Quality: The Potential of Data and Analytics to Generate Knowledge, John Wiley and Sons.
5. Kenett, R.S. and Redman, T.C. (2019), The Real Work of Data Science: How to turn data into information, better decisions, and stronger organizations, John Wiley and Sons.
6. Tukey, J. (1962), “The Future of Data Analysis,” The Annals of Mathematical Statistics, 33, pp. 1–67.

Return to programme